CN112636338A - Load partition regulation and control system and method based on edge calculation - Google Patents

Load partition regulation and control system and method based on edge calculation Download PDF

Info

Publication number
CN112636338A
CN112636338A CN202011453438.7A CN202011453438A CN112636338A CN 112636338 A CN112636338 A CN 112636338A CN 202011453438 A CN202011453438 A CN 202011453438A CN 112636338 A CN112636338 A CN 112636338A
Authority
CN
China
Prior art keywords
load
edge computing
coordination center
management platform
power
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.)
Granted
Application number
CN202011453438.7A
Other languages
Chinese (zh)
Other versions
CN112636338B (en
Inventor
胡楠
傅靖
黄霆
王栋
贲树俊
管永丽
徐晓轶
朱忆洋
于雅薇
毛艳芳
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.)
Nantong Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Original Assignee
Nantong Power Supply Co of State Grid Jiangsu Electric Power 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 Nantong Power Supply Co of State Grid Jiangsu Electric Power Co Ltd filed Critical Nantong Power Supply Co of State Grid Jiangsu Electric Power Co Ltd
Priority to CN202011453438.7A priority Critical patent/CN112636338B/en
Publication of CN112636338A publication Critical patent/CN112636338A/en
Application granted granted Critical
Publication of CN112636338B publication Critical patent/CN112636338B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00004—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the power network being locally controlled
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/008—Circuit arrangements for ac mains or ac distribution networks involving trading of energy or energy transmission rights
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
    • H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2310/00—The network for supplying or distributing electric power characterised by its spatial reach or by the load
    • H02J2310/50—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads
    • H02J2310/56—The network for supplying or distributing electric power characterised by its spatial reach or by the load for selectively controlling the operation of the loads characterised by the condition upon which the selective controlling is based
    • H02J2310/58—The condition being electrical
    • H02J2310/60—Limiting power consumption in the network or in one section of the network, e.g. load shedding or peak shaving
    • 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
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y04S20/20—End-user application control systems
    • Y04S20/222—Demand response systems, e.g. load shedding, peak shaving

Abstract

The invention provides a load partition regulation and control system based on edge computing, which comprises user terminal control equipment, edge computing equipment, a coordination center, a load aggregator management platform and a human-computer interaction interface, wherein the user terminal control equipment is connected with the edge computing equipment; the load partition regulation and control system completes response power optimized allocation nearby on the user side through the edge computing device, so that the calculated amount of the load aggregator management platform is reduced, and the operation efficiency is improved. The invention provides a load partition regulation and control system and method based on edge calculation, which can complete response power optimized distribution nearby at a user side, improve the operation efficiency and ensure the safe, stable and economic operation of a power system.

