CN102855524A - Carry-over storage year-end fluctuating level prediction method and system - Google Patents
Carry-over storage year-end fluctuating level prediction method and system Download PDFInfo
- Publication number
- CN102855524A CN102855524A CN2012102884192A CN201210288419A CN102855524A CN 102855524 A CN102855524 A CN 102855524A CN 2012102884192 A CN2012102884192 A CN 2012102884192A CN 201210288419 A CN201210288419 A CN 201210288419A CN 102855524 A CN102855524 A CN 102855524A
- Authority
- CN
- China
- Prior art keywords
- year
- reservoir
- storage
- model
- level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims description 112
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 103
- 230000001105 regulatory effect Effects 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 230000008878 coupling Effects 0.000 claims description 16
- 238000010168 coupling process Methods 0.000 claims description 16
- 238000005859 coupling reaction Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 13
- 230000005611 electricity Effects 0.000 claims description 6
- 238000009825 accumulation Methods 0.000 claims description 5
- 238000013459 approach Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000033228 biological regulation Effects 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 8
- 206010013647 Drowning Diseases 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000014759 maintenance of location Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- LOYTUFQOTJYLPX-UHFFFAOYSA-N C1=CC=[Si]C=C1 Chemical compound C1=CC=[Si]C=C1 LOYTUFQOTJYLPX-UHFFFAOYSA-N 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种多年调节水库年末消落水位预测方法及系统，所述方法包括以下步骤：S1，建立多年调节水库年末消落水位预测模型，并将其存储在模型库中；S2，预测服务器根据梯级总能量最大为优化调度目标，计算选择相应的多年调节水库年末消落水位预测模型；S3，预测服务器调用算法库中的模型求解算法，求解多年调节水库年末消落水位预测模型，得到年末消落水位规律。与现有技术相比，本发明求解过程简单，考虑了多年调节水库年末以后的调度后期效益，能够提高预测方法的准确性；与BP神经网络等方法相比，本发明更适用于径流资料系列不长的水库。
The invention discloses a method and system for predicting the end-of-year water level of a multi-year regulating reservoir. The method includes the following steps: S1, establishing a prediction model for the year-end water level of a multi-year regulating reservoir, and storing it in a model library; S2, predicting The server calculates and selects the corresponding prediction model of the year-end drawdown level of the multi-year regulating reservoir based on the maximum total energy of the cascade as the optimal scheduling target; S3, the forecasting server invokes the model solving algorithm in the algorithm library to solve the prediction model of the year-end drawdown level of the multi-year regulating reservoir, and obtains The law of water level at the end of the year. Compared with the prior art, the present invention has a simple solution process, considers the post-regulation benefits of multi-year regulation reservoirs after the end of the year, and can improve the accuracy of the prediction method; compared with methods such as BP neural network, the present invention is more suitable for runoff data series Not long reservoir.
Description
Technical field
The present invention relates to a kind of year-end level of multi-year regulating storage reservoir for timed position prediction method and system, belong to Cascade Reservoirs Optimized Operation field.
Background technology
From available data, very few about the research of year-end level of multi-year regulating storage reservoir for timed position both at home and abroad.On the one hand, because carry-over storage is actually rare; On the other hand, existing scheduling system take the quality of year as unit evaluation scheduling, do not take into full account the year-end level of multi-year regulating storage reservoir for timed position to the impact of future scheduling, so the research does not cause enough attention usually.In recent years, large-scale development along with the basin step power station, carry-over storage increases gradually, water power progressively participates in the competition of electricity market, the compensating action that carry-over storage is brought into play in cascade operation is increasing, so that being preferably for one of the focus in the step reservoir scheduling research and difficulties of year-end level of multi-year regulating storage reservoir for timed position.
The application mathematical statistics that Huang Qiang etc. (1999) propose, theory and the method for numerical analysis, study year-end level of multi-year regulating storage reservoir for timed position, imperial sheep gorge and played control law under the water transfer position in difference, and carried out venture analysis, the method is before setting up funtcional relationship, prior hypothesis CWinInetConnection type (namely linear, non-linear, caret function etc.), and year-end level of multi-year regulating storage reservoir for timed position Z disappears and principal element between relation sometimes be difficult to describe with a definite functional expression, directly affected the accuracy of the method.For the problems referred to above, Zhang Wenyi (2006) etc. improves the method, on the basis of the drowning position influence factor that at the end of utilizing Successive Regression to find out, disappears, utilize genetic algorithm and BP neural network algorithm, the year-end level of multi-year regulating storage reservoir for timed position is predicted, because the training need great amount of samples data of intelligent algorithm for the not long reservoir of Streamflow Data series, then are difficult to reach training requirement.Zou enters (2006) on the basis of analyzing carry-over storage hydropower station amount and reservoir accumulation of energy magnitude relation, set up the Fuzzy Multi-Objective Decision model of year-end level of multi-year regulating storage reservoir for timed position in definite step reservoir, but model weight coefficient when finding the solution is difficult to determine, and solution procedure is more loaded down with trivial details.Cross the Long-term Optimal Regulation for Reservoir model that the summer bright (2003) has proposed to consider rich withered tou power price, under disappearing drowning position some year ends of setting, added the electricity price factor to determine the optimal power generation strategy of generated energy maximum, but the method fails carry-over storage later scheduling later stage benefit at the year end is taken into account, and lacks foundation when falling into water the position so that this model disappears at the end of formulating.
Summary of the invention
The object of the invention is to, a kind of year-end level of multi-year regulating storage reservoir for timed position prediction method and system are provided, solution procedure is simple, considered carry-over storage later scheduling later stage benefit at the year end, can improve the accuracy of Forecasting Methodology, compare with the method such as BP neural network, the present invention more is applicable to the long reservoir of Streamflow Data series.
