[go: up one dir, main page]

CN111507766B - Microgrid electric power big data transaction management system applying block chains and artificial intelligence - Google Patents

Microgrid electric power big data transaction management system applying block chains and artificial intelligence Download PDF

Info

Publication number
CN111507766B
CN111507766B CN202010301731.5A CN202010301731A CN111507766B CN 111507766 B CN111507766 B CN 111507766B CN 202010301731 A CN202010301731 A CN 202010301731A CN 111507766 B CN111507766 B CN 111507766B
Authority
CN
China
Prior art keywords
electricity
signal
power generation
power
price
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.)
Active
Application number
CN202010301731.5A
Other languages
Chinese (zh)
Other versions
CN111507766A (en
Inventor
林峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siping Power Supply Co of State Grid Jilin Electric Power Co Ltd
Original Assignee
Ningbo Qianyi Energy Saving Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ningbo Qianyi Energy Saving Technology Co ltd filed Critical Ningbo Qianyi Energy Saving Technology Co ltd
Priority to CN202010301731.5A priority Critical patent/CN111507766B/en
Publication of CN111507766A publication Critical patent/CN111507766A/en
Application granted granted Critical
Publication of CN111507766B publication Critical patent/CN111507766B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0206—Price or cost determination based on market factors
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
    • Y04S50/14—Marketing, i.e. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Water Supply & Treatment (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Human Resources & Organizations (AREA)
  • Primary Health Care (AREA)
  • Game Theory and Decision Science (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本发明公开了一种应用区块链和人工智能的微电网电力大数据交易管理系统，包括购电接收模块根据用电侧以往的用电数据记录整理出已完成交易的购电单价，并记录用电侧本次需要购买的电量，电价调整模块将已完成交易的购电单价的平均值作为初始电价，并比较当前所有发电侧的发电总量和所有用电侧需要购买的总电量，智能匹配模块筛选能够满足用电侧需要购买的电量的发电侧，并选择合适的发电侧进行匹配；本发明在人工智能的基础上同时结合区块链技术，增强了交易管理系统的智能化、去中心化以及数据的不可篡改性。

Figure 202010301731

The invention discloses a microgrid power big data transaction management system applying blockchain and artificial intelligence, comprising a power purchase receiving module that sorts out the power purchase unit price of the completed transaction according to the previous power consumption data records on the power consumption side, and records The electricity price that needs to be purchased on the electricity side this time, the electricity price adjustment module takes the average value of the electricity purchase unit price of the completed transaction as the initial electricity price, and compares the current total power generation of all power generation sides with the total electricity that needs to be purchased on all electricity consumption sides. The matching module screens the power generation side that can satisfy the electricity that needs to be purchased by the power consumption side, and selects the appropriate power generation side for matching; the invention combines the blockchain technology on the basis of artificial intelligence, and enhances the intelligence of the transaction management system. Centralization and immutability of data.