Description

Load partition regulation and control system and method based on edge calculation
Technical Field
The invention belongs to the technical field of power detection, and particularly relates to a load partition regulation and control system and method based on edge calculation.
Background
With the rapid development of modern society, the electricity consumption in China is continuously increased, the peak-to-valley difference is continuously enlarged, and great pressure is brought to the balance of electric power systems in China. The load can be called to carry out peak clipping and valley filling through the load regulation and control method, the peak-valley difference is reduced, and the method has great significance for guaranteeing the safe, stable and economic operation of the power system. On one hand, centralized scheduling of a plurality of loads can bring about the problems of excessive information data, high cost and great decision difficulty, and by adopting the ADMM distributed algorithm, the communication delay and the calculation time of information interaction can be reduced, the calculation efficiency is greatly improved, and load regulation and control with shorter time scale are realized. On the other hand, the load gaps of different power supply areas are influenced by various factors with larger difference, and more accurate load regulation and control can be realized by adopting the power supply area as the area division basis.
The invention provides a load partition regulation and control system and method based on edge calculation, which can realize the distributed dispatching of loads through the load regulation and control system based on edge calculation when a certain power supply station area has a power supply load gap, reduce the communication delay and the calculation time of information interaction, realize the load regulation and control with shorter time scale, and have great significance for ensuring the safe, stable and economic operation of a power system.
Disclosure of Invention
The invention provides a load partition regulation and control system and method based on edge calculation, which can complete response power optimized distribution nearby at a user side, improve the operation efficiency and ensure the safe, stable and economic operation of a power system.
The invention particularly relates to a load partition regulation and control system based on edge computing, which comprises user terminal control equipment, edge computing equipment, a coordination center, a load aggregator management platform and a human-computer interaction interface, wherein the user terminal control equipment is sequentially connected with the edge computing equipment, the coordination center, the load aggregator management platform and the human-computer interaction interface; the load partition regulation and control system completes response power optimized allocation nearby on the user side through the edge computing device, so that the calculated amount of the load aggregator management platform is reduced, and the operation efficiency is improved.
The main functions of the user terminal control equipment are to collect real-time data of the terminal equipment, upload the real-time data to the edge computing equipment, receive a control instruction issued by a superior and control the terminal equipment.
The edge computing device includes an adjustable capacity computation and a power split computation,
the method for predicting the schedulable capacity of the controllable load by adopting the LSTM method for calculating the schedulable capacity comprises the following steps:
(1) normalizing the input data;
(2) inputting data of a training set in the constructed LSTM model, and obtaining a predicted value through calculation;
(3) calculating an error according to the obtained predicted value and a known real value;
(4) updating the weight of the LSTM by using a back propagation algorithm according to the error to realize the supervised learning of the LSTM;
(5) storing the trained LSTM neural network, and predicting schedulable capacity of 24h in the future by using the stored model to input test set data;
the power distribution calculation distributes response power to each user terminal control device by adopting a consistency algorithm, and the consistency variable is
Figure BDA0002832394970000021
Optimizing the model area agent: calling cost minimum as objective function
Figure BDA0002832394970000022
The constraint condition is
Figure BDA0002832394970000023
Figure BDA0002832394970000024
Calculating the response power of the user terminal control equipment k in the subordinate edge of the coordination center i at the time t;
Figure BDA0002832394970000025
controlling the maximum response power of the equipment k at the time t for the user terminal; u shapeijThe user terminal control equipment set administered by the edge computing equipment j under the coordination center i;
Figure BDA0002832394970000026
calculating the adjusting power of equipment j for the subordinate edge of the coordination center i;
constructing an augmented Lagrange expression:
Figure BDA0002832394970000027
λij,kis Lagrange relaxation factor, and rho is a quadratic penalty coefficient;
the load control is carried out by adopting an ADMM algorithm, and the method comprises the following steps:
(1) initializing parameters, including edge computing equipment consistency variables, user terminal control equipment variables and Lagrange relaxation factors;
(2) the edge computing device consistency variable x updates:
Figure BDA0002832394970000028
(3) the user terminalEnd control device variables
Figure BDA0002832394970000029
Updating:
Figure BDA00028323949700000210
(4) the Lagrange relaxation factor λij,kUpdating:
Figure BDA0002832394970000031
(5) when the condition is satisfied
Figure BDA0002832394970000032
And (c) the algorithm converges when the trends of the consistency variable of the edge computing equipment j and the optimization variable of the user terminal control equipment are consistent, wherein epsilon is a positive number with an infinite size.
The main functions of the coordination center include an up-to-function and a down-to-function,
the pair of upper functions is as follows:
maximum adjustable capacity of the coordination center i
Figure BDA0002832394970000033
Figure BDA0002832394970000034
Maximum response power P of the edge computing equipment j under the coordination center i at the moment ti tThe maximum adjustable capacity of the coordination center i at the moment t;
the average quote cost of the coordination center is
Figure BDA0002832394970000035
Figure BDA0002832394970000036
The cost of response of the user terminal control equipment k in the area under the jurisdiction of the edge computing equipment j at the time t for a coordination center i;
the pair of functions is as follows:
power distribution by the coordination center to the edge computing devices governed thereby
Figure BDA0002832394970000037
Figure BDA0002832394970000038
Participating in responding to a power instruction for the partition where the coordination center i is located;
Figure BDA0002832394970000039
calculating a responsive power for the edge computing device j administered by the coordination center i;
Figure BDA00028323949700000310
calculating the average response cost of the edge device j administered by the coordination center i according to j
Figure BDA00028323949700000311
And (4) arranging in an ascending order.
The main functions of the load aggregation manager management platform comprise a receiving part, an uploading part and a sending part,
the receiving section includes:
(1) receiving actual operation data uploaded by each coordination center as a basis for responding settlement;
(2) receiving the adjustable capacity P of each district uploaded by each coordination centeri tAnd the average cost price
Figure BDA00028323949700000312
(3) A man-machine interaction interface exists, and the quotation and report data uploaded by a user on the mobile phone APP are received;
(4) receiving each partition scheduling instruction issued by scheduling;
the uploading part is as follows: according to the average cost quotation of each district reported by each coordination center
Figure BDA00028323949700000313
The bidding price of each district participating in market competition is generated according to a certain rule
Figure BDA00028323949700000314
Will put the price on
Figure BDA00028323949700000315
And said capacity Pi tUploading to participate in market competition;
the issuing section includes:
(1) the method comprises the steps that an electric power company determines calling indexes of all partitions according to load notches of all power supply partitions and quotations of all partitions of a load aggregator management platform and sends the calling indexes to the load aggregator management platform, and the load aggregator management platform dispatches the calling indexes to the load aggregator management platform according to received scheduling instructions of all the partitions
Figure BDA0002832394970000041
Sending the data to each coordination center;
(2) and taking the received actual response operation data as a settlement basis for settlement, and issuing a settlement result to the user side mobile phone APP.
And the human-computer interaction interface sets the load quantity participating in regulation and the load quotation participating in regulation in each time interval according to the maximum regulation potential in each time interval in the system, receives the settlement amount sent by the load aggregator management platform and realizes the quotation and the report quantity of the user mobile phone APP.
The invention also provides a load partition regulation and control method based on edge calculation, which comprises the following steps:
step (1): the edge computing equipment predicts the adjustable capacity, uploads the capacity to the load aggregator management platform step by step, and sends the capacity to a user side through the human-computer interaction interface;
step (2): the user side reports and quotes the load through the user mobile phone end APP, and data are sent to the edge computing equipment step by step through the load aggregator management platform;
and (3): the coordination center generates the total load adjustment amount and the average load adjustment cost of the power supply area according to the received report quotation of the user side, and reports the total load adjustment amount and the average load adjustment cost to the load aggregator management platform;
and (4): the load aggregator management platform generates market bid prices according to the load average adjustment cost reported by each coordination center, and participates in market bidding according to the adjustable capacity of each partition and the newly generated bid prices;
and (5): the power company determines the load calling condition of each subarea according to the power supply load gap condition and the market bidding condition of each power supply area, and issues each subarea scheduling index to the load aggregator management platform;
and (6): the load aggregator management platform issues the received partition scheduling indexes to the coordination centers;
and (7): each coordination center determines the load regulation power of each edge computing device governed by the coordination center according to a certain rule;
and (8): each edge computing device determines the load response power of each user according to the ADMM algorithm and sends the load response power to the user terminal control device;
and (9): the user side participates in response, and the user terminal control equipment acquires actual operation data and uploads the actual operation data to the load aggregator management platform step by step;
step (10): and the load aggregator management platform performs compensation settlement according to the collected actual user response condition and issues the settlement amount to the user mobile phone end APP through the human-computer interaction interface.
Compared with the prior art, the beneficial effects are: the load partition regulation and control system adopts the power supply partition as the coordination center, so that the power grid can issue load scheduling instructions according to actual running conditions and the actual conditions of different areas. Because the calling of the load side has the conditions of more users, small volume and dispersion, the iterative alternation calculation process of the dispersed load terminal and the cloud load management platform is transferred to the edge node device by adopting the ADMM distributed algorithm, so that the load terminal can be in information interaction with the edge node device nearby and complete iterative calculation, the communication delay and the calculation time generated when the load terminal is directly butted with the cloud load management platform can be greatly reduced, the calculation efficiency can be improved by the ADMM distributed algorithm, the load regulation and control requirement of shorter time scale can be met, and the ADMM distributed algorithm has great significance for guaranteeing the safe, stable and economic operation of a power system; in addition, the LSTM is adopted to predict the schedulable capacity, so that the correlation characteristics contained in the time sequence data can be well learned, and the prediction error is reduced; the user side APP is adopted to interact with the load aggregator management platform, so that the transaction of the user participating in load regulation and control is more transparent and convenient.
Drawings