For solving the problems of the technologies described above, the present invention adopts following technical scheme: a kind of year-end level of multi-year regulating storage reservoir for timed position prediction method may further comprise the steps:
S1 sets up year-end level of multi-year regulating storage reservoir for timed position prediction model, and it is stored in the model bank;
S2, predictive server is the Optimized Operation target to the maximum according to the step gross energy, calculates and selects corresponding year-end level of multi-year regulating storage reservoir for timed position prediction model;
S3, predictive server is called the model solution algorithm in the algorithms library, finds the solution year-end level of multi-year regulating storage reservoir for timed position prediction model, obtains the position rule of falling into water that disappears the year end.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction method, year-end level of multi-year regulating storage reservoir for timed position prediction model comprises multiple goal coupling prediction model and the Successive Regression forecast model that excavates based on mathematical statistics.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction method,
(1) objective function of multiple goal coupling prediction model is: E=Max (E
d+ E
s), in the formula:
E is step reservoir generating gross energy, E
dFor step reservoir is worked as annual electricity generating capacity, E
sBe the accumulation of energy at the year end of carry-over storage,
Be objective function Ob:
In the formula: n is whole step reservoir number, and m is carry-over storage number in the step reservoir, and T is the period sum, K
iBe the comprehensive power factor of the reservoir that is numbered i, Q
I, tBe the reservoir that the is numbered i generating flow at period t, H
I, tBe the reservoir that the is numbered i generating net head at period t, A
jFor coefficient is A
j=K
j/ 3600, V
NjBe the carry-over storage that the is numbered j storage capacity at the year end,
For the carry-over storage that is numbered j holds the average productive head that stays storage capacity at the year end, if this carry-over storage downstream still has reservoir, then
Should be lower reservoir and hold the average productive head sum of staying storage capacity;
(2) constraint condition of multiple goal coupling prediction model comprises:
A water balance constraint: V (i, t+1)=V (i, t)+(Q
I(i, t)-Q
O(i, t)) * Δ t,
In the formula: V (i, t), V (i, t+1) represent respectively first, the last storage capacity of i reservoir t period; Q
I(i, t), Q
O(i, t) represents respectively warehouse-in and the outbound flow of i reservoir t period;
B flow equilibrium constraint: Q
I(i+1, t)=Q
O(i, t)+q (i, t),
In the formula: q (i, t) expression i and the local inflow of i+1 reservoir t period;
C water storage level constraint: Z
Min(i, t)≤Z (i, t)≤Z
Max(i, t),
In the formula: Z
Max(i, t), Z
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of water level;
D vent flow constraint: Q
Omin(i, t)≤Q
O(i, t)≤Q
Omax(i, t),
In the formula: Q
Omax(i, t), Q
Omin(i, t) represents respectively the upper and lower limit of i reservoir vent flow;
E output of power station constraint: N
Min(i, t)≤N (i, t)≤N
Max(i, t),
In the formula: N
Max(i, t), N
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of exerting oneself.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction method, application progressively optimize-approaches one by one dynamic programming (DPSA-POA) hybrid algorithm and finds the solution the multiple goal coupling prediction model.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction method, the finding the solution of Successive Regression forecast model of excavating based on mathematical statistics is based on the long serial combined optimization adjusting result of calculation of Cascade Reservoirs, use the stepwise regression analysis method, set up the nonlinear function of year-end level of multi-year regulating storage reservoir for timed position correlation factor, and it is carried out reasonableness test.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction method, stepwise regression method is when fitting function, according to the level of confidence of drafting, utilize the F check, operation is introduced or kicked out of to each factor, thereby automatically select optimum factor and make up fitting function, have larger elasticity and fitting precision.
Realize a kind of year-end level of multi-year regulating storage reservoir for timed position prediction system of preceding method, comprise forecast model storehouse, predictive server and algorithms library, predictive server is provided with the Model Selection module and the database that predicts the outcome, the Model Selection module is connected with forecast model storehouse, algorithms library respectively, algorithms library is connected with the database that predicts the outcome, wherein
The forecast model storehouse is used for storage year-end level of multi-year regulating storage reservoir for timed position prediction model;
The Model Selection module is used for predictive server and is the Optimized Operation target to the maximum according to the step gross energy, selects corresponding year-end level of multi-year regulating storage reservoir for timed position prediction model;
Algorithms library is used for storage and finds the solution year-end level of multi-year regulating storage reservoir for timed position prediction model;
The database that predicts the outcome is used for the position rule of falling into water that disappears at year end that the storage solving model obtains.
In the aforesaid year-end level of multi-year regulating storage reservoir for timed position prediction system, also be provided with long serial combined optimization on the predictive server and regulate computing module, long serial combined optimization is regulated computing module and is connected with algorithms library, the database that predicts the outcome respectively, be used for the long serial Streamflow Data of watershed and calculate, obtain long serial combined optimization and regulate result of calculation.
Compared with prior art, the present invention utilizes disappear when falling into water the position year end of multiple goal coupling prediction model research carry-over storage, can process preferably the generated energy of reservoir and the relation between the reservoir accumulation of energy contradiction target, this method has been taken into account reservoir generated energy then and the energy that stored in the reservoir in follow-up several years.But owing to the unknown to the water situation, the multi-objective predictive model does not fully take into account a few years from now on water to the impact of step reservoir scheduling, therefore, the present invention adopts the method for statistical law to set up year-end level of multi-year regulating storage reservoir for timed position prediction model, the Successive Regression forecast model that namely excavates based on mathematical statistics.Regulation o f reservoir operation is with concrete summarizes and the expression of historical summary to the reasonable moving law research of reservoir, can be used for instructing the following operation of reservoir.Based on the thinking of obtaining scheduling graph, consider to have storehouse group's cooperation of carry-over storage participation, can set up really qualitative mathematics model of multi-reservoir combined dispatching, then grow series and regulate calculating, obtain the long-term optimal operation plan of multi-reservoir, wherein also comprise the reasonable change rule of year-end level of multi-year regulating storage reservoir for timed position, it is carried out analytical calculation, then can draw control (prediction) rule (or function) of the drowning position that disappears the year end.Solution procedure of the present invention is simple, and has considered carry-over storage later scheduling later stage benefit at the year end, so that the accuracy of Forecasting Methodology has improved 5 ~ 8%.Because the methods such as the Forecasting Methodology that the present invention relates to and BP neural network are compared, and do not need long serial runoff sample data training network and then draft network parameter, therefore comparatively speaking, the present invention is more practical to the long reservoir of runoff data system.
