CN113904380A - Virtual power plant adjustable resource accurate control method considering demand response - Google Patents
Virtual power plant adjustable resource accurate control method considering demand response Download PDFInfo
- Publication number
- CN113904380A CN113904380A CN202111171340.7A CN202111171340A CN113904380A CN 113904380 A CN113904380 A CN 113904380A CN 202111171340 A CN202111171340 A CN 202111171340A CN 113904380 A CN113904380 A CN 113904380A
- Authority
- CN
- China
- Prior art keywords
- adjustable
- control
- layer
- regulation
- power plant
- 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
- 230000004044 response Effects 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000005457 optimization Methods 0.000 claims abstract description 27
- 230000002787 reinforcement Effects 0.000 claims abstract description 25
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 10
- 230000001276 controlling effect Effects 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 23
- 230000001105 regulatory effect Effects 0.000 claims description 22
- 238000004146 energy storage Methods 0.000 claims description 12
- 230000006854 communication Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000002360 preparation method Methods 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005265 energy consumption Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 239000003795 chemical substances by application Substances 0.000 description 18
- 238000005516 engineering process Methods 0.000 description 8
- 229920000642 polymer Polymers 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012800 visualization 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
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- H02J13/00001—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
- 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]
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/12—Monitoring or controlling equipment for energy generation units, e.g. distributed energy generation [DER] or load-side generation
- Y04S10/126—Monitoring or controlling equipment for energy generation units, e.g. distributed energy generation [DER] or load-side generation the energy generation units being or involving electric vehicles [EV] or hybrid vehicles [HEV], i.e. power aggregation of EV or HEV, vehicle to grid arrangements [V2G]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S50/00—Market activities related to the operation of systems integrating technologies related to power network operation or related to communication or information technologies
- Y04S50/16—Energy services, e.g. dispersed generation or demand or load or energy savings aggregation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Power Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a virtual power plant adjustable resource accurate control method considering demand response, which comprises the following steps: acquiring adjustable resource information of a virtual power plant, and evaluating the regulation and control potential of the adjustable resource; classifying and layering adjustable resources of the virtual power plant, and constructing a multilayer control framework of the adjustable resources of the virtual power plant; establishing an adjustable resource optimization control model and a regulation constraint model of the virtual power plant; decomposing the adjustable resource control task of the virtual power plant to form a multi-layer subtask, solving an optimization control problem by adopting a layered depth reinforcement learning algorithm, and controlling a task regulation and control instruction to perform automatic optimal decomposition and issuing layer by layer from top to bottom. The invention can improve the precision of the adjustable resource control and can process the nonlinearity, the randomness and the uncertainty in the actual control.
Description
Technical Field
The invention belongs to the technical field of power resource regulation and control, and relates to a virtual power plant adjustable resource accurate control method considering demand response.
Background
The term "virtual power plant" was sourced from the "virtual utility" by doctor SHimon averebuch in 1997, in his work: description, technology and competitiveness of emerging industries definition of virtual public facilities in book: virtual utilities are a flexible collaboration between independent and market-driven entities that can provide consumers with the efficient electrical energy services they need without having to own the corresponding assets. Just as the virtual public facilities provide consumer-oriented electric energy services by using emerging technologies, the virtual power plant does not change the grid-connected mode of each distributed power supply, but aggregates different types of distributed energy sources such as the distributed power supplies, the energy storage system, the controllable loads, the electric vehicles and the like by advanced technologies such as control, metering, communication and the like, and realizes the coordinated optimization operation of a plurality of distributed energy sources by a higher-level software framework, thereby being more beneficial to the reasonable optimization configuration and utilization of resources.
The concept of the virtual power plant emphasizes the functions and effects presented to the outside, the operation concept is updated, social and economic benefits are generated, and the basic application scene is the power market. The method can aggregate the distributed energy to stably transmit power to the public network without modifying the power grid, provides auxiliary service with quick response, becomes an effective method for adding the distributed energy into the power market, reduces the unbalance risk of independent operation in the market, and can obtain the benefit of scale economy. Meanwhile, the impact of the grid connection of the conventional distributed energy sources on a public network is greatly reduced by visualization of the distributed energy sources and coordinated control optimization of a virtual power plant, the scheduling difficulty caused by the increase of the distributed power sources is reduced, the power distribution management tends to be more reasonable and orderly, and the stability of system operation is improved.
The virtual power plant is an effective means for constructing large-scale, normalized and accurate distributed resource adjustability, can effectively realize friendly interaction of distributed resources and a power system, realizes integration and distribution of various resources, and has great application value.
Virtual power plants have been practiced many times worldwide, the development of virtual power plants also brings new challenges to power system scheduling, and unreasonable scheduling control often increases power network loss and reduces the economy of power grid operation. The existing virtual power plant control method has the following defects: a centralized control architecture is adopted, so that the algorithm is complex and the calculated amount is large; the regulation and control instruction is decomposed to a specific unit according to the weight, and the optimization cannot be realized; the control algorithm cannot cope with the non-linearity, randomness and uncertainty of the system. Therefore, an accurate control method for the fine granularity of the adjustable resources of the virtual power plant is lacked.
Disclosure of Invention
In order to overcome the defects in the prior art, the application provides the accurate control method for the adjustable resources of the virtual power plant, considering the demand response.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for accurately controlling adjustable resources of a virtual power plant in consideration of demand response comprises the following steps:
step 1: acquiring adjustable resource information of the virtual power plant based on the cloud side architecture, and evaluating the regulation and control potential of the adjustable resource;
step 2: classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resource participating in the demand response and the regulation and control information of the adjustable resources, and constructing a multi-layer control framework of the adjustable resources of the virtual power plant corresponding to different types of control tasks by combining a cloud side framework;
and step 3: establishing adjustable resource optimization control models of the virtual power plant and regulation constraint models thereof corresponding to different types of control tasks based on a multilayer control architecture of the adjustable resources of the virtual power plant according to a demand response strategy and an evaluation result of the regulation potential of the adjustable resources;
and 4, step 4: and (3) solving the optimization control model established in the step (3) by using a multi-layer deep reinforcement learning algorithm of multi-layer task cooperation to obtain a regulation and control instruction of each layer, and then issuing an instruction according to the cloud edge architecture to control specific adjustable resources to participate in the control task.
The invention further comprises the following preferred embodiments:
preferably, the cloud edge architecture in step 1 includes a cloud platform, an edge server and an intelligent terminal;
the intelligent terminal is deployed on the resource-adjustable equipment of the virtual power plant, comprises a sensor and an actuator and is used for state sensing and control;
forming edge agents based on the cooperation of the cloud platform and the edge server, wherein all the edge agents are uniformly managed by the cloud platform, and the edge agents and the cloud platform carry out information interaction through a communication network;
the edge agent distributes equipment codes, equipment numbers, user names and passwords to the intelligent terminals connected with the edge server, receives and processes data of the intelligent terminals, sends processed state sensing results to the cloud platform, receives regulation and control instructions of the cloud platform and sends the regulation and control instructions to the intelligent terminals.
Preferably, step 1 is specifically:
the intelligent terminal is used for sensing the model, the parameters and the state data of the adjustable resources of the virtual power plant, the edge server receives the sensed data and extracts the relevant information of the adjustable resources of the virtual power plant through edge calculation, and the regulation and control potential of the adjustable resources