CN115360708A - Coordination control method and device for virtual power plant, electronic equipment and storage medium - Google Patents
Coordination control method and device for virtual power plant, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115360708A CN115360708A CN202211290465.6A CN202211290465A CN115360708A CN 115360708 A CN115360708 A CN 115360708A CN 202211290465 A CN202211290465 A CN 202211290465A CN 115360708 A CN115360708 A CN 115360708A
- Authority
- CN
- China
- Prior art keywords
- energy block
- scheduling
- energy
- target
- objective function
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006870 function Effects 0.000 claims abstract description 182
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims description 48
- 230000015654 memory Effects 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 20
- 238000010606 normalization Methods 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 238000009826 distribution Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 claims description 4
- 230000006403 short-term memory Effects 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000005611 electricity Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000012782 phase change material Substances 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- H02J3/007—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources
- H02J3/0075—Arrangements for selectively connecting the load or loads to one or several among a plurality of power lines or power sources for providing alternative feeding paths between load and source according to economic or energy efficiency considerations, e.g. economic dispatch
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- 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
- H02J13/00006—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- 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
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected 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
- 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
- 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
- H02J2310/62—The condition being non-electrical, e.g. temperature
- H02J2310/64—The condition being economic, e.g. tariff based load management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Power Engineering (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application provides a coordination control method, a coordination control device, electronic equipment and a storage medium of a virtual power plant, which perform sequence maximization processing on an initial energy block scheduling strategy according to a pointer network model, avoid solving the energy block scheduling strategy by adopting a planning method, and solve the problem that the solving time of the planning method increases along with the number of objective functions by utilizing the characteristic that the solving efficiency of the pointer network model is irrelevant to the number of the objective functions, so that the solving efficiency of the energy block scheduling strategy is improved, and model support is provided for the comprehensiveness of the objective functions corresponding to the subsequent energy block scheduling strategies.
Description
Technical Field
The application relates to the technical field of power system demand side response, in particular to a coordination control method and device for a virtual power plant, electronic equipment and a storage medium.
Background
With the proposal of a double-carbon target, the installed proportion of new energy power generation is continuously improved, and meanwhile, the intelligent level of the load of the power grid terminal is continuously improved, thereby bringing huge challenges and opportunities to the operation and maintenance of the power grid. The virtual power plant is a power supply coordination management system which integrates power loads such as charging piles, air conditioners and energy storage scattered in energy blocks through an energy internet technology and realizes coordination optimization so as to participate in power grid operation and power market of a special power plant.
Generally, a demand side response function of a virtual power plant can realize real-time response to a scheduling command, however, in the coordination control process of the virtual power plant, the benefit maximization is taken as a single target of the coordination control, the future load condition of energy blocks in the virtual power plant is ignored in constraints, the time consumption for solving the coordination control problem by adopting a linear programming method is increased along with the increase of the number of the energy blocks, and in order to improve the positivity of the energy blocks in the virtual power plant on response to the scheduling command and the efficiency of solving the coordination control problem, a coordination control method which has the minimum influence on the load of the energy blocks and has the maximum benefit needs to be provided.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method, an apparatus, an electronic device and a storage medium for coordinated control of a virtual power plant, so as to solve or partially solve the above technical problems.
Based on the above object, a first aspect of the present application provides a coordination control method for a virtual power plant, where the method is applied to a master station of a virtual power plant system, and the virtual power plant system includes: the system comprises a main station, a plurality of edge gateways and a plurality of energy blocks, wherein the main station is in communication connection with the edge gateways, and each edge gateway in the edge gateways is in one-to-one corresponding communication connection with each energy block in the energy blocks; the method comprises the following steps:
receiving a scheduling instruction;
acquiring a power prediction function of an energy block connected with the edge gateways through the edge gateways, and sending the power prediction function to a master station;
inputting a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy;
according to the pointer network model obtained by pre-trainingThe block scheduling strategy carries out sequence maximization processing to obtain an energy block scheduling strategy meeting a first objective function, a second objective function and a third objective function, wherein the first objective function is max C 0 ，C 0 The second objective function is min k for the compensation value corresponding to the energy block scheduling strategy after normalization processing 0 ，k 0 The number of target energy blocks corresponding to the energy block scheduling strategy after normalization processing is defined, and the third target function is min h 0 ，h 0 The number of loads corresponding to the energy block scheduling strategy after normalization processing is obtained;
and sending the energy block scheduling strategy to an edge gateway corresponding to a target energy block in the energy block scheduling strategy, wherein the energy block scheduling strategy is used for controlling the output power of the corresponding target energy block by the edge gateway.