Description of drawings
Fig. 1 is the workflow diagram of the embodiment of the invention;
Fig. 2 is that the different water frequency of reservoir lower step reservoir gross energy curve map crosses in flood man;
Fig. 3 is the different water frequency of goupitan reservoir lower step reservoir gross energy curve map;
Fig. 4 is water level and step gross energy graph of a relation at the beginning of flood man is crossed;
Fig. 5 is water level and step gross energy graph of a relation at the beginning of the Goupitan;
Fig. 6 is that the reservoir position change curve that falls into water that disappears the year end crosses in flood man;
Fig. 7 is the position change curve that falls into water that disappears at goupitan reservoir year end;
Fig. 8 is that two kinds of different model predictions of reservoir position comparison diagram that falls into water that disappears crosses in flood man;
Fig. 9 is two kinds of different model predictions of goupitan reservoir position comparison diagrams that fall into water that disappear;
Figure 10 is the system architecture schematic diagram of the embodiment of the invention.
Reference numeral: 1-forecast model storehouse, 2-Model Selection module, the 3-algorithms library, the 4-predictive server, the 5-database that predicts the outcome, the long serial combined optimization of 6-is regulated computing module.
The present invention is further illustrated below in conjunction with the drawings and specific embodiments.
Embodiment
Embodiments of the invention: the position prediction method of falling into water that disappears at the end of a kind of carry-over storage (Hong Jiadu of Wujiang River Basin, two reservoirs in Goupitan) as shown in Figure 1, may further comprise the steps:
S1 sets up year-end level of multi-year regulating storage reservoir for timed position prediction model, and it is stored in the model bank;
S2, predictive server is the Optimized Operation target to the maximum according to the step gross energy, calculates and selects corresponding year-end level of multi-year regulating storage reservoir for timed position prediction model;
S3, predictive server is called the model solution algorithm in the algorithms library, finds the solution year-end level of multi-year regulating storage reservoir for timed position prediction model, obtains the position rule of falling into water that disappears the year end.
Year-end level of multi-year regulating storage reservoir for timed position prediction model comprises multiple goal coupling prediction model and the Successive Regression forecast model that excavates based on mathematical statistics.
1, multiple goal coupling prediction model:
(1) objective function of multiple goal coupling prediction model is: E=Max (E
d+ E
s), in the formula:
E is step reservoir generating gross energy, E
dFor step reservoir is worked as annual electricity generating capacity, E
sBe the accumulation of energy at the year end of carry-over storage,
Be objective function Ob:
In the formula: n is whole step reservoir number, and m is carry-over storage number in the step reservoir, and T is the period sum, K
iBe the comprehensive power factor of the reservoir that is numbered i, Q
I, tBe the reservoir that the is numbered i generating flow at period t, H
I, tBe the reservoir that the is numbered i generating net head at period t, A
jFor coefficient is A
j=K
j/ 3600, V
NjBe the carry-over storage that the is numbered j storage capacity at the year end,
For the carry-over storage that is numbered j holds the average productive head that stays storage capacity at the year end, if this carry-over storage downstream still has reservoir, then
Should be lower reservoir and hold the average productive head sum of staying storage capacity;
(2) constraint condition of multiple goal coupling prediction model comprises:
A water balance constraint: V (i, t+1)=V (i, t)+(Q
I(i, t)-Q
O(i, t)) * Δ t,
In the formula: V (i, t), V (i, t+1) represent respectively first, the last storage capacity of i reservoir t period; Q
I(i, t), Q
O(i, t) represents respectively warehouse-in and the outbound flow of i reservoir t period;
B flow equilibrium constraint: Q
I(i+1, t)=Q
O(i, t)+q (i, t),
In the formula: q (i, t) expression i and the local inflow of i+1 reservoir t period;
C water storage level constraint: Z
Min(i, t)≤Z (i, t)≤Z
Max(i, t),
In the formula: Z
Max(i, t), Z
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of water level;
D vent flow constraint: Q
Omin(i, t)≤Q
O(i, t)≤Q
Omax(i, t),
In the formula: Q
Omax(i, t), Q
Omin(i, t) represents respectively the upper and lower limit of i reservoir vent flow;
E output of power station constraint: N
Min(i, t)≤N (i, t)≤N
Max(i, t),
In the formula: N
Max(i, t), N
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of exerting oneself.
Application progressively optimize-approaches one by one dynamic programming (DPSA-POA) hybrid algorithm and finds the solution the multiple goal coupling prediction model.Its solving result and analysis on its rationality are as follows:
Consider affect disappear the year end the fall into water factor of position of reservoir and mainly contain two: one is water level at the beginning of the reservoir, and another is exactly year to put a runoff in storage.At first, get identical warehouse-in runoff, analyze different beginning of the year water level to the impact of position of falling into water that disappears the year end of Hong Jiadu, goupitan reservoir; Secondly, get water level at the beginning of the identical reservoir, the warehouse-in runoff of analyzing different frequency is on the reservoir impact of position of falling into water that disappears the year end.In calculating, be to reduce the phase mutual interference between Hong Jiadu, two carry-over storages in Goupitan, cross reservoir in research flood man and disappear the year end when falling into water the position rule, the water level at the whole story of goupitan reservoir is decided to be 620m; Simultaneously, disappear at the end of the research goupitan reservoir when falling into water the position rule, Jiang Hongjia crosses reservoir water level at the whole story and is decided to be 1124m.