Figure 202010301731

Description

Microgrid electric power big data transaction management system applying block chains and artificial intelligence
Technical Field
The invention relates to electric power transaction management, in particular to a microgrid electric power big data transaction management system applying block chains and artificial intelligence.
Background
At present, electric power transactions are concentrated on a small number of large platforms, the centralization degree is serious, benefit control of a power generation side and a power utilization side is concentrated on the platforms, faults of an electric power system are easy to occur, and the influence range is enlarged; because the transactions of the power generation side and the power utilization side do not need to meet, the key requirements of all parties participating in the transactions need to be solved, the accuracy and rapidness of the transactions are strived for, and thus the traditional power transactions lack personalized adjustment and the unrelated transactions are influenced. The generation and development of the block chain technology can seek some ways for solving the problem of over-centralized power transaction, so that the power transaction is more fair and all parties can obtain benefits from the power transaction.
Many power trading systems allocate power generation side resources according to matching of power supply and power utilization, so that real-time and effective allocation of power resources is achieved, but the problems of geographical positions of power allocation, power utilization loss, power utilization power and the like are not comprehensively considered in such a mode. Along with the reduction of the main bodies of electric power participation, the appearance of productive consumers and the electricity consumption of some flexible loads, the complexity of the electric power transaction layer is higher, the difficulty degree of electric power transaction operation is greatly increased by the simultaneous participation of all the main bodies, the uneven distribution of electric power resources sometimes occurs, and the stability is poor. In the aspect of transaction matching, most systems can guess the transaction situation, but the existing prediction means has disadvantages due to large fluctuation of historical data, strong time-varying characteristics, nonlinearity and the like, so that the guess error is possibly large, and the generation and the execution of the transaction are further influenced.
Disclosure of Invention
The invention provides a microgrid electric power big data transaction management system applying a block chain and artificial intelligence to solve the problems.
A microgrid electric power big data transaction management system applying block chains and artificial intelligence comprises:
the electricity purchasing receiving module is used for sorting out the electricity purchasing unit price after the transaction is finished according to the past electricity utilization data record of the electricity utilization side and recording the electric quantity required to be purchased by the electricity utilization side at this time;
the electricity price adjusting module is used for taking the average value of the electricity purchasing prices which have finished the transaction as the initial electricity price, comparing the total electricity generation quantity of all current electricity generation sides with the total electricity quantity which needs to be purchased by all electricity utilization sides, reducing the initial electricity price as the current electricity price according to a preset value when the total electricity generation quantity is larger than the total electricity quantity which needs to be purchased, and increasing the initial electricity price as the current electricity price according to the preset value when the total electricity generation quantity is smaller than the total electricity quantity which needs to be purchased;
the intelligent matching module is used for screening power generation sides capable of meeting the electric quantity required to be purchased by the power utilization side, and selecting proper power generation sides for matching according to response signals generated by the power generation sides during past transactions;
the total price calculating module is used for calculating the total electricity purchasing price of the electricity utilization side according to the electric quantity required to be purchased by the electricity utilization side and the current electricity price and sending the total electricity purchasing price to the electricity generation side;
after the power generation side confirms the total price of electricity purchase, the transaction generation module generates the transaction and receives a response signal generated by the power generation side, and transmits the transaction electric quantity, the total price of electricity purchase, the information of the power utilization side, the information of the power generation side and the response signal generated by the power generation side corresponding to the transaction to the block chain;
and the butt joint arrangement module is used for sending the total price of electricity purchase to the electricity utilization side for payment, distributing corresponding electric quantity after the payment is successful and finishing the transaction.
The transaction management system provided by the invention enables the transaction to be more accurate and rapid, the progress among the transactions cannot be influenced mutually, and less system resources are occupied; the demand characteristics of each transaction participant are provided, the transaction is generated in a personalized manner, and the intellectualization, the decentralization and the data non-tamper property of the transaction system are enhanced by combining the block chain technology on the basis of artificial intelligence.