A second aspect of the present application provides a coordination control device of a virtual power plant, the device being installed in a master station of a virtual power plant system, the virtual power plant system comprising: the system comprises a main station, a plurality of edge gateways and a plurality of energy blocks, wherein the main station is in communication connection with the edge gateways, and each edge gateway in the edge gateways is in one-to-one corresponding communication connection with each energy block in the energy blocks; the device comprises:
a receiving module configured to receive a scheduling instruction;
the system comprises a prediction module, a master station and a plurality of edge gateways, wherein the prediction module is configured to obtain power prediction functions of energy blocks connected with the edge gateways through the edge gateways and send the power prediction functions to the master station;
the input module is configured to input a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy;
a sequence module configured to perform sequence maximization processing on the initial energy block scheduling policy according to a pointer network model obtained through pre-training to obtain an energy block scheduling policy satisfying a first objective function, a second objective function and a third objective function, wherein the first objective function is max C 0 ，C 0 For the compensation value corresponding to the energy block scheduling strategy after normalization processing, the second objective function is min k 0 ，k 0 After normalization processingThe number of target energy blocks corresponding to the energy block scheduling strategy is set, and the third target function is min h 0 ，h 0 The number of loads corresponding to the energy block scheduling strategy after normalization processing is obtained;
the sending module is configured to send the energy block scheduling policy to an edge gateway corresponding to a target energy block in the energy block scheduling policy, where the energy block scheduling policy is used for the edge gateway to control output power of the corresponding target energy block.
A third aspect of the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.
A fourth aspect of the present application provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect.
From the above, according to the coordination control method, the coordination control device, the electronic equipment and the storage medium for the virtual power plant, the initial energy block scheduling strategy is subjected to sequence maximization processing according to the pointer network model, the problem that the solving time of the planning method increases along with the number of objective functions is solved by using the characteristic that the solving efficiency of the pointer network model is irrelevant to the number of the objective functions, the solving efficiency of the energy block scheduling strategy is improved, and therefore model support is provided for the comprehensiveness of the objective functions corresponding to the subsequent energy block scheduling strategies.
Drawings
In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for the embodiments or related technologies in the following description are briefly introduced, and it is obvious that the drawings in the following description are only the embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of a virtual power plant system;
FIG. 2 is a schematic flow chart of a coordination control method of a virtual power plant according to an embodiment of the present application;
FIG. 3 is a schematic structural diagram of a coordination control device of a virtual power plant according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to specific embodiments and the accompanying drawings.
It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The use of "first," "second," and similar terms in the embodiments of the present application is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used only to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As background, virtual power plant system 100 as shown in fig. 1, the virtual power plant system 100 includes a master station 101, a plurality of edge gateways (e.g., edge gateway 102, edge gateway 103, edge gateway 104), and a plurality of energy blocks (e.g., energy block 105, energy block 106, energy block 107), wherein the master station 101 is communicatively coupled to the plurality of energy blocks (e.g., the master station 101 is communicatively coupled to the edge gateway 102, the edge gateway 103, and the edge gateway 104), and each of the plurality of edge gateways is communicatively coupled to each of the plurality of energy blocks (e.g., the edge gateway 102 is communicatively coupled to the energy block 105, the edge gateway 103 is communicatively coupled to the energy block 106, and the edge gateway 104 is communicatively coupled to the energy block 107).
The master station 101 receives the scheduling command, constructs an energy block scheduling policy according to the scheduling command, and sends the energy block scheduling policy to an edge gateway connected to a target energy block in the energy block scheduling policy, where the edge gateway controls the output power of the energy block according to the scheduling command in the energy scheduling policy. For example, when the load curve in the power grid has a peak, a part of the load needs to be reduced to ensure the stable operation of the power system. At this time, the master station 101 receives a scheduling instruction sent by the power grid as an instruction in a peak clipping scene, and the master station 101 selects a target energy block from the plurality of energy blocks according to a load power reduction amount within a period of time corresponding to the peak clipping instruction, and sends the load power reduction amount within the period of time to an edge gateway connected to the target energy block. And after the edge gateway controls the target energy block to cut off the corresponding power load, calculating the compensation electric charge of the power grid to the energy block according to the electric quantity reduced by the target energy block in the process of responding to the peak clipping instruction.
In the related technology, an energy block scheduling strategy with low compensation electricity charge and small target energy block number can be adopted to complete the response of the scheduling command, the low compensation electricity charge represents that the resource cost required by the response of the scheduling command is low, the small target energy block number represents that the compensation electricity charge averagely obtained by the target energy block is large under the condition of certain compensation electricity charge, namely the average income obtained by the target energy block is maximum, the energy block scheduling strategy is favorable for exciting other energy blocks to be added into a virtual power plant system responding to the scheduling command, the working efficiency of the virtual power plant system for expanding the schedulable capacity is improved, and the ground application of the virtual power plant system is effectively promoted.
The problems thus posed are: due to the increase of the number of the objective functions, the solving time of a traditional planning method or a natural evolution algorithm is increased, and the real-time generation of the energy block strategy scheduling strategy is reduced.
In view of this, embodiments of the present application provide a coordination control method and apparatus for a virtual power plant, an electronic device, and a storage medium, which may be applied to response of a scheduling instruction in a virtual power plant system.
As shown in fig. 2, the method of the embodiment is applied to a master station of a virtual power plant system, and the virtual power plant system includes: the system comprises a main station, a plurality of edge gateways and a plurality of energy blocks, wherein the main station is in communication connection with the edge gateways, and each edge gateway in the edge gateways is in one-to-one corresponding communication connection with each energy block in the energy blocks; the method of the embodiment comprises the following steps:
In this step, the scheduling instruction refers to an instruction for power adjustment, and the scheduling instruction in this embodiment may be an instruction for adjusting output power of an energy block, and includes: the target capacity, the scheduling start time and the scheduling end time can be obtained by integrating the output power with time, so that the output power required to be adjusted can be calculated according to the target capacity, the scheduling start time and the scheduling end time of the scheduling instruction.