Fig. 1 is an architecture diagram of a load partition control system based on edge computing according to the present invention.
Fig. 2 is a flowchart of a load partition control method based on edge computing according to the present invention.
Fig. 3 is a topology of an LSTM network model.
Fig. 4 is a flow chart of the work flow of the ADMM algorithm for load control.
Detailed Description
The following describes in detail a specific embodiment of the load partition control system based on edge calculation according to the present invention with reference to the accompanying drawings.
As shown in fig. 1, the load partition regulation and control system of the present invention includes a user terminal control device, an edge computing device, a coordination center, a load aggregator management platform, and a human-computer interaction interface, where the user terminal control device is sequentially connected to the edge computing device, the coordination center, the load aggregator management platform, and the human-computer interaction interface; the load partition regulation and control system completes response power optimized allocation nearby on the user side through the edge computing device, so that the calculated amount of the load aggregator management platform is reduced, and the operation efficiency is improved.
The signal of the invention is transmitted from bottom to top by data acquisition signal and from top to bottom by control signal.
The main functions of the user terminal control equipment are to collect real-time data of the terminal equipment, upload the real-time data to the edge computing equipment, receive a control instruction issued by a superior and control the terminal equipment.
The edge computing device includes an adjustable capacity computation and a power split computation,
and calculating the adjustable capacity:
the long-short-term memory (LSTM) model has a special memory structure and a special door structure, and can better learn the correlation characteristics contained in time sequence data, the invention adopts an LSTM method to predict the schedulable capacity of the controllable load, and the structure is shown in FIG. 3;
the specific calculation in the LSTM unit is shown below:
left door
Figure BDA0002832394970000061
② input gate
Figure BDA0002832394970000062
Output door
Figure BDA0002832394970000063
Memory cell states
Figure BDA0002832394970000064
Figure BDA0002832394970000065
In the formula, sigma is a Sigmoid layer; input gate
Figure BDA0002832394970000066
And
Figure BDA0002832394970000067
performing dot multiplication to determine whether to update the state of the t time step memory unit; forgetting door
Figure BDA0002832394970000068
And c＜t-1＞Performing dot multiplication to determine whether to reserve the original state of the t-1 time step memory unit; a is＜t＞Representing the number of hidden layers at the time t; wf、Wu、WoAnd WcAnd bf、bu、boAnd bcThe parameters which are common to all the LSTM units in the same layer are the parts of the network which need to be learned;
Figure BDA0002832394970000069
i.e. a gate structure that controls whether the memory cell needs to be updated, set to 0, and reflected in the activation vector; activation value a of hidden layer at time step t＜t＞Not only with the historical load value x of the input at time step t＜t＞Hiding layer activation value a at last time step＜t-1＞Related to and also the state c of the memory cell at this time step＜t＞It is related.
The method for predicting the schedulable capacity of the controllable load by adopting the LSTM method comprises the following steps:
(1) normalizing the input data;
(2) inputting data of a training set in the constructed LSTM model, and obtaining a predicted value through calculation;
(3) calculating an error according to the obtained predicted value and a known real value;
(4) updating the weight of the LSTM by using a back propagation algorithm according to the error to realize the supervised learning of the LSTM;
(5) storing the trained LSTM neural network, and predicting schedulable capacity of 24h in the future by using the stored model to input test set data;
the power distribution calculation distributes response power to each user terminal control device by adopting a consistency algorithm, and the consistency variable is
Figure BDA0002832394970000071
Optimizing the model area agent: calling cost minimum as objective function
Figure BDA0002832394970000072
The constraint condition is
Figure BDA0002832394970000073
Figure BDA0002832394970000074
Calculating the response power of the user terminal control equipment k in the subordinate edge of the coordination center i at the time t;
Figure BDA0002832394970000075
controlling the maximum response power of the equipment k at the time t for the user terminal; u shapeijThe user terminal control equipment set administered by the edge computing equipment j under the coordination center i;
Figure BDA0002832394970000076
calculating the adjusting power of equipment j for the subordinate edge of the coordination center i;
constructing an augmented Lagrange expression:
Figure BDA0002832394970000077
λij,kis Lagrange relaxation factor, and rho is a quadratic penalty coefficient;
as shown in fig. 4, the ADMM algorithm is used for load control, and includes the following steps:
(1) initializing parameters, including edge computing equipment consistency variables, user terminal control equipment variables and Lagrange relaxation factors;
(2) the edge computing device consistency variable x updates:
Figure BDA0002832394970000078
(3) the user terminal controls the device variables
Figure BDA0002832394970000079
Updating:
Figure BDA00028323949700000710
(4) the Lagrange relaxation factor λij,kUpdating:
Figure BDA00028323949700000711
(5) when the condition is satisfied
Figure BDA00028323949700000712
And (c) the algorithm converges when the trends of the consistency variable of the edge computing equipment j and the optimization variable of the user terminal control equipment are consistent, wherein epsilon is a positive number with an infinite size.
The main functions of the coordination center include an up-to-function and a down-to-function,
the pair of upper functions is as follows:
maximum adjustable capacity of the coordination center i
Figure BDA0002832394970000081
Figure BDA0002832394970000082
Maximum response power P of the edge computing equipment j under the coordination center i at the moment ti tThe maximum adjustable capacity of the coordination center i at the moment t;
the average quote cost of the coordination center is
Figure BDA0002832394970000083
Figure BDA0002832394970000084
The cost of response of the user terminal control equipment k in the area under the jurisdiction of the edge computing equipment j at the time t for a coordination center i;
the pair of functions is as follows:
power distribution by the coordination center to the edge computing devices governed thereby