(1) impact of warehouse-in runoff
For analyzing the different runoff process of frequencies of putting in storage to the impact of year-end level of multi-year regulating storage reservoir for timed position, get flood man cross reservoir, Goupitan at the beginning of water level be respectively 1100m, 608m, use the DPSA algorithm above-mentioned Optimal Operation Model found the solution calculating, the result as table 1,2 and Fig. 2,3 shown in.
Station different frequency warehouse-in runoff process result of calculation table (unit: water level/m, energy/hundred million kWh) crosses in table 1 flood man
| |
5% | 10% | 20% | 30% | 40% | 50% | 60% | 70% | 80% | 90% | 95% |
| The year end water level | 1125 | 1120 | 1118 | 1113 | 1112 | 1110 | 1104 | 1098 | 1095 | 1091 | 1088 |
| Energy | 381.3 | 358.7 | 355.4 | 334 | 325.6 | 300.3 | 290.2 | 273.5 | 266 | 209.7 | 198.5 |
Table 2 Goupitan different frequency warehouse-in runoff process result of calculation table (unit: water level/m, energy/hundred million kWh)
| |
5% | 10% | 20% | 30% | 40% | 50% | 60% | 70% | 80% | 90% | 95% |
| The year |
620 | 619 | 618 | 617 | 616 | 615 | 614 | 612 | 608 | 602 | 600 |
| |
360 | 338.9 | 335.4 | 319.5 | 313.4 | 293.9 | 282.1 | 269.5 | 258.8 | 200.6 | 169.4 |
As shown in Table 1, flood man crossed reservoir and disappeared the year end and to fall into water the position generally about 1120m the high flow year, was not less than 1110m, played the effect of " holding rich "; Normal flow year generally about 1110m, is not less than water level at the beginning of the year; Low flow year generally is not higher than about 1100m, is not less than level of dead water 1076m, plays the effect of " mending withered ".
(2) impact analysis of water level at the beginning of
Discrete water level at the beginning of two carry-over storages, it is 50% corresponding 1992 warehouse-in runoff process that the warehouse-in runoff is got frequency, use DPSA and calculate, result of calculation as table 3,4 and Fig. 4,5 shown in.
The position result of calculation (P=50%) (unit: water level/m, energy/hundred million kWh) of falling into water that disappears at the end of the water level the different beginning of the years is crossed by table 3 flood man
| The beginning of the |
1080 | 1082 | 1084 | 1086 | 1088 | 1090 | 1092 | 1094 | 1096 | 1098 | 1100 |
| The year |
1085 | 1085 | 1086 | 1087 | 1089 | 1091 | 1094 | 1094 | 1099 | 1110 | 1111 |
| Energy | 298.7 | 299.9 | 301.3 | 302.5 | 304 | 305.4 | 307.1 | 308.6 | 310.1 | 311.7 | 313.9 |
| The beginning of the year water level | 1102 | 1104 | 1106 | 1108 | 1110 | 1115 | 1120 | 1125 | 1130 | 1135 | 1140 |
| The year end water level | 1112 | 1113 | 1116 | 1117 | 1118 | 1121 | 1128 | 1130 | 1131 | 1136 | 1139 |
| Energy | 316.6 | 319.1 | 321.1 | 323.3 | 325.6 | 331.3 | 337.4 | 343.5 | 349 | 356.6 | 364.2 |
The position result of calculation (P=50%) of falling into water disappears at the end of the water level at the beginning of the difference of table 4 Goupitan
(unit: water level/m, energy/hundred million kWh)
Under warehouse-in runoff and other equal conditions, from table 3 and Fig. 4,5 as can be known: if water level was lower than 1110m at the beginning of reservoir crossed in flood man, then its susceptibility that falls into water position influence to disappearing the year end is not clearly, and along with raising of water level at the beginning of the reservoir crossed by flood man, the position institute of falling into water of disappearing the year end is influenced larger.This mainly is because what adopt when calculating is normal flow year, the warehouse-in runoff belongs to not rich not withered situation, owing to being subject to the restriction that the step assurance is exerted oneself and minimum load retrains, if the beginning of the year, water level was lower, the water consumption rate of its unit of electrical energy is just larger, and corresponding water consumption is just larger, and if the beginning of the year water level higher, corresponding water consumption is less, and the water yield of saving just can increase its productive head again.Therefore the scheduling end of term, for having the leading reservoir of emphasizing to save performance in the step reservoir, begins have higher water level in schedule periods, for can be got back to high water stage and established certain basis.The goupitan reservoir gross energy is along with constantly the raising of water level at the beginning of the year as shown in Table 4, presents the trend of increase.
(3) Hong Jiadu, the goupitan reservoir position prediction result that falls into water that disappears the year end
Use above-mentioned model, can draw Hong Jiadu, the different warehouse-in of goupitan reservoir runoff and the position prediction result that falls into water that disappears at the end of the water level the different beginning of the years, shown in table 5,6.
The reservoir position prediction table (unit: m) that falls into water that disappears the year end crosses in table 5 flood man
Annotate: P is warehouse-in flow frequency (%).
Position prediction table (the unit: m) that falls into water disappears at the end of table 6 goupitan reservoir
Annotate: P is warehouse-in flow frequency (%).
The position multiple goal coupling of falling into water for disappearing at the end of Hong Jiadu, the Goupitan in the his-and-hers watches 5,6 predicts the outcome and carries out analysis on its rationality, and analog computation is carried out in this research application 1951.5 ~ 2007.4 totally 56 older series materials.At first according to the water level at the beginning of the year of the water frequency of calculating the time and Hong Jiadu, goupitan reservoir, fall into water according to determining in the table 5,6 that Hong Jiadu, goupitan reservoir disappear the year end thus; Use the maximum model of step reservoir generated energy again, carry out that optimal operation of cascade reservoirs calculates in year, for many years average generated energy, assurance exert oneself and generate electricity fraction and design load compares to step power station, and be as shown in table 7.