In this way, a data basis is provided for subsequently generating an initial energy block scheduling policy.
Step 202, obtaining power prediction functions of energy blocks connected with the edge gateways through a plurality of edge gateways, and sending the power prediction functions to the master station.
In this step, the energy block refers to an object capable of responding to the scheduling command, and the preferred energy block of the embodiment may be a virtual power plant capable of responding to the scheduling command, for example, the energy block may be an office building including a schedulable load, wherein the schedulable load includes an air conditioner for accumulating cold through the phase change material and an electrically driven air conditioner. When the energy block needs to respond to a scheduling instruction of peak clipping, the refrigerating capacity of electrically-driven air-conditioning equipment in an office building is replaced by refrigerating capacity of phase-change material cold accumulation, so that the electricity consumption of the office building is reduced, namely, the energy block responds to the scheduling instruction of peak clipping; when the valley filling dispatching instruction needs to be responded, the electric energy is converted into the cold accumulation energy of the phase change material in the cold accumulation equipment.
The power prediction function refers to a function of the change of the power of the energy block capable of responding to the scheduling command with time, and the preferred power prediction function of the embodiment may be a function of the change of the active power of the energy block capable of responding to the scheduling command with time.
Therefore, the power prediction function of the energy block is obtained according to the edge gateway, the power prediction of the main station on a plurality of energy blocks is avoided, the data processing task of the main station is shared through the edge gateway, the data processing workload of the main station is reduced, and a data basis is provided for the generation of a subsequent initial energy management strategy.
And 203, inputting a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy.
In this step, the target energy block refers to an energy block that changes output power according to the scheduling command, and a preferred target energy block in this embodiment may be an energy block that changes output active power according to the scheduling command.
In this way, a data base is provided for the input of the subsequent pointer network model.
Step 204, performing sequence maximization processing on the initial energy block scheduling strategy according to a pointer network model obtained through pre-training to obtain an energy block scheduling strategy meeting a first objective function, a second objective function and a third objective function, wherein the first objective function is max C 0 ，C 0 For the compensation value corresponding to the initial energy block scheduling strategy after normalization processing, the second objective function is min k 0 ，k 0 The number of target energy blocks corresponding to the initial energy block scheduling strategy after normalization processing is calculated, and the third target function is min h 0 ，h 0 And the load number corresponding to the initial energy block scheduling strategy after the normalization processing is carried out.
In this step, the pointer network model refers to a model based on a pointer network and capable of generating an energy block scheduling policy according to an initial energy block scheduling policy, and the preferred pointer network model in this embodiment is a model based on a pointer network trained in advance and capable of generating an energy block scheduling policy according to the initial energy block scheduling policy.
First objective function max C 0 Refer to the ability to represent energy blocksFunction with maximum compensation value of degree strategy, second objective function min k 0 The function which can represent the minimum number of target energy blocks in the energy block scheduling strategy is referred to, and a third target function min h 0 Refers to a function that can indicate that the number of loads in the energy block scheduling policy is the smallest.
The normalization processing refers to converting the compensation value, the number of target energy blocks and the number of loads into decimal numbers between (0, 1), so that the influence of different orders of magnitude among the compensation value, the number of target energy blocks and the number of loads on the calculation of the target function is avoided.
Specifically, the maximum compensation value C corresponding to the target energy block is obtained max And the minimum compensation value C min Then, the formula for performing normalization processing on the compensation value C of the energy block scheduling policy is: c 0 =（C-C min ）/（C max -C min ) (ii) a Obtaining the maximum number k of target energy blocks max And a minimum number k min Then, the formula for normalizing the number k of the target energy blocks of the energy block scheduling policy is as follows: k is a radical of formula 0 =（k-k min ）/（k max -k min ) (ii) a Obtaining the maximum load number h of the target energy block max And the minimum number of loads h min Then, the formula for normalizing the load number h of the energy block scheduling policy is as follows: h is 0 =（h-h min ）/（h max -h min ）。
Therefore, the problem that the solving time of the planning method increases along with the number of the objective functions is solved by utilizing the characteristic that the solving efficiency of the pointer network model is irrelevant to the number of the objective functions, the solving efficiency of the energy block scheduling strategy is improved, and model support is provided for the comprehensiveness of the objective functions corresponding to the subsequent energy block scheduling strategy.
In this step, the output power refers to the power consumption of the energy block under the control of the edge gateway, and the preferred output power of this embodiment may be the active power of the target energy block under the control of the edge gateway.
Through the scheme, the initial energy block scheduling strategy is subjected to sequence maximization processing according to the pointer network model, the energy block scheduling strategy is prevented from being solved by adopting a planning method, the problem that the solving time of the planning method is increased along with the number of objective functions is solved by utilizing the characteristic that the solving efficiency of the pointer network model is irrelevant to the number of the objective functions, and the solving efficiency of the energy block scheduling strategy is improved, so that model support is provided for the comprehensiveness of the objective functions corresponding to the subsequent energy block scheduling strategy.
In some embodiments, the training process of the pointer network model comprises:
acquiring a training set;
constructing an initial pointer network model by adopting a long-term and short-term memory network;
inputting an initial training scheduling strategy in a training set into an initial pointer network model to obtain a target function value set;
determining a loss function according to the first objective function, the second objective function and the third objective function;
iterating the encoder parameters and the decoder parameters in the initial pointer network model according to the loss function until the mean square error of the target function value set is smaller than a preset training threshold;
and taking the initial pointer network model as a pointer network model.