Figure BDA0002832394970000085
Figure BDA0002832394970000086
Participating in responding to a power instruction for the partition where the coordination center i is located;
Figure BDA0002832394970000087
calculating a responsive power for the edge computing device j administered by the coordination center i;
Figure BDA0002832394970000088
calculating the average response cost of the edge device j administered by the coordination center i according to j
Figure BDA0002832394970000089
And (4) arranging in an ascending order.
The main functions of the load aggregation manager management platform comprise a receiving part, an uploading part and a sending part,
the receiving section includes:
(1) receiving actual operation data uploaded by each coordination center as a basis for responding settlement;
(2) receiving the adjustable capacity P of each district uploaded by each coordination centeri tAnd the average cost price
Figure BDA00028323949700000810
(3) A man-machine interaction interface exists, and the quotation and report data uploaded by a user on the mobile phone APP are received;
(4) receiving each partition scheduling instruction issued by scheduling;
the uploading part is as follows: according to the average cost quotation of each district reported by each coordination center
Figure BDA00028323949700000811
The bidding price of each district participating in market competition is generated according to a certain rule
Figure BDA00028323949700000812
Will put the price on
Figure BDA00028323949700000813
And said capacity Pi tUploading to participate in market competition;
the issuing section includes:
(1) the method comprises the steps that an electric power company determines calling indexes of all partitions according to load notches of all power supply partitions and quotations of all partitions of a load aggregator management platform and sends the calling indexes to the load aggregator management platform, and the load aggregator management platform dispatches the calling indexes to the load aggregator management platform according to received scheduling instructions of all the partitions
Figure BDA0002832394970000091
Sending the data to each coordination center;
(2) and taking the received actual response operation data as a settlement basis for settlement, and issuing a settlement result to the user side mobile phone APP.
And the human-computer interaction interface sets the load quantity participating in regulation and the load quotation participating in regulation in each time interval according to the maximum regulation potential in each time interval in the system, receives the settlement amount sent by the load aggregator management platform and realizes the quotation and the report quantity of the user mobile phone APP.
As shown in fig. 2, the present invention further provides a load partition regulation and control method based on edge calculation, where the load partition regulation and control method includes the following steps:
step (1): the edge computing equipment predicts the adjustable capacity, uploads the capacity to the load aggregator management platform step by step, and sends the capacity to a user side through the human-computer interaction interface;
step (2): the user side reports and quotes the load through the user mobile phone end APP, and data are sent to the edge computing equipment step by step through the load aggregator management platform;
and (3): the coordination center generates the total load adjustment amount and the average load adjustment cost of the power supply area according to the received report quotation of the user side, and reports the total load adjustment amount and the average load adjustment cost to the load aggregator management platform;
and (4): the load aggregator management platform generates market bid prices according to the load average adjustment cost reported by each coordination center, and participates in market bidding according to the adjustable capacity of each partition and the newly generated bid prices;
and (5): the power company determines the load calling condition of each subarea according to the power supply load gap condition and the market bidding condition of each power supply area, and issues each subarea scheduling index to the load aggregator management platform;
and (6): the load aggregator management platform issues the received partition scheduling indexes to the coordination centers;
and (7): each coordination center determines the load regulation power of each edge computing device governed by the coordination center according to a certain rule;
and (8): each edge computing device determines the load response power of each user according to the ADMM algorithm and sends the load response power to the user terminal control device;
and (9): the user side participates in response, and the user terminal control equipment acquires actual operation data and uploads the actual operation data to the load aggregator management platform step by step;
step (10): and the load aggregator management platform performs compensation settlement according to the collected actual user response condition and issues the settlement amount to the user mobile phone end APP through the human-computer interaction interface.
When a power supply load gap occurs in a certain power supply station area, the load can be distributed and scheduled through the load partition regulation and control system based on edge calculation, the communication delay and the calculation time length of information interaction are reduced, the load regulation and control with shorter time scale is realized, and the method has great significance for guaranteeing the safe, stable and economic operation of a power system. The specific application scenarios are as follows: the electric power company issues a scheduling instruction according to the power supply load gap condition and the market bidding condition of each power supply station area, each subarea issues a scheduling index to a load aggregator management platform and further issues the scheduling index to a coordination center, each coordination center determines the load adjusting power of each edge device governed by the coordination center according to a certain rule, each edge device decomposes and determines the response power of each terminal device according to an ADMM algorithm, and after the final user side participates in response, the load aggregator management platform performs compensation settlement according to the collected actual user response condition and issues the settlement amount to the user mobile phone end through man-machine interaction, so that the load regulation and control based on edge calculation are realized.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention and not for limiting the same. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (7)