The long serial examination table of table 7 year-end level of multi-year regulating storage reservoir for timed position multiple goal coupling prediction model
As can be seen from the above table, the step after model calculates for many years average generated energy is 292.45 hundred million kWh, and comparing design load 289.7 hundred million kWh has increased by 0.9%, and the assurance of calculating is exerted oneself has increased by 8.37% for 2417.2MW compares design load 2230.4MW.Therefore, the drowning position rule that disappears at the end of the Hong Jiadu under this rule, the goupitan reservoir is rationally, reliably, can use in production practices.
2, the Successive Regression forecast model that excavates based on mathematical statistics:
It is based on the long serial combined optimization of Cascade Reservoirs and regulates result of calculation, uses the stepwise regression analysis method, sets up the nonlinear function of year-end level of multi-year regulating storage reservoir for timed position correlation factor, and it is carried out reasonableness test.
Stepwise regression method according to the level of confidence of drafting, utilizes the F check when fitting function, operation is introduced or kicked out of to each factor, makes up fitting function thereby automatically select optimum factor.The relevant initial regression vectors in position of falling into water of disappearing the year end is crossed by flood man to be had: Hong Jiadu then reservoir inflow and following several years reservoir inflow, Hong Jia cross water level at the beginning of the year, introduction cross reach then following several years outbound flow, Hong Jiadu-east wind-introduction crosses the following several years runoff reach of reservoir; The fall into water initial regression vectors of position of disappearing at goupitan reservoir year end has: goupitan reservoir is the water level and the outbound flow of following several years warehouse-in runoff (comprising the reservoir runoff reach) and Da Hua water at the beginning of the year of water level, the following several years runoff reach of Wu Jiangdu-goupitan reservoir, lower reservoir (Silin) at the beginning of reservoir inflow and following several years reservoir inflow, the goupitan reservoir then.The position influence factor of falling into water of disappearing the year end is crossed by flood man: flood man cross the beginning of the year water level and square, First Year reservoir inflow square, Second Year reservoir inflow, the 3rd year reservoir inflow square; The position influence factor of falling into water of disappearing at Goupitan year end is: at the beginning of the goupitan reservoir water level and square, Goupitan First Year reservoir inflow, Goupitan Second Year reservoir inflow, Goupitan the 4th year and the 5th year reservoir inflow.
When using the maximum model of step generated energy to grow series to calculate, for reduce as far as possible reservoir the whole story water level on the impact of regression model, this returns and calculates the adjusting calculating achievement that adopted 1952 ~ 2002 years and analyze.Choosing respectively level of confidence is 0.1 and 0.001, sets up the Successive Regression model, and result of calculation is as shown in table 8.Result in the associative list, and consider that the unitarity of upstream and downstream reservoir, this forecast model set up that unified to adopt level of confidence be 0.1, obtain Hong Jiadu and Goupitan Successive Regression forecast model respectively suc as formula 1, shown in the formula 2.
The different degree of confidence regression effects of table 8 relatively
Z
Year disappears=7144.898-11.06Z
1+ 5.0359 * 10
-3Z
1 2+ 5.5068 * 10
-4Q
1 2-6.2918 * 10
-3Q
2+ 1.2885 * 10
-4Q
3 2(formula 1)
Z
Year disappears=4320.053-11.96Z
1+ 0.01Z
1 2+ 0.1Q
1-0.04Q
2-0.06Q
4+ 0.03Q
5(formula 2)
Wherein: Z
Year disappearsBe the position of falling into water that disappears at year end of reservoir; Z
1Be water level at the beginning of this reservoir; Q
1, Q
2, Q
3, Q
4, Q
5For forecasting the water yield and forecast in rear 5 years then, this reservoir comes the water yield.
The forecast model solving result of Hong Jiadu, Goupitan is seen respectively Fig. 6,7.Flood man is crossed, two kinds of model predictions of goupitan reservoir disappear falls into water the position comparison diagram respectively shown in Fig. 8,9.
When the concrete use procedure of model, have the following suggestion can be for reference:
(1) because Goupitan year-end level of multi-year regulating storage reservoir for timed position influence many factors shows fully and statistical analysis method is very difficult, therefore can preferentially select the multi-objective predictive model;
(2) can find from Fig. 8, the predicting the outcome of two kinds of models that carry-over storage crosses in flood man is more or less the same, but for the low flow year, Statistical Prediction Model often predicted value is lower, cause like this step generated energy to increase, the adjusting function of considering the downstream goupitan reservoir is better, and therefore when water was more withered, the drowning position that disappears the year end is crossed by flood man can pay the utmost attention to Statistical Prediction Model;
(3) for the high flow year of Hong Jiadu, middle water year, two kinds of model prediction results are then comparatively close.In the actual use procedure, the drowning position that disappears the year end of Hong Jiadu, two carry-over storages in Goupitan can be predicted respectively by two kinds of models, then according to the actual conditions of producing, controls in conjunction with yardman's operating experience.
Realize a kind of year-end level of multi-year regulating storage reservoir for timed position prediction system of preceding method, as shown in figure 10, comprise forecast model storehouse 1, predictive server 4 and algorithms library 3, predictive server 4 is provided with Model Selection module 2 and the database 5 that predicts the outcome, Model Selection module 2 is connected with forecast model storehouse 1, algorithms library 3 respectively, algorithms library 3 is connected with the database 5 that predicts the outcome, wherein
The database 5 that predicts the outcome is used for the position rule of falling into water that disappears at year end that the storage solving model obtains.
Also be provided with long serial combined optimization on the predictive server 4 and regulate computing module 6, long serial combined optimization is regulated computing module 6 and is connected with algorithms library 3, the database 5 that predicts the outcome respectively, be used for the long serial Streamflow Data of watershed and calculate, obtain long serial combined optimization and regulate result of calculation.