In the above scheme, the training set refers to a data set including a plurality of initial training scheduling strategies and training scheduling strategies corresponding to the initial training scheduling strategies, and the preferred training set in this embodiment may be an initial training scheduling strategy generated by using a monte carlo algorithm and a scheduling strategy corresponding to the initial training scheduling strategy calculated by using a planning algorithm.
The initial pointer network model refers to a model with a pointer network architecture, and the initial pointer network model preferred in this embodiment may be a model with a pointer network architecture that is constructed by using LSTM (Long Short-Term Memory network) as an encoder and a decoder.
The target function value set refers to a first target function value, a second target function value and a third target function value of an initial training scheduling strategy which is obtained by calculation according to the initial pointer network model and meets the first target function, the second target function and the third target function.
Specifically, when the mean square error of the objective function value set is minimum, it indicates that the initial training scheduling strategy which satisfies the first objective function, the second objective function and the third objective function and is calculated by the initial pointer network model is closest to the scheduling strategy corresponding to the initial training scheduling strategy calculated by the planning algorithm in the training set.
Therefore, the pointer network model is trained in a mean square error mode, and the solving accuracy of the pointer network model can be guaranteed.
In some embodiments, determining the loss function from the first objective function, the second objective function, and the third objective function comprises:
the loss function is calculated using the following formula:
wherein J is a loss function, theta is an encoder parameter and a decoder parameter, p (theta) is probability distribution corresponding to theta, pi is a training scheduling strategy corresponding to p (theta), pi-p (theta) represents probability distribution of pi obeying p (theta),
for a mathematical expectation corresponding to the first objective function,
for the mathematical expectation corresponding to the second objective function,
for the mathematical expectation of the third objective function, G 1 (π) is the first objective function value corresponding to the training scheduling policy, G 2 (pi) as a training scheduling strategyCorresponding second value of objective function, G 3 And (pi) is a third objective function value corresponding to the training scheduling strategy.
In the above solution, in order to iterate the encoder parameters and the decoder parameters in the initial pointer network model, the iteration directions of the encoder parameters and the decoder parameters need to be calculated according to the probability distributions of the encoder parameters and the decoder parameters.
The training scheduling strategy refers to a strategy generated by an initial pointer network model according to the initial training scheduling strategy.
Through the scheme, a judgment basis is provided for the iteration directions of the encoder parameters and the decoder parameters.
In some embodiments, performing sequence maximization processing on an initial energy block scheduling policy according to a pointer network model obtained through pre-training to obtain an energy block scheduling policy that satisfies a first objective function, a second objective function, and a third objective function, includes:
inputting an initial energy block scheduling strategy into an encoder of a pointer network model;
performing space mapping on the initial energy block scheduling strategy through an encoder according to encoder parameters to obtain an encoding vector;
carrying out weighted summation on the coding vectors through an attention mechanism of a decoder to obtain an output sequence;
calculating the probability of an output sequence by adopting a conditional random field to obtain a conditional probability set;
and selecting an output sequence corresponding to the maximum conditional probability in the conditional probability set as an energy block scheduling strategy.
In the above scheme, the pointer network model can maximize the probability of obtaining the initial energy block scheduling policy that satisfies the first objective function, the second objective function, and the third objective function.
Specifically, the pointer network model is structured similarly to the seq2seq (sequence-sequence) model, and is composed of an encoder and a decoder. The original pointer network is used to solve the traveler problem, the input of the encoder is a vector of node coordinates and the output of the decoder is some sort of node coordinates.
The input of the encoder in this embodiment is an initial energy block scheduling policy, that is, an output power sequence of a target energy block, and a coding vector of the initial energy block scheduling policy is obtained through spatial mapping of the encoder, that is, a predicted output power sequence of the target energy block is obtained through calculation according to probability distribution of encoder parameters.
The attention mechanism of the decoder can calculate a first objective function value, a second objective function value and a third objective function value corresponding to the predicted output power sequence.
For example, the compensation value in the first objective function value is calculated according to the following equation:
wherein C is a compensation value, d i Compensation coefficient for the ith target energy block, D i The compensation capacity allocated according to the target capacity for the ith target energy block,
and is provided with
And R is the target capacity.
The conditional random field refers to a model capable of performing sequence labeling on a sequence, and the conditional random field in this embodiment can label the probability corresponding to the sequence, so as to provide a selection basis for subsequently selecting an output sequence with the maximum conditional probability.
By the scheme, the problem that the solving time of the planning method increases along with the number of the objective functions is solved by utilizing the characteristic that the solving efficiency of the pointer network model is irrelevant to the number of the objective functions, and the solving efficiency of the energy block scheduling strategy is improved, so that model support is provided for the comprehensiveness of the objective functions corresponding to the subsequent energy block scheduling strategy.
In some embodiments, the conditional random field is used to compute probabilities of the output sequences, resulting in a conditional probability set, comprising:
the probability of the output sequence is calculated using the following formula:
wherein, X 0 Y is an object vector formed by a first object function value, a second object function value and a third object function value corresponding to the output sequence, and P (Y | X |) 0 ) To output the probability of a sequence, x i For the output power sequence of the ith target energy block, y i And the target vector corresponding to the ith target energy block.