1. A load partition regulation and control system based on edge computing is characterized by comprising user terminal control equipment, edge computing equipment, a coordination center, a load aggregator management platform and a human-computer interaction interface, wherein the user terminal control equipment is sequentially connected with the edge computing equipment, the coordination center, the load aggregator management platform and the human-computer interaction interface; the load partition regulation and control system completes response power optimized allocation nearby on the user side through the edge computing device, so that the calculated amount of the load aggregator management platform is reduced, and the operation efficiency is improved.
2. The load partition regulation and control system based on edge computing as claimed in claim 1, wherein the main function of the user terminal control device is to collect real-time data of a terminal device and upload the data to the edge computing device, receive a control instruction issued by a superior and control the terminal device.
3. The edge computing-based load partition conditioning system of claim 2, wherein the edge computing device comprises an adjustable capacity computation and a power split computation,
the method for predicting the schedulable capacity of the controllable load by adopting the LSTM method for calculating the schedulable capacity comprises the following steps:
(1) normalizing the input data;
(2) inputting data of a training set in the constructed LSTM model, and obtaining a predicted value through calculation;
(3) calculating an error according to the obtained predicted value and a known real value;
(4) updating the weight of the LSTM by using a back propagation algorithm according to the error to realize the supervised learning of the LSTM;
(5) storing the trained LSTM neural network, and predicting schedulable capacity of 24h in the future by using the stored model to input test set data;
the power distribution calculation distributes response power to each user terminal control device by adopting a consistency algorithm, and the consistency variable is
Figure FDA0002832394960000011
Optimizing the model area agent: calling cost minimum as objective function
Figure FDA0002832394960000012
Restraint stripThe component is
Figure FDA0002832394960000013
Figure FDA0002832394960000014
Calculating the response power of the user terminal control equipment k in the subordinate edge of the coordination center i at the time t;
Figure FDA0002832394960000015
controlling the maximum response power of the equipment k at the time t for the user terminal; u shapeijThe user terminal control equipment set administered by the edge computing equipment j under the coordination center i;
Figure FDA0002832394960000016
calculating the adjusting power of equipment j for the subordinate edge of the coordination center i;
constructing an augmented Lagrange expression:
Figure FDA0002832394960000021
λij,kis Lagrange relaxation factor, and rho is a quadratic penalty coefficient;
the load control is carried out by adopting an ADMM algorithm, and the method comprises the following steps:
(1) initializing parameters, including edge computing equipment consistency variables, user terminal control equipment variables and Lagrange relaxation factors;
(2) the edge computing device consistency variable x updates:
Figure FDA0002832394960000022
(3) the user terminal controls the device variables
Figure FDA0002832394960000023
Updating:
Figure FDA0002832394960000024
(4) the Lagrange relaxation factor λij,kUpdating:
Figure FDA0002832394960000025
(5) when the condition is satisfied
Figure FDA0002832394960000026
And (c) the algorithm converges when the trends of the consistency variable of the edge computing equipment j and the optimization variable of the user terminal control equipment are consistent, wherein epsilon is a positive number with an infinite size.
4. An edge computing based load partitioning and conditioning system as claimed in claim 3, wherein said coordination center's primary functions comprise an up-to-up function and a down-to-down function,
the pair of upper functions is as follows:
maximum adjustable capacity of the coordination center i
Figure FDA0002832394960000027
Figure FDA0002832394960000028
Maximum response power P of the edge computing equipment j under the coordination center i at the moment ti tThe maximum adjustable capacity of the coordination center i at the moment t;
the average quote cost of the coordination center is
Figure FDA0002832394960000029
Figure FDA00028323949600000210
Responding to the user terminal control device k in the area under the border computing device j at the time t for a coordination center iCost;
the pair of functions is as follows:
power distribution by the coordination center to the edge computing devices governed thereby
Figure FDA00028323949600000211
Figure FDA00028323949600000212
Participating in responding to a power instruction for the partition where the coordination center i is located;
Figure FDA0002832394960000031
calculating a responsive power for the edge computing device j administered by the coordination center i;
Figure FDA0002832394960000032
calculating the average response cost of the edge device j administered by the coordination center i according to j
Figure FDA0002832394960000033
And (4) arranging in an ascending order.
5. The edge-computing-based load partition regulation and control system of claim 4, wherein the main functions of the load aggregator management platform comprise a receive part, an upload part, and a send-down part,
the receiving section includes:
(1) receiving actual operation data uploaded by each coordination center as a basis for responding settlement;
(2) receiving the adjustable capacity P of each district uploaded by each coordination centeri tAnd the average cost price
Figure FDA0002832394960000034
(3) A man-machine interaction interface exists, and the quotation and report data uploaded by a user on the mobile phone APP are received;
(4) receiving each partition scheduling instruction issued by scheduling;
the uploading part is as follows: according to the average cost quotation of each district reported by each coordination center
Figure FDA0002832394960000035
The bidding price of each district participating in market competition is generated according to a certain rule
Figure FDA0002832394960000036
Will put the price on
Figure FDA0002832394960000037
And said capacity Pi tUploading to participate in market competition;
the issuing section includes:
(1) the method comprises the steps that an electric power company determines calling indexes of all partitions according to load notches of all power supply partitions and quotations of all partitions of a load aggregator management platform and sends the calling indexes to the load aggregator management platform, and the load aggregator management platform dispatches the calling indexes to the load aggregator management platform according to received scheduling instructions of all the partitions
Figure FDA0002832394960000038
Sending the data to each coordination center;
(2) and taking the received actual response operation data as a settlement basis for settlement, and issuing a settlement result to the user side mobile phone APP.
6. The load partition regulation and control system based on edge computing as claimed in claim 5, wherein the human-computer interaction interface sets the load amount participating in adjustment and the load quotation participating in adjustment in each time interval according to the maximum adjustment potential in each time interval in the system, receives the settlement amount sent by the load aggregator management platform, and realizes the quotation and report of the user mobile phone end APP.
7. The method for regulating and controlling the load-partitioning regulation and control system based on the edge computing according to any one of claims 1 to 6, wherein the load-partitioning regulation and control method comprises the following steps:
step (1): the edge computing equipment predicts the adjustable capacity, uploads the capacity to the load aggregator management platform step by step, and sends the capacity to a user side through the human-computer interaction interface;
step (2): the user side reports and quotes the load through the user mobile phone end APP, and data are sent to the edge computing equipment step by step through the load aggregator management platform;
and (3): the coordination center generates the total load adjustment amount and the average load adjustment cost of the power supply area according to the received report quotation of the user side, and reports the total load adjustment amount and the average load adjustment cost to the load aggregator management platform;
and (4): the load aggregator management platform generates market bid prices according to the load average adjustment cost reported by each coordination center, and participates in market bidding according to the adjustable capacity of each partition and the newly generated bid prices;
and (5): the power company determines the load calling condition of each subarea according to the power supply load gap condition and the market bidding condition of each power supply area, and issues each subarea scheduling index to the load aggregator management platform;
and (6): the load aggregator management platform issues the received partition scheduling indexes to the coordination centers;
and (7): each coordination center determines the load regulation power of each edge computing device governed by the coordination center according to a certain rule;
and (8): each edge computing device determines the load response power of each user according to the ADMM algorithm and sends the load response power to the user terminal control device;
and (9): the user side participates in response, and the user terminal control equipment acquires actual operation data and uploads the actual operation data to the load aggregator management platform step by step;
step (10): and the load aggregator management platform performs compensation settlement according to the collected actual user response condition and issues the settlement amount to the user mobile phone end APP through the human-computer interaction interface.
CN202011453438.7A 2020-12-11 2020-12-11 Load partition regulation and control system and method based on edge calculation Active CN112636338B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011453438.7A CN112636338B (en) 2020-12-11 2020-12-11 Load partition regulation and control system and method based on edge calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011453438.7A CN112636338B (en) 2020-12-11 2020-12-11 Load partition regulation and control system and method based on edge calculation