Claims (8)
1. a year-end level of multi-year regulating storage reservoir for timed position prediction method is characterized in that, may further comprise the steps:
S1 sets up year-end level of multi-year regulating storage reservoir for timed position prediction model, and it is stored in the model bank;
S2, predictive server is the Optimized Operation target to the maximum according to the step gross energy, calculates and selects corresponding year-end level of multi-year regulating storage reservoir for timed position prediction model;
S3, predictive server is called the model solution algorithm in the algorithms library, finds the solution year-end level of multi-year regulating storage reservoir for timed position prediction model, obtains the position rule of falling into water that disappears the year end.
2. year-end level of multi-year regulating storage reservoir for timed position prediction method according to claim 1 is characterized in that: year-end level of multi-year regulating storage reservoir for timed position prediction model comprises multiple goal coupling prediction model and the Successive Regression forecast model that excavates based on mathematical statistics.
3. year-end level of multi-year regulating storage reservoir for timed position prediction method according to claim 2 is characterized in that:
(1) objective function of multiple goal coupling prediction model is: E=Max (E
d+ E
s), in the formula:
E is step reservoir generating gross energy, E
dFor step reservoir is worked as annual electricity generating capacity, E
sBe the accumulation of energy at the year end of carry-over storage,
Be objective function Ob:
In the formula: n is whole step reservoir number, and m is carry-over storage number in the step reservoir, and T is the period sum, K
iBe the comprehensive power factor of the reservoir that is numbered i, Q
I, tBe the reservoir that the is numbered i generating flow at period t, H
I, tBe the reservoir that the is numbered i generating net head at period t, A
jFor coefficient is A
j=K
j/ 3600, V
NjBe the carry-over storage that the is numbered j storage capacity at the year end,
For the carry-over storage that is numbered j holds the average productive head that stays storage capacity at the year end, if this carry-over storage downstream still has reservoir, then
Should be lower reservoir and hold the average productive head sum of staying storage capacity;
(2) constraint condition of multiple goal coupling prediction model comprises:
A water balance constraint: V (i, t+1)=V (i, t)+(Q
I(i, t)-Q
O(i, t)) * Δ t,
In the formula: V (i, t), V (i, t+1) represent respectively first, the last storage capacity of i reservoir t period; Q
I(i, t), Q
O(i, t) represents respectively warehouse-in and the outbound flow of i reservoir t period;
B flow equilibrium constraint: Q
I(i+1, t)=Q
O(i, t)+q (i, t),
In the formula: q (i, t) expression i and the local inflow of i+1 reservoir t period;
C water storage level constraint: Z
Min(i, t)≤Z (i, t)≤Z
Max(i, t),
In the formula: Z
Max(i, t), Z
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of water level;
D vent flow constraint: Q
Omin(i, t)≤Q
O(i, t)≤Q
Omax(i, t),
In the formula: Q
Omax(i, t), Q
Omin(i, t) represents respectively the upper and lower limit of i reservoir vent flow;
E output of power station constraint: N
Min(i, t)≤N (i, t)≤N
Max(i, t),
In the formula: N
Max(i, t), N
Min(i, t) represents that respectively i reservoir t period allows the upper and lower limit of exerting oneself.
4. it is characterized in that according to claim 2 or 3 described year-end level of multi-year regulating storage reservoir for timed position prediction methods: use and progressively optimize-approach one by one the dynamic programming hybrid algorithm and find the solution the multiple goal coupling prediction model.
5. year-end level of multi-year regulating storage reservoir for timed position prediction method according to claim 2, it is characterized in that: the finding the solution of Successive Regression forecast model of excavating based on mathematical statistics is based on the long serial combined optimization adjusting result of calculation of Cascade Reservoirs, use the stepwise regression analysis method, set up the nonlinear function of year-end level of multi-year regulating storage reservoir for timed position correlation factor, and it is carried out reasonableness test.
6. year-end level of multi-year regulating storage reservoir for timed position prediction method according to claim 5, it is characterized in that: stepwise regression method is when fitting function, according to the level of confidence of drafting, utilize the F check, operation is introduced or kicked out of to each factor, make up fitting function thereby automatically select optimum factor.
7. realize a kind of year-end level of multi-year regulating storage reservoir for timed position prediction system of the described method of claim 1～6, it is characterized in that: comprise forecast model storehouse (1), predictive server (4) and algorithms library (3), predictive server (4) is provided with Model Selection module (2) and the database that predicts the outcome (5), Model Selection module (2) respectively with forecast model storehouse (1), algorithms library (3) connects, algorithms library (3) is connected with the database that predicts the outcome (5), wherein
Forecast model storehouse (1) is used for storage year-end level of multi-year regulating storage reservoir for timed position prediction model; Model Selection module (2) is used for predictive server (4) and is the Optimized Operation target to the maximum according to the step gross energy, selects corresponding year-end level of multi-year regulating storage reservoir for timed position prediction model;
Algorithms library (3) is used for storage and finds the solution year-end level of multi-year regulating storage reservoir for timed position prediction model;
The database (5) that predicts the outcome is used for the position rule of falling into water that disappears at year end that the storage solving model obtains.