In the above scheme, in order to obtain the initial energy block scheduling policy that satisfies the first objective function, the second objective function, and the third objective function with the maximum probability, the probability of the output sequence corresponding to the initial energy block scheduling policy needs to be calculated.
Through the scheme, a selection basis is provided for the output sequence with the maximum subsequent selection probability.
In some embodiments, the scheduling instructions include: target capacity, scheduling start time and scheduling end time;
inputting a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy, which comprises the following steps:
selecting at least one energy block from the plurality of energy blocks as a target energy block, and counting the number of the target energy blocks or the number of loads in the target energy block;
determining the scheduling capacity of the target energy block through integration according to the power prediction function, the scheduling start time and the scheduling end time, wherein the scheduling capacity is larger than or equal to the target capacity;
determining compensation capacity corresponding to the target energy block according to the scheduling capacity;
and determining a compensation value corresponding to the target capacity through multiplication according to the pre-stored compensation coefficient and the compensation capacity.
In the above solution, the scheduling capacity refers to an upper limit of a capacity in which an energy block is changed in response to a scheduling instruction, and a preferred scheduling capacity of the embodiment may be an upper limit of a capacity in which a target energy block is changed in response to a scheduling instruction. The compensation capacity refers to a value of the target energy block sharing target capacity, and the preferred compensation capacity of the embodiment may be a value of the target energy block sharing target capacity in the virtual power plant system.
The scheduling capacity is calculated according to the following formula:
where E is the scheduling capacity, P i (t) is the power prediction function of the ith target energy block, t 0 For scheduling the start time, t, in the instruction 1 K is the scheduling end time in the scheduling instruction, and k is the number of the target energy blocks.
In response to determining that the number of target energy blocks is 1, calculating a scheduling capacity according to:
where E is the scheduling capacity, P (t) is the power prediction function of the target energy block, t 0 For scheduling start time, t, in scheduling instructions 1 Is the scheduled end time in the scheduling instruction.
Through the scheme, a basis is provided for the subsequent calculation of the first objective function, the second objective function and the third objective function.
In some embodiments, selecting at least one energy chunk from a plurality of energy chunks as a target energy chunk comprises:
selecting at least one energy block as a target energy block from low to high according to the compensation coefficients corresponding to the energy blocks;
or the like, or a combination thereof,
selecting at least one energy block as a target energy block from low to high according to the power supply priority corresponding to the energy blocks;
or the like, or, alternatively,
and at least one energy block is selected as a target energy block from at least according to the historical response regulation and control times corresponding to the energy blocks.
In the above scheme, the power supply priority refers to a priority corresponding to an electrical load in an energy block, and the preferred power supply priority in this embodiment may be a priority corresponding to an electrical load in an energy block in a virtual power plant system, for example, the power supply priority may be an electrical load ranked according to a user comfort level, the power supply priority of an air conditioner load in a mall is higher than the power supply priority of a water heater load in an office building, a scheduling instruction for responding to peak clipping by a short-time power failure of a water heater is used, and a scheduling instruction for responding to peak clipping by a short-time power failure of an air conditioner in a mall is used, where the former has less influence on the user comfort level than the latter.
In order to increase the success rate of the target energy block responding to the scheduling instruction, the historical response scheduling times of a plurality of energy blocks can be counted, and the energy block with the historical response regulation and control times is selected as the target energy block.
Through the scheme, the coordination control model can pre-select the energy block with low power supply priority as the target energy block, and the rationality of selecting the target energy block is improved.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and is completed by the mutual cooperation of a plurality of devices. In the case of such a distributed scenario, one device of the multiple devices may only execute one or more steps of the method of the embodiment of the present application, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides a coordination control device of the virtual power plant.
Referring to fig. 3, a coordinated control apparatus of a virtual power plant includes:
a receiving module 301 configured to receive a scheduling instruction;
a prediction module 302 configured to obtain, through a plurality of edge gateways, a power prediction function of an energy block connected to the edge gateways and transmit the power prediction function to a master station;
the input module 303 is configured to input a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling policy;
a sequence module 304, configured to perform sequence maximization processing on the initial energy block scheduling policy according to the pointer network model obtained through pre-training, so as to obtain an energy block scheduling policy that satisfies a first objective function, a second objective function, and a third objective function, where the first objective function is max C 0 ，C 0 For the compensation value corresponding to the initial energy block scheduling strategy after normalization processing, the second objective function is min k 0 ，k 0 The number of target energy blocks corresponding to the energy block scheduling strategy after normalization processing is calculated, and the third target function is min h 0 ，h 0 The number of loads corresponding to the energy block scheduling strategy after normalization processing is obtained;
a sending module 305, configured to send an energy block scheduling policy to an edge gateway corresponding to a target energy block in the energy block scheduling policy, where the energy block scheduling policy is used for the edge gateway to control output power of the corresponding target energy block.
In some embodiments, the training unit of the pointer network model in the sequence module 304 is specifically configured to:
acquiring a training set;
constructing an initial pointer network model by adopting a long-term and short-term memory network;
inputting an initial training scheduling strategy in a training set into an initial pointer network model to obtain a target function value set;
determining a loss function according to the first objective function, the second objective function and the third objective function;
iterating the encoder parameters and the decoder parameters in the initial pointer network model according to the loss function until the mean square error of the target function value set is smaller than a preset training threshold;
and taking the initial pointer network model as a pointer network model.