According to the invention, the response signal of the power generation side is serialized and decomposed into a plurality of intermediate signal sets and residual signal sets, and the response of the power generation side to the transaction is conjectured by using the recurrent neural network, so that the accuracy of conjecture of the current transaction is improved, the matching degree between the power generation side and the power utilization side is enhanced, the distribution of electric power is more reasonable, and users of the power generation side and the power utilization side can obtain profits from the electric power.
The probability condition that the power generation side is separated from the microgrid is used for evaluating, the dynamic stability between the power supply and the load of the microgrid when the microgrid receives disturbance is predicted, and the corresponding power is obtained from the power generation side in the later period through the mean value calculation of the emergency power, so that the microgrid can keep the power supply to the power utilization side when the power generation side is separated, and the normal operation of power transaction cannot be lost due to the separation of the power generation side.
Drawings
FIG. 1 is a system diagram of the transaction management system of the present invention.
Detailed Description
The invention is further illustrated by the following specific examples:
a microgrid electric power big data transaction management method applying block chains and artificial intelligence comprises the following steps:
the electricity purchasing receiving module sorts out the electricity purchasing unit price of the completed transaction according to the past electricity consumption data record of the electricity consumption side and records the electric quantity required to be purchased by the electricity consumption side at this time;
the electricity price adjusting module takes the average value of the electricity purchasing prices which have finished the transaction as the initial electricity price, compares the total electricity generation amount of all current electricity generation sides with the total electricity quantity which needs to be purchased by all electricity utilization sides, reduces the initial electricity price according to a preset value to be taken as the current electricity price when the total electricity generation amount is larger than the total electricity quantity which needs to be purchased, and increases the initial electricity price according to the preset value to be taken as the current electricity price when the total electricity generation amount is smaller than the total electricity quantity which needs to be purchased;
the intelligent matching module screens the power generation side capable of meeting the electric quantity required to be purchased by the power utilization side, and selects a proper power generation side for matching according to a response signal generated by the power generation side in the past transaction;
the total price calculating module calculates the total electricity purchasing price of the electricity utilization side according to the electric quantity required to be purchased by the electricity utilization side and the current electricity price, and sends the total electricity purchasing price to the electricity generation side;
after the power generation side confirms the total price of electricity purchase, the transaction generation module generates the transaction and receives a response signal generated by the power generation side, and transmits the transaction electric quantity, the total price of electricity purchase, the information of the power utilization side, the information of the power generation side and the response signal generated by the power generation side corresponding to the transaction to the block chain;
and the butt joint arrangement module sends the total price of the electricity purchase to the electricity utilization side for payment, and after the payment is successful, corresponding electric quantity is distributed and the transaction is ended.
Further, the specific steps of selecting a proper power generation side for matching according to a response signal generated by the power generation side during the past transaction are as follows:
(1) acquiring a response signal of the power generation side during the past transaction from the block chain, checking the response signal, and marking the incomplete signal as a incomplete signal;
(2) arranging the rest signals from small to large and dividing the rest signals into four equal parts, wherein the signals at the three division positions are respectively a first division signal, a second division signal and a third division signal, and 1.5 times of the difference between the first division signal and the third division signal is marked as an abnormal difference;
(3) marking the signals which are higher than the abnormal difference above the third segmentation signal or lower than the abnormal difference below the first segmentation signal as abnormal signals;
(4) analyzing a change trend curve of the signal by using a linear regression mode on the non-incomplete and non-abnormal signal by taking time as a variable;
(5) extracting an error value of each signal and a corresponding point on the change trend curve, training a distributed gradient enhancement library according to the time corresponding to the signal and the error value, and predicting the error values of the incomplete signal and the abnormal signal according to the distributed gradient enhancement library;
(6) correcting the incomplete signals and the abnormal signals based on the variation trend curve and the predicted error values to obtain normal signals, and arranging the normal signals into a signal set according to a time sequence;
(7) determining local extreme points of the signal set, fitting an envelope of a relative maximum point and an envelope of a relative minimum point by using Spline interpolation, and obtaining an average value of the envelope and the envelope, namely an average envelope;