8. year-end level of multi-year regulating storage reservoir for timed position prediction according to claim 7 system, it is characterized in that: also be provided with long serial combined optimization on the predictive server (4) and regulate computing module (6), long serial combined optimization is regulated computing module (6) and is connected with algorithms library (3), the database that predicts the outcome (5) respectively, be used for the long serial Streamflow Data of watershed and calculate, obtain long serial combined optimization and regulate result of calculation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102884192A CN102855524A (en) | 2012-08-14 | 2012-08-14 | Carry-over storage year-end fluctuating level prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102884192A CN102855524A (en) | 2012-08-14 | 2012-08-14 | Carry-over storage year-end fluctuating level prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102855524A true CN102855524A (en) | 2013-01-02 |
Family
ID=47402097
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102884192A Pending CN102855524A (en) | 2012-08-14 | 2012-08-14 | Carry-over storage year-end fluctuating level prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102855524A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065226A (en) * | 2013-01-05 | 2013-04-24 | 桂林电子科技大学 | Hydropower station reservoir long-term optimal operation decision water-level determination method |
| CN105096216A (en) * | 2015-09-01 | 2015-11-25 | 中国长江电力股份有限公司 | Method for fast calculating electric energy production of hydropower station |
| CN105550944A (en) * | 2016-01-21 | 2016-05-04 | 武汉大学 | Method for determining firm capacity and annual average generating capacity of carry-over storage |
| CN105719020A (en) * | 2016-01-21 | 2016-06-29 | 武汉大学 | Carry-over storage year-end water storage level determining method |
| CN105787589A (en) * | 2016-02-26 | 2016-07-20 | 黄河勘测规划设计有限公司 | Optimum control method for carry-over storage drought limitation water level and dedicated control system |
| CN106485346A (en) * | 2016-09-18 | 2017-03-08 | 武汉大学 | A kind of series-parallel connection reservoir impoundment ahead Multiobjective Optimal Operation method |
| TWI587222B (en) * | 2016-06-29 | 2017-06-11 | 台灣電力股份有限公司 | Neural networks based water level predicting system and method for reservoirs |
| CN107144317A (en) * | 2017-05-16 | 2017-09-08 | 中冶赛迪装备有限公司 | A kind of Intelligent liquid level meter |
| CN108764539A (en) * | 2018-05-15 | 2018-11-06 | 中国长江电力股份有限公司 | A kind of water levels of upstream and downstream prediction technique of step hydropower station |
| CN108921279A (en) * | 2018-03-26 | 2018-11-30 | 西安电子科技大学 | Reservoir day enters water prediction technique |
| CN109492802A (en) * | 2018-10-30 | 2019-03-19 | 河海大学 | A kind of year-end level of multi-year regulating storage reservoir for timed position preferred method based on expert system |
| CN111445061A (en) * | 2020-03-07 | 2020-07-24 | 华中科技大学 | Determination method of year-end ebb and flow level of multi-year regulating reservoir considering differences in inflow frequency |
| CN111832900A (en) * | 2020-06-15 | 2020-10-27 | 华中科技大学 | A dynamic control method for year-end ebb and flow of a multi-year reservoir |
| CN113919719A (en) * | 2021-10-18 | 2022-01-11 | 河南郑大水利科技有限公司 | Method and system for calculating power generation flow of radial flow type hydropower station and method for adjusting output |
| CN115082257A (en) * | 2022-06-20 | 2022-09-20 | 中国水利水电科学研究院 | Evaluation method for the impact of downstream tailwater level rise on the annual power generation of the hydropower station in operation |
| CN116226687A (en) * | 2023-05-10 | 2023-06-06 | 长江三峡集团实业发展(北京)有限公司 | Reservoir daily initial water level estimation method and device based on data mining technology |
| CN119476770A (en) * | 2024-10-10 | 2025-02-18 | 中国长江三峡集团有限公司 | A method and device for generating an optimal dispatching scheme for cascade reservoir drawdown period |
| CN119765509A (en) * | 2025-03-05 | 2025-04-04 | 云南华电金沙江中游水电开发有限公司 | Quick generation method for medium-long term power generation scheduling decision in flood control and water storage reservoir |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101408769A (en) * | 2008-11-21 | 2009-04-15 | 冶金自动化研究设计院 | On-line energy forecasting system and method based on product ARIMA model |
| US20090132448A1 (en) * | 2000-10-17 | 2009-05-21 | Jeffrey Scott Eder | Segmented predictive model system |
| CN101783075A (en) * | 2010-02-05 | 2010-07-21 | 北京科技大学 | System for forecasting traffic flow of urban ring-shaped roads |
-
2012
- 2012-08-14 CN CN2012102884192A patent/CN102855524A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090132448A1 (en) * | 2000-10-17 | 2009-05-21 | Jeffrey Scott Eder | Segmented predictive model system |
| CN101408769A (en) * | 2008-11-21 | 2009-04-15 | 冶金自动化研究设计院 | On-line energy forecasting system and method based on product ARIMA model |
| CN101783075A (en) * | 2010-02-05 | 2010-07-21 | 北京科技大学 | System for forecasting traffic flow of urban ring-shaped roads |
Non-Patent Citations (1)
| Title |
|---|
| 刘晋: "乌江梯级七库中长期发电优化调度研究", 《中国优秀硕士学位论文全文库》, no. 1, 15 January 2011 (2011-01-15) * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103065226B (en) * | 2013-01-05 | 2015-07-08 | 桂林电子科技大学 | Hydropower station reservoir long-term optimal operation decision water-level determination method |
| CN103065226A (en) * | 2013-01-05 | 2013-04-24 | 桂林电子科技大学 | Hydropower station reservoir long-term optimal operation decision water-level determination method |
| CN105096216B (en) * | 2015-09-01 | 2018-07-31 | 中国长江电力股份有限公司 | A kind of method of quick calculating hydropower station amount |
| CN105096216A (en) * | 2015-09-01 | 2015-11-25 | 中国长江电力股份有限公司 | Method for fast calculating electric energy production of hydropower station |
| CN105550944A (en) * | 2016-01-21 | 2016-05-04 | 武汉大学 | Method for determining firm capacity and annual average generating capacity of carry-over storage |
| CN105719020A (en) * | 2016-01-21 | 2016-06-29 | 武汉大学 | Carry-over storage year-end water storage level determining method |
| CN105550944B (en) * | 2016-01-21 | 2020-06-23 | 武汉大学 | Method for determining guaranteed output and annual average generated energy of perennial regulation reservoir |
| CN105787589A (en) * | 2016-02-26 | 2016-07-20 | 黄河勘测规划设计有限公司 | Optimum control method for carry-over storage drought limitation water level and dedicated control system |