In some embodiments, the training unit is further specifically configured to:
the loss function is calculated using the following formula:
wherein J is a loss function, theta is an encoder parameter and a decoder parameter, p (theta) is probability distribution corresponding to theta, pi is a training scheduling strategy corresponding to p (theta), pi-p (theta) represents probability distribution of pi obeying p (theta),
for a mathematical expectation corresponding to the first objective function,
for the mathematical expectation corresponding to the second objective function,
for the mathematical expectation of the third objective function, G 1 (π) is the first objective function value corresponding to the training scheduling policy, G 2 (pi) is a second objective function value corresponding to the training scheduling strategy, G 3 And (pi) is a third objective function value corresponding to the training scheduling strategy.
In some embodiments, the sequence module 304 is specifically configured to:
inputting an initial energy block scheduling strategy into an encoder of a pointer network model;
performing space mapping on the initial energy block scheduling strategy through an encoder according to encoder parameters to obtain an encoding vector;
carrying out weighted summation on the coding vectors through an attention mechanism of a decoder to obtain an output sequence;
calculating the probability of an output sequence by adopting a conditional random field to obtain a conditional probability set;
and selecting an output sequence corresponding to the maximum conditional probability in the conditional probability set as an energy block scheduling strategy.
In some embodiments, the sequence module 304 is further specifically configured to:
the probability of the output sequence is calculated using the following formula:
wherein X 0 Y is an object vector formed by a first object function value, a second object function value and a third object function value corresponding to the output sequence, and P (Y | X |) 0 ) Is the probability of the output sequence, x i For the output power sequence of the ith target energy block, y i And the target vector corresponding to the ith target energy block.
In some embodiments, the scheduling instructions include: target capacity, scheduling start time and scheduling end time; the input module 303 is specifically configured to:
selecting at least one energy block from the plurality of energy blocks as a target energy block, and counting the number of the target energy blocks or the number of loads in the target energy block;
determining the scheduling capacity of the target energy block through integration according to the power prediction function, the scheduling start time and the scheduling end time, wherein the scheduling capacity is larger than or equal to the target capacity;
determining compensation capacity corresponding to the target energy block according to the scheduling capacity;
and determining a compensation value corresponding to the target capacity through multiplication according to the pre-stored compensation coefficient and the compensation capacity.
In some embodiments, the input module 303 is further specifically configured to:
selecting at least one energy block as a target energy block from low to high according to the compensation coefficients corresponding to the energy blocks;
or the like, or, alternatively,
selecting at least one energy block as a target energy block from low to high according to the power supply priority corresponding to the energy blocks;
or the like, or a combination thereof,
and at least one energy block is selected as a target energy block according to the historical response regulation times corresponding to the energy blocks.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more pieces of software and/or hardware in the practice of the present application.
The device of the above embodiment is used for implementing the coordination control method of the virtual power plant in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to the method in any embodiment, the application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the program, the coordination control method for the virtual power plant in any embodiment is implemented.
Fig. 4 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called by the processor 1010 for execution.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present device and other devices. The communication module can realize communication in a wired mode (for example, USB, network cable, etc.), and can also realize communication in a wireless mode (for example, mobile network, WIFI, bluetooth, etc.).
The bus 1050 includes a path to transfer information between various components of the device, such as the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040.
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
The electronic device of the above embodiment is used for implementing the coordination control method of the virtual power plant in any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above embodiments, the present application further provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the coordination control method of the virtual power plant according to any of the above embodiments.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, for storing information may be implemented in any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The computer instructions stored in the storage medium of the above embodiment are used to enable a computer to execute the coordination control method of the virtual power plant according to any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which are not described herein again.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, technical features in the above embodiments or in different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Further, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures, such as Dynamic RAM (DRAM), may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalents, improvements, and the like that may be made without departing from the spirit or scope of the embodiments of the present application are intended to be included within the scope of the claims.
Claims (10)
1. A coordination control method of a virtual power plant is characterized in that the method is applied to a master station of a virtual power plant system, and the virtual power plant system comprises the following steps: the system comprises a main station, a plurality of edge gateways and a plurality of energy blocks, wherein the main station is in communication connection with the edge gateways, and each edge gateway in the edge gateways is in one-to-one corresponding communication connection with each energy block in the energy blocks; the method comprises the following steps:
receiving a scheduling instruction;
acquiring a power prediction function of an energy block connected with the edge gateways through the edge gateways, and sending the power prediction function to a master station;
inputting a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy;
performing sequence maximization processing on an initial energy block scheduling strategy according to a pointer network model obtained through pre-training to obtain an energy block scheduling strategy meeting a first objective function, a second objective function and a third objective function, wherein the first objective function is max C 0 ，C 0 The second objective function is min k for the compensation value corresponding to the initial energy block scheduling strategy after normalization processing 0 ，k 0 The number of target energy blocks corresponding to the initial energy block scheduling strategy after normalization processing is calculated, and the third target function is min h 0 ，h 0 The number of loads corresponding to the initial energy block scheduling strategy after normalization processing is obtained;
and sending the energy block scheduling strategy to an edge gateway corresponding to a target energy block in the energy block scheduling strategy, wherein the energy block scheduling strategy is used for controlling the output power of the corresponding target energy block by the edge gateway.