(8) judging the difference between the number of times of the signal set passing through the zero point and the number of opposite poles, if not more than one, taking the signal set as an intermediate signal set and skipping the step (9), and if more than one, judging whether the average envelope is zero;
(9) if the average envelope is zero, taking the signal set as an intermediate signal set, if the average envelope is not zero, subtracting the average envelope from the signal set to obtain a new signal set, and repeating the step (7);
(10) storing the intermediate signal set and judging whether the result of subtracting the intermediate signal set from the signal set is a monotone queue, if so, taking the result as a residual signal set and skipping the step (11), and if not, judging whether all signals in the result are the same;
(11) if all the signals in the result are the same, taking the result as a residual signal set, and if the signals in the result are not the same, taking the result as a new signal set and repeating the step (7);
(12) for all the signals in the stored intermediate signal set and residual signal set, reducing the amplitude of each signal, and inputting the intermediate signal set and residual signal set with reduced amplitudes into a recurrent neural network for training; the method of reducing the amplitude of each signal is: recording the difference between the minimum value in a signal and the non-reduced signal as a first difference value, recording the difference between the maximum value and the minimum value in the non-reduced signal as a second difference value, multiplying the ratio of the first difference value to the second difference value by two, and recording as a third calculation value, wherein the result of subtracting one from the third calculation value is the value of the signal after the amplitude is reduced;
(13) and outputting the speculative value of the response signal of the current transaction power generation side by using the trained recurrent neural network, and selecting the power generation side with the maximum signal speculative value to match with the power utilization side.
When a certain power generation side is separated from the microgrid, the probability that the power generation side is separated from the microgrid is obtained from historical data and recorded as ht；
And disconnecting the electric quantity transaction corresponding to the power generation side, and calculating the descending emergency electric quantity mean value w of the micro-grid within the time T in the process that the power generation side is separated from the micro-grid as follows:
Figure BDA0002454248390000061
wherein OB ═ MT-Pt,T-Mt,T；
g (E) is the probability of the generation of a non-random error E of the microgrid within a time T, and obeys standard normal distribution, MTIs the maximum non-random error value, M, that the microgrid can bear during the time Tt,TIs the maximum non-random error value, P, that the microgrid can bear within the time T after the power generation side is separated from the microgridt,TThe generated power at the power generation side in the time T;
and when the power generation side is reconnected to the microgrid, the microgrid acquires corresponding electric quantity from the power generation side according to the calculated average value of the descending emergency electric quantity.
A microgrid electric power big data transaction management system applying block chains and artificial intelligence comprises:
the electricity purchasing receiving module is used for sorting out the electricity purchasing unit price after the transaction is finished according to the past electricity utilization data record of the electricity utilization side and recording the electric quantity required to be purchased by the electricity utilization side at this time;
the electricity price adjusting module is used for taking the average value of the electricity purchasing prices which have finished the transaction as the initial electricity price, comparing the total electricity generation quantity of all current electricity generation sides with the total electricity quantity which needs to be purchased by all electricity utilization sides, reducing the initial electricity price as the current electricity price according to a preset value when the total electricity generation quantity is larger than the total electricity quantity which needs to be purchased, and increasing the initial electricity price as the current electricity price according to the preset value when the total electricity generation quantity is smaller than the total electricity quantity which needs to be purchased;
the intelligent matching module is used for screening power generation sides capable of meeting the electric quantity required to be purchased by the power utilization side, and selecting proper power generation sides for matching according to response signals generated by the power generation sides during past transactions;
the total price calculating module is used for calculating the total electricity purchasing price of the electricity utilization side according to the electric quantity required to be purchased by the electricity utilization side and the current electricity price and sending the total electricity purchasing price to the electricity generation side;
the transaction generating module is used for generating a secondary transaction after the power generation side confirms the total power purchase price, receiving a response signal generated by the power generation side, and transmitting the transaction electric quantity, the total power purchase price, the power utilization side information, the power generation side information and the response signal generated by the power generation side corresponding to the transaction to the block chain;
and the butt joint arrangement module is used for sending the total price of electricity purchase to the electricity utilization side for payment, distributing corresponding electric quantity after the payment is successful and finishing the transaction.