Publications (2)

Publication Number Publication Date
CN112636338A true CN112636338A (en) 2021-04-09
CN112636338B CN112636338B (en) 2022-08-19

Family

ID=75309830

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011453438.7A Active CN112636338B (en) 2020-12-11 2020-12-11 Load partition regulation and control system and method based on edge calculation

Country Status (1)

Country Link
CN (1) CN112636338B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113315172A (en) * 2021-05-21 2021-08-27 华中科技大学 Distributed source load data scheduling system of electric heating comprehensive energy
CN113408741A (en) * 2021-06-22 2021-09-17 重庆邮电大学 Distributed ADMM machine learning method of self-adaptive network topology
CN114050644A (en) * 2021-10-21 2022-02-15 国电南瑞科技股份有限公司 Electric heating equipment participates in electric wire netting interactive system
CN114204675A (en) * 2021-11-15 2022-03-18 国网辽宁省电力有限公司葫芦岛供电公司 Power distribution station electric energy data acquisition terminal based on cloud edge cooperation
CN115409431A (en) * 2022-10-31 2022-11-29 国网湖北省电力有限公司信息通信公司 Distributed power resource scheduling method based on neural network
CN115842415A (en) * 2023-02-13 2023-03-24 南京中电科能技术有限公司 Energy management method and system based on cloud edge cooperation
CN116231860A (en) * 2023-03-02 2023-06-06 山东省计算中心（国家超级计算济南中心） Cloud edge end cooperation-based intelligent power load identification system, method and equipment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106786551A (en) * 2017-01-17 2017-05-31 深圳尚沃电力有限公司 Load group towards power supply and demand balance participates in the control method and its system of scheduling
CN109149589A (en) * 2018-09-19 2019-01-04 国家电网有限公司 A kind of flexible load management method and system based on more agency mechanisms
CN111754023A (en) * 2020-05-22 2020-10-09 明阳智慧能源集团股份公司 Edge-cloud-cooperated user load prediction control and transaction system and implementation method thereof