| CN105787589B (en) * | 2016-02-26 | 2019-04-26 | 黄河勘测规划设计研究院有限公司 | Carry-over storage drought is restricted water supply the method for optimally controlling and dedicated control system of position |
| TWI587222B (en) * | 2016-06-29 | 2017-06-11 | 台灣電力股份有限公司 | Neural networks based water level predicting system and method for reservoirs |
| CN106485346A (en) * | 2016-09-18 | 2017-03-08 | 武汉大学 | A kind of series-parallel connection reservoir impoundment ahead Multiobjective Optimal Operation method |
| CN107144317A (en) * | 2017-05-16 | 2017-09-08 | 中冶赛迪装备有限公司 | A kind of Intelligent liquid level meter |
| CN108921279A (en) * | 2018-03-26 | 2018-11-30 | 西安电子科技大学 | Reservoir day enters water prediction technique |
| CN108764539A (en) * | 2018-05-15 | 2018-11-06 | 中国长江电力股份有限公司 | A kind of water levels of upstream and downstream prediction technique of step hydropower station |
| CN108764539B (en) * | 2018-05-15 | 2021-10-15 | 中国长江电力股份有限公司 | Upstream and downstream water level prediction method for cascade power station |
| CN109492802A (en) * | 2018-10-30 | 2019-03-19 | 河海大学 | A kind of year-end level of multi-year regulating storage reservoir for timed position preferred method based on expert system |
| CN111445061A (en) * | 2020-03-07 | 2020-07-24 | 华中科技大学 | Determination method of year-end ebb and flow level of multi-year regulating reservoir considering differences in inflow frequency |
| CN111445061B (en) * | 2020-03-07 | 2022-07-19 | 华中科技大学 | Determination method for year-end fluctuating level of regulated reservoir by considering incoming flow frequency difference |
| CN111832900A (en) * | 2020-06-15 | 2020-10-27 | 华中科技大学 | A dynamic control method for year-end ebb and flow of a multi-year reservoir |
| CN111832900B (en) * | 2020-06-15 | 2024-02-09 | 华中科技大学 | Dynamic control method for regulating water level of reservoir at end of year |
| CN113919719A (en) * | 2021-10-18 | 2022-01-11 | 河南郑大水利科技有限公司 | Method and system for calculating power generation flow of radial flow type hydropower station and method for adjusting output |
| CN113919719B (en) * | 2021-10-18 | 2024-10-25 | 河南郑大水利科技有限公司 | Calculation method, system and output adjustment method for power generation flow of radial-flow hydropower station |
| CN115082257A (en) * | 2022-06-20 | 2022-09-20 | 中国水利水电科学研究院 | Evaluation method for the impact of downstream tailwater level rise on the annual power generation of the hydropower station in operation |
| CN116226687A (en) * | 2023-05-10 | 2023-06-06 | 长江三峡集团实业发展(北京)有限公司 | Reservoir daily initial water level estimation method and device based on data mining technology |
| CN119476770A (en) * | 2024-10-10 | 2025-02-18 | 中国长江三峡集团有限公司 | A method and device for generating an optimal dispatching scheme for cascade reservoir drawdown period |
| CN119765509A (en) * | 2025-03-05 | 2025-04-04 | 云南华电金沙江中游水电开发有限公司 | Quick generation method for medium-long term power generation scheduling decision in flood control and water storage reservoir |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102855524A (en) | Carry-over storage year-end fluctuating level prediction method and system | |
| Xu et al. | Predicting river dissolved oxygen time series based on stand-alone models and hybrid wavelet-based models | |
| CN112184070B (en) | A multi-objective optimal scheduling method and system for cascade hydropower stations with coordinated ecological flow demand | |
| CN108985585B (en) | Reservoir flood resource utilization risk hedging decision method considering forecast uncertainty influence | |
| CN105243438A (en) | Multi-year regulating storage reservoir optimal scheduling method considering runoff uncertainty | |
| CN114723230B (en) | Microgrid dual-layer dispatching method and system for renewable energy generation and energy storage | |
| CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
| CN106682810A (en) | Method for operating cross-basin cascade hydropower station groups under condition of dynamic commissioning of giant hydropower stations for long term | |
| CN108734378A (en) | A kind of reservoir operation state of risk groups Decision Method under the conditions of imperfect information | |
| CN108596242A (en) | Power grid meteorology load forecasting method based on wavelet neural network and support vector machines | |
| CN119515016B (en) | A method for ecological regulation of river-lake systems coupled with basin hydrological response | |
| CN107565585A (en) | Energy storage device peak regulation report-back time Forecasting Methodology and its model creation method | |
| CN114548609B (en) | Water resource collaborative allocation method for ecological power generation and water supply | |
| CN112001581A (en) | Power grid electric power quantity balancing method | |
| CN115809718A (en) | Multi-objective competition relationship quantification-based cascade power station power generation and ecological collaborative optimization method and system | |
| Liu et al. | Quantifying streamflow predictive uncertainty for the optimization of short-term cascade hydropower stations operations | |
| CN106570786B (en) | A Reservoir Adaptive Scheduling Method Based on Time-varying Characteristics of Scheduling Rules | |
| Liu et al. | Effect of the quality of streamflow forecasts on the operation of cascade hydropower stations using stochastic optimization models | |
| Zhang et al. | Optimized scheduling of cascade hydropower stations with advance risk control in dynamic operations | |
| Shu et al. | Value of long-term inflow forecast for hydropower operation: A case study in a low forecast precision region | |
| CN108615091B (en) | Electric power meteorological load data prediction method based on cluster screening and neural network | |
| CN117833351A (en) | A new energy power system operation risk online assessment method and system | |
| CN111079066B (en) | A Method for Analyzing the Competitive Relationship between Reservoir Group Power Generation Ecological Two Objectives | |
| CN104778512B (en) | Meter and the moon dispatching method of energy-conservation risk assessment | |
| CN119623784B (en) | Combined scheduling method and device for runoff prediction and hydro-power-hydrogen system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130102 |
|
| WD01 | Invention patent application deemed withdrawn after publication |