Claims (1)

1.一种应用区块链和人工智能的微电网电力大数据交易管理系统，其特征在于，包括：1. A microgrid power big data transaction management system applying block chain and artificial intelligence, is characterized in that, comprises: 购电接收模块，用于根据用电侧以往的用电数据记录整理出已完成交易的购电单价，并记录用电侧本次需要购买的电量；The power purchase receiving module is used to sort out the power purchase unit price of the completed transaction according to the previous power consumption data records of the power consumption side, and record the electricity that the power consumption side needs to purchase this time; 电价调整模块，用于将已完成交易的购电单价的平均值作为初始电价，并比较当前所有发电侧的发电总量和所有用电侧需要购买的总电量，当发电总量比需要购买的总电量大时，按预设值降低初始电价作为当前电价，当发电总量比需要购买的总电量小时，按预设值提高初始电价作为当前电价；The electricity price adjustment module is used to take the average value of the electricity purchase unit price of the completed transaction as the initial electricity price, and compare the current total power generation of all power generation sides with the total electricity that needs to be purchased on all power consumption sides. When the total electricity is large, the initial electricity price is reduced by the preset value as the current electricity price; when the total amount of electricity generated is smaller than the total electricity to be purchased, the initial electricity price is increased by the preset value as the current electricity price; 智能匹配模块，用于筛选能够满足用电侧需要购买的电量的发电侧，并根据发电侧以往交易时产生的响应信号，选择合适的发电侧进行匹配；The intelligent matching module is used to screen the power generation side that can meet the electricity needs to be purchased by the power consumption side, and select the appropriate power generation side for matching according to the response signals generated by the power generation side in previous transactions; 总价计算模块，用于按照用电侧需要购买的电量和当前电价计算出该用电侧的购电总价，并将该购电总价发送至发电侧；The total price calculation module is used to calculate the total power purchase price of the power consumption side according to the amount of electricity that needs to be purchased on the power consumption side and the current power price, and send the total power purchase price to the power generation side; 发电侧对购电总价确认后，交易生成模块生成本次交易并接收发电侧产生的响应信号，并将所述交易对应的交易电量、购电总价、用电侧信息、发电侧信息和发电侧产生的响应信号传至区块链；After the power generation side confirms the total power purchase price, the transaction generation module generates this transaction and receives the response signal generated by the power generation side, and converts the transaction amount corresponding to the transaction, total power purchase price, power consumption side information, power generation side information and The response signal generated by the power generation side is transmitted to the blockchain; 对接整理模块，用于将购电总价发送给用电侧进行付款，付款成功后分配相应电量并结束本次交易；The docking and sorting module is used to send the total purchase price of electricity to the electricity consumer for payment. After the payment is successful, the corresponding electricity is allocated and the transaction is ended; 根据发电侧以往交易时产生的响应信号，选择合适的发电侧进行匹配，具体步骤为：According to the response signals generated by the power generation side in the past transactions, select the appropriate power generation side for matching. The specific steps are as follows: (1)从区块链获取发电侧以往交易时的响应信号并检查，将不完整的信号标记为残缺信号；(1) Obtain and check the response signals of past transactions on the power generation side from the blockchain, and mark incomplete signals as incomplete signals; (2)把其余信号由小到大排列并分成四等份，处于三个分割位置的信号分别为第一分割信号、第二分割信号和第三分割信号，将第一分割信号和第三分割信号之间差距的1.5倍记为异常差距；(2) Arrange the remaining signals from small to large and divide them into four equal parts. The signals in the three division positions are the first divided signal, the second divided signal and the third divided signal. The first divided signal and the third divided signal are divided into four equal parts. 1.5 times the difference between the signals is recorded as an abnormal difference; (3)将高于第三分割信号上方异常差距或低于第一分割信号下方异常差距的信号标记为异常信号；(3) marking the signal that is higher than the abnormal gap above the third divided signal or lower than the abnormal gap below the first divided signal as abnormal signal; (4)以时间为变量，对非残缺且非异常的信号使用线性回归方式分析出信号的变化趋势曲线；(4) Using time as a variable, use linear regression to analyze the change trend curve of the signal for non-defective and non-abnormal signals; (5)提取每个信号与该变化趋势曲线上对应点的误差值，按照信号对应的时间与所述误差值训练分布式梯度增强库，之后根据该分布式梯度增强库对残缺信号和异常信号的误差值做出预测；(5) Extract the error value between each signal and the corresponding point on the change trend curve, train the distributed gradient enhancement library according to the time corresponding to the signal and the error value, and then analyze the incomplete signal and abnormal signal according to the distributed gradient enhancement library. error value to make predictions; (6)基于变化趋势曲线和预测的误差值对残缺信号和异常信号进行修正，得到正常的信号，并按照时间顺序排列为信号集；(6) Correct the incomplete signal and abnormal signal based on the change trend curve and the predicted error value to obtain the normal signal, and arrange it into a signal set according to the time sequence; (7)确定信号集的局部极值点，用Spline插值拟合出相对极大点的包络和相对极小点的包络，并得到两者的平均值即平均包络；(7) Determine the local extreme point of the signal set, use Spline interpolation to fit the envelope of the relative maximum point and the envelope of the relative minimum point, and obtain the average value of the two, that is, the average envelope; (8)判断信号集经过零点的次数和相对极点数量之差，若不大于一，则将信号集作为中间信号集并跳过步骤(9)，若大于一，则判断平均包络是否为零；(8) Judge the difference between the number of times the signal set passes through the zero point and the number of relative poles. If it is not greater than one, the signal set is used as the intermediate signal set and step (9) is skipped. If it is greater than one, then it is judged whether the average envelope is zero. ; (9)若平均包络为零，则将信号集作为中间信号集，若不为零，用信号集减去平均包络得到新的信号集，并重复步骤(7)；(9) If the average envelope is zero, the signal set is used as the intermediate signal set, if not, subtract the average envelope from the signal set to obtain a new signal set, and repeat step (7); (10)保存中间信号集并判断信号集减去中间信号集的结果是否为单调队列，若是，则将所述结果作为残余信号集并跳过步骤(11),若不是，则判断所述结果中的所有信号是否相同；(10) Save the intermediate signal set and judge whether the result of subtracting the intermediate signal set from the signal set is a monotonic queue, if so, use the result as the residual signal set and skip step (11), if not, judge the result Are all the signals in the same; (11)若所述结果中的所有信号相同，则将所述结果作为残余信号集，若不相同，则将所述结果作为新的信号集重复步骤(7)；(11) If all the signals in the result are the same, use the result as a residual signal set, if not, repeat step (7) with the result as a new signal set; (12)对于保存的所有中间信号集和残余信号集中的信号，缩小每个信号的幅度，将缩小幅度后的中间信号集和残余信号集输入递归神经网络进行训练；(12) For the stored signals in all intermediate signal sets and residual signal sets, reduce the amplitude of each signal, and input the reduced amplitude intermediate signal set and residual signal set into a recurrent neural network for training; (13)利用训练好的递归神经网络输出本次交易发电侧的响应信号的推测值，选择信号推测值最大的发电侧与用电侧进行匹配。(13) Use the trained recurrent neural network to output the estimated value of the response signal of the power generation side in this transaction, and select the power generation side with the largest signal estimated value to match the power consumption side.
CN202010301731.5A 2020-04-16 2020-04-16 Microgrid electric power big data transaction management system applying block chains and artificial intelligence Active CN111507766B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010301731.5A CN111507766B (en) 2020-04-16 2020-04-16 Microgrid electric power big data transaction management system applying block chains and artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010301731.5A CN111507766B (en) 2020-04-16 2020-04-16 Microgrid electric power big data transaction management system applying block chains and artificial intelligence