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106786551A (en) * 2017-01-17 2017-05-31 深圳尚沃电力有限公司 Load group towards power supply and demand balance participates in the control method and its system of scheduling
CN109149589A (en) * 2018-09-19 2019-01-04 国家电网有限公司 A kind of flexible load management method and system based on more agency mechanisms
CN111754023A (en) * 2020-05-22 2020-10-09 明阳智慧能源集团股份公司 Edge-cloud-cooperated user load prediction control and transaction system and implementation method thereof

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113315172A (en) * 2021-05-21 2021-08-27 华中科技大学 Distributed source load data scheduling system of electric heating comprehensive energy
CN113408741A (en) * 2021-06-22 2021-09-17 重庆邮电大学 Distributed ADMM machine learning method of self-adaptive network topology
CN113408741B (en) * 2021-06-22 2022-12-27 重庆邮电大学 Distributed ADMM machine learning method of self-adaptive network topology
CN114050644A (en) * 2021-10-21 2022-02-15 国电南瑞科技股份有限公司 Electric heating equipment participates in electric wire netting interactive system
CN114204675A (en) * 2021-11-15 2022-03-18 国网辽宁省电力有限公司葫芦岛供电公司 Power distribution station electric energy data acquisition terminal based on cloud edge cooperation
CN115409431A (en) * 2022-10-31 2022-11-29 国网湖北省电力有限公司信息通信公司 Distributed power resource scheduling method based on neural network
CN115409431B (en) * 2022-10-31 2023-01-24 国网湖北省电力有限公司信息通信公司 Distributed power resource scheduling method based on neural network
CN115842415A (en) * 2023-02-13 2023-03-24 南京中电科能技术有限公司 Energy management method and system based on cloud edge cooperation
CN116231860A (en) * 2023-03-02 2023-06-06 山东省计算中心（国家超级计算济南中心） Cloud edge end cooperation-based intelligent power load identification system, method and equipment
CN116231860B (en) * 2023-03-02 2023-10-17 山东省计算中心（国家超级计算济南中心） Cloud edge end cooperation-based intelligent power load identification system, method and equipment

Also Published As

Publication number Publication date
CN112636338B (en) 2022-08-19

Similar Documents

Publication Publication Date Title
CN112636338B (en) Load partition regulation and control system and method based on edge calculation
CN109190802B (en) Multi-microgrid game optimization method based on power generation prediction in cloud energy storage environment
Jasmin et al. Reinforcement learning approaches to economic dispatch problem
CN112529727A (en) Micro-grid energy storage scheduling method, device and equipment based on deep reinforcement learning
CN113032995B (en) Electric power market simulation optimization and operation method, system and simulation platform
CN113326002A (en) Cloud edge cooperative control system based on computing migration and migration decision generation method
CN112217195B (en) Cloud energy storage charging and discharging strategy forming method based on GRU multi-step prediction technology
CN113326994A (en) Virtual power plant energy collaborative optimization method considering source load storage interaction
CN114219212A (en) Flexible scheduling method for demand side resources considering ubiquitous power internet of things and edge calculation
CN113807589B (en) Rolling optimization method and device for energy storage of operators based on model prediction
Liu et al. Optimal dispatch strategy of virtual power plants using potential game theory
CN116231748A (en) Power distribution network bearing capacity assessment method considering demand response and time period coupling
CN114239372A (en) Multi-target unit maintenance double-layer optimization method and system considering unit combination
Lin et al. Aggregator pricing and electric vehicles charging strategy based on a two-layer deep learning model
Wang et al. A tri-level framework for distribution-level market clearing considering strategic participation of electrical vehicles and interactions with wholesale market
CN115513945A (en) Distributed power supply management method based on Internet of things
CN112564151A (en) Multi-microgrid cloud energy storage optimization scheduling method and system considering privacy awareness
CN113298329A (en) Training and strategy generating method, system, computer device and storage medium
CN110099415A (en) A kind of cloud wireless access network computational resource allocation method and system based on volume forecasting
Yan et al. Matching Theory Aided Federated Learning Method for Load Forecasting of Virtual Power Plant
CN113675866B (en) Dynamic gridding pyramid scheduling method for large-scale electric automobile
WO2023073863A1 (en) Area design proposal system and area design proposal method
Wang et al. Day-ahead Optimal Scheduling Algorithm Considering Uncertainty of Demand Response
CN115689091A (en) Method and device for constructing hierarchical contract model of virtual power plant value network
Sheng et al. Research on Application of Neural Network Based on Cloud Computing in Power Load Forecasting

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
GR01 Patent grant
GR01 Patent grant