2. The method of claim 1, wherein the training process of the pointer network model comprises:
acquiring a training set;
constructing an initial pointer network model by adopting a long-term and short-term memory network;
inputting an initial training scheduling strategy in a training set into an initial pointer network model to obtain a target function value set;
determining a loss function according to the first objective function, the second objective function and the third objective function;
iterating the encoder parameters and the decoder parameters in the initial pointer network model according to the loss function until the mean square error of the target function value set is smaller than a preset training threshold;
and taking the initial pointer network model as a pointer network model.
3. The method of claim 2, wherein determining the loss function based on the first objective function, the second objective function, and the third objective function comprises:
the loss function is calculated using the following formula:
wherein J is a loss function, theta is an encoder parameter and a decoder parameter, p (theta) is probability distribution corresponding to theta, pi is a training scheduling strategy corresponding to p (theta), pi-p (theta) represents probability distribution of pi obeying p (theta),
for the mathematical expectation corresponding to the first objective function,
for the mathematical expectation corresponding to the second objective function,
for the mathematical expectation of the third objective function, G 1 (pi) is a first objective function value corresponding to the training scheduling strategy, G 2 (π) is the second objective function value corresponding to the training scheduling policy, G 3 And (pi) is a third objective function value corresponding to the training scheduling strategy.
4. The method of claim 2, wherein performing sequence maximization processing on an initial energy block scheduling policy according to a pointer network model obtained by pre-training to obtain an energy block scheduling policy that satisfies a first objective function, a second objective function, and a third objective function, comprises:
inputting an initial energy block scheduling strategy into an encoder of a pointer network model;
performing space mapping on the initial energy block scheduling strategy through an encoder according to encoder parameters to obtain an encoding vector;
carrying out weighted summation on the coding vectors through an attention mechanism of a decoder to obtain an output sequence;
calculating the probability of an output sequence by adopting a conditional random field to obtain a conditional probability set;
and selecting an output sequence corresponding to the maximum conditional probability in the conditional probability set as an energy block scheduling strategy.
5. The method of claim 4 wherein computing the probability of the output sequence using the conditional random field to obtain a conditional probability set comprises:
the probability of the output sequence is calculated using the following formula:
wherein, X 0 Y is an object vector formed by a first object function value, a second object function value and a third object function value corresponding to the output sequence, and P (Y | X |) 0 ) To output the probability of a sequence, x i For the output power sequence of the ith target energy block, y i And the target vector corresponding to the ith target energy block.
6. The method of claim 1, wherein scheduling instructions comprises: target capacity, scheduling start time and scheduling end time;
inputting a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy, wherein the method comprises the following steps:
selecting at least one energy block from the plurality of energy blocks as a target energy block, and counting the number of the target energy blocks or the number of loads in the target energy block;
determining the scheduling capacity of the target energy block through integration according to the power prediction function, the scheduling start time and the scheduling end time, wherein the scheduling capacity is larger than or equal to the target capacity;
determining compensation capacity corresponding to the target energy block according to the scheduling capacity;
and determining a compensation value corresponding to the target capacity through multiplication according to the pre-stored compensation coefficient and the compensation capacity.
7. The method of claim 6, wherein selecting at least one energy block from the plurality of energy blocks as a target energy block comprises:
selecting at least one energy block as a target energy block from low to high according to the compensation coefficients corresponding to the energy blocks;
or the like, or, alternatively,
selecting at least one energy block as a target energy block from low to high according to the power supply priority corresponding to the energy blocks;
or the like, or a combination thereof,
and at least one energy block is selected as a target energy block from at least according to the historical response regulation and control times corresponding to the energy blocks.