Publications (2)

Publication Number Publication Date
CN111507766A CN111507766A (en) 2020-08-07
CN111507766B true CN111507766B (en) 2021-06-18

Family

ID=71877600

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010301731.5A Active CN111507766B (en) 2020-04-16 2020-04-16 Microgrid electric power big data transaction management system applying block chains and artificial intelligence

Country Status (1)

Country Link
CN (1) CN111507766B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040254899A1 (en) * 2003-05-08 2004-12-16 Keiko Abe Electric power trading support system
CN109785131A (en) * 2018-12-21 2019-05-21 昆明理工大学 A kind of electricity transaction method based on block chain
CN110059970A (en) * 2019-04-23 2019-07-26 南京工程学院 A kind of network system method of commerce based on block chain technology
CN110175699A (en) * 2019-04-26 2019-08-27 郑州大学 Electric power resource decentralization configuration method and system, storage medium based on user preference
CN110400144A (en) * 2019-08-05 2019-11-01 国网电子商务有限公司 A blockchain-based power trading method and device

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049798B (en) * 2012-12-05 2016-04-20 浙江大学城市学院 A kind of short-term power generation power Forecasting Methodology being applied to photovoltaic generating system
CN108717670A (en) * 2017-09-20 2018-10-30 赫普科技发展（北京）有限公司 A kind of electricity transaction system
CN107730058A (en) * 2017-11-28 2018-02-23 北京恒华龙信数据科技有限公司 One kind declares Electricity price forecasting solution and device
CN108961018A (en) * 2018-07-19 2018-12-07 华北电力大学（保定） Micro-capacitance sensor electricity market decentralization mechanism of exchange based on intelligent contract
CN110956312B (en) * 2019-11-15 2022-11-15 国网浙江省电力有限公司电力科学研究院 Photovoltaic distribution network voltage prediction method based on EMD-CNN deep neural network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040254899A1 (en) * 2003-05-08 2004-12-16 Keiko Abe Electric power trading support system
CN109785131A (en) * 2018-12-21 2019-05-21 昆明理工大学 A kind of electricity transaction method based on block chain
CN110059970A (en) * 2019-04-23 2019-07-26 南京工程学院 A kind of network system method of commerce based on block chain technology
CN110175699A (en) * 2019-04-26 2019-08-27 郑州大学 Electric power resource decentralization configuration method and system, storage medium based on user preference
CN110400144A (en) * 2019-08-05 2019-11-01 国网电子商务有限公司 A blockchain-based power trading method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"基于灰色神经网络功率预测的微电网优化运行研究";李佳慧;《中国优秀硕士学位论文全文数据库工程科技II辑》;20190115(第01期);全文 *
"基于经验模态分解的时间序列预测研究";成小林;《中国优秀硕士学位论文全文数据库基础科学辑》;20190215(第02期);全文 *