8. The utility model provides a coordinated control device of virtual power plant, its characterized in that, the device is installed in the main website of virtual power plant system, and virtual power plant system includes: the system comprises a main station, a plurality of edge gateways and a plurality of energy blocks, wherein the main station is in communication connection with the edge gateways, and each edge gateway in the edge gateways is in one-to-one corresponding communication connection with each energy block in the energy blocks; the device comprises:
a receiving module configured to receive a scheduling instruction;
the system comprises a prediction module, a master station and a plurality of edge gateways, wherein the prediction module is configured to obtain power prediction functions of energy blocks connected with the edge gateways through the edge gateways and send the power prediction functions to the master station;
the input module is configured to input a scheduling instruction and a power prediction function into a pre-constructed coordination control model to obtain an initial energy block scheduling strategy;
a sequence module configured to perform sequence maximization processing on the initial energy block scheduling policy according to a pointer network model obtained through pre-training to obtain an energy block scheduling policy satisfying a first objective function, a second objective function and a third objective function, wherein the first objective function is max C 0 ，C 0 To normalize the processed initial energyThe compensation value corresponding to the gauge block scheduling strategy, and the second objective function is min k 0 ，k 0 The number of target energy blocks corresponding to the energy block scheduling strategy after normalization processing is calculated, and the third target function is min h 0 ，h 0 The number of loads corresponding to the energy block scheduling strategy after normalization processing is obtained;
the sending module is configured to send the energy block scheduling policy to an edge gateway corresponding to a target energy block in the energy block scheduling policy, where the energy block scheduling policy is used for the edge gateway to control output power of the corresponding target energy block.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, the processor implementing the method of any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211290465.6A CN115360708B (en) | 2022-10-21 | 2022-10-21 | Coordination control method and device for virtual power plant, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211290465.6A CN115360708B (en) | 2022-10-21 | 2022-10-21 | Coordination control method and device for virtual power plant, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115360708A true CN115360708A (en) | 2022-11-18 |
| CN115360708B CN115360708B (en) | 2023-01-06 |
Family
ID=84008297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211290465.6A Active CN115360708B (en) | 2022-10-21 | 2022-10-21 | Coordination control method and device for virtual power plant, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115360708B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115940166A (en) * | 2023-03-10 | 2023-04-07 | 中国铁塔股份有限公司 | Base station scheduling method and device, electronic equipment and readable storage medium |
| CN116207867A (en) * | 2023-05-06 | 2023-06-02 | 深圳艾斯特创新科技有限公司 | Household energy storage system management method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170207633A1 (en) * | 2016-01-19 | 2017-07-20 | Fujitsu Limited | Aggregated and optimized virtual power plant control |
| CN113379566A (en) * | 2021-07-07 | 2021-09-10 | 国网冀北电力有限公司 | Virtual power plant support system |
| CN113489797A (en) * | 2021-07-07 | 2021-10-08 | 国网冀北电力有限公司 | Virtual power plant data collection and information transmission method, device and equipment |
| CN215956553U (en) * | 2021-09-15 | 2022-03-04 | 上海电器科学研究所（集团）有限公司 | Edge gateway device for virtual power plant |
-
2022
- 2022-10-21 CN CN202211290465.6A patent/CN115360708B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170207633A1 (en) * | 2016-01-19 | 2017-07-20 | Fujitsu Limited | Aggregated and optimized virtual power plant control |
| CN113379566A (en) * | 2021-07-07 | 2021-09-10 | 国网冀北电力有限公司 | Virtual power plant support system |
| CN113489797A (en) * | 2021-07-07 | 2021-10-08 | 国网冀北电力有限公司 | Virtual power plant data collection and information transmission method, device and equipment |
| CN215956553U (en) * | 2021-09-15 | 2022-03-04 | 上海电器科学研究所（集团）有限公司 | Edge gateway device for virtual power plant |
Non-Patent Citations (1)
| Title |
|---|
| 张军六等: "计及需求响应的气电互联虚拟电厂多目标调度优化模型", 《电力建设》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115940166A (en) * | 2023-03-10 | 2023-04-07 | 中国铁塔股份有限公司 | Base station scheduling method and device, electronic equipment and readable storage medium |
| CN116207867A (en) * | 2023-05-06 | 2023-06-02 | 深圳艾斯特创新科技有限公司 | Household energy storage system management method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115360708B (en) | 2023-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115360708B (en) | Coordination control method and device for virtual power plant, electronic equipment and storage medium | |
| Yin et al. | Day-ahead stochastic coordinated scheduling for thermal-hydro-wind-photovoltaic systems | |
| CN111525601B (en) | Charging and discharging control method and device for user side energy storage equipment and storage medium | |
| US9235847B2 (en) | Energy-disutility modeling for agile demand response | |
| WO2020103048A1 (en) | Energy storage management and control method, system, computer device, and storage medium | |
| Abdulaal et al. | Two-stage discrete-continuous multi-objective load optimization: An industrial consumer utility approach to demand response | |
| CN110535183B (en) | Scheduling method and system of virtual power plant | |
| CN112070301A (en) | Method, system and equipment for adjusting power consumption of user | |
| WO2020123799A1 (en) | Hybrid power plant | |
| KR102463146B1 (en) | HEMS optimization method and apparatus using hierarchical deep reinforcement learning | |
| JP2020039222A (en) | Power supply-demand control device, power supply-demand control system, and power supply-demand control method | |
| CN110705738B (en) | Intelligent electricity utilization stimulation demand response method and system based on artificial intelligence | |
| US20140365023A1 (en) | Systems and Methods for Computer Implemented Energy Management | |
| Wang et al. | Learning-based energy management policy with battery depth-of-discharge considerations | |
| CN113555887B (en) | Power grid energy control method and device, electronic equipment and storage medium | |
| US20230129279A1 (en) | Systems and methods for renewable powerplant serving multiple loads | |
| CN114243681B (en) | Power utilization regulation and control method, device, equipment and storage medium of power system | |
| CN115411725B (en) | Coordination control method and device for virtual power plant, electronic equipment and storage medium | |
| CN109301820A (en) | A kind of enterprise's electrical control method and system | |
| Zhou et al. | Energy management for energy internet: a combination of game theory and big data-based renewable power forecasting | |
| Wang et al. | Reinforcement learning based bilevel real-time pricing strategy for a smart grid with distributed energy resources | |
| CN113988473A (en) | Method, system, device and storage medium for configuring energy in region | |
| Cho et al. | Two-stage robust unit commitment with uncertain demand response | |
| CN117293916B (en) | User-oriented power grid dispatching method and device and computing equipment | |
| WO2023069161A1 (en) | Target function prioritization of control modes for renewable electric generation resource and charge storage device |
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 |