Also Published As

Publication number Publication date
CN111507766A (en) 2020-08-07

Similar Documents

Publication Publication Date Title
Jamasb et al. Strategic behaviour under regulatory benchmarking
Taylor et al. Supply chain relationships and contracts: The impact of repeated interaction on capacity investment and procurement
Van Biesebroeck Exporting raises productivity in sub-Saharan African manufacturing firms
CN106845988A (en) method and device for selecting payment channel
Alamsyah et al. Artificial neural network for Indonesian tourism demand forecasting
CN101593295A (en) A kind of questionnaire type computer-aided proposal estimating and examining system and evaluation method
Zayed et al. A framework for performance assessment of organizations in the construction industry
CN111932044A (en) Steel product price prediction system and method based on machine learning
CN113344467A (en) Method and device for predicting capital of electric power engineering
Wu Applying grey model to prioritise technical measures in quality function deployment
Barril et al. Natural gas supply behavior under interventionism: the case of Argentina
Chang et al. A model for selecting product ideas in fuzzy front end
Azhar et al. A multi-attribute product life-cycle approach to replacement decisions: an application of Saaty's system-with-feedback method
CN111507766B (en) Microgrid electric power big data transaction management system applying block chains and artificial intelligence
CN114693265B (en) A supply chain multi-user docking method and system for a cloud cutting platform
Shrestha et al. The link between global value chain activity and local human capital: Evidence from Indonesia’s manufacturing sector
Lind A vertically integrated perspective on nordic manufacturing productivity
Kalirajan et al. Public Sector Enterprises in India: Is Privatisation the Only Answer?
Micco et al. Costs and Benefits of Firms' Use of Outsourced Labor: A Structural Estimation
CN112417288A (en) A task cross-domain recommendation method for crowdsourced software testing
Jefry et al. The Implementation of Value for Money Quantitative Analysis on Infrastructure Projects in Indonesia: Case Study of Trans Sumatera Toll Road Project–Section of Palembang Indralaya
Huang et al. A DEMATEL based network process for deriving factors influencing the acceptance of tablet personal computers
Bahmanzadeh et al. Reserve market scheduling considering both capacity and energy bids of reserve
Vogelezang Implementing COSMIC-FFP as a replacement for FPA
Petkus et al. Investigation of human factors while solving multiple criteria optimization problems in computer network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20201023

Address after: 430000 Jueshi Jiayuan, wusheng West Street, Qiaokou District, Wuhan City, Hubei Province

Applicant after: Wan Tiansheng

Address before: Room 011-215, room 01, floor 6, building 1, sage technology R & D center, 26 Binhu Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province

Applicant before: Wuhan kezerui New Material Technology Co.,Ltd.

TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20210528

Address after: 315000 room 428, No.11, building 4, Kaixuan tomorrow, Zhonghe street, Yinzhou District, Ningbo City, Zhejiang Province

Applicant after: Ningbo Qianyi Energy Saving Technology Co.,Ltd.

Address before: 430000 jueshijiayuan, wusheng West Street, Qiaokou District, Wuhan City, Hubei Province

Applicant before: Wan Tiansheng

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20220928

Address after: 136000 No. 999, Zhongyang West Road, Tiexi District, Siping City, Jilin Province

Patentee after: SIPING POWER SUPPLY COMPANY OF STATE GRID JILINSHENG ELECTRIC POWER SUPPLY Co.

Address before: 315000 room 428, No.11, building 4, Kaixuan tomorrow, Zhonghe street, Yinzhou District, Ningbo City, Zhejiang Province

Patentee before: Ningbo Qianyi Energy Saving Technology Co.,Ltd.

TR01 Transfer of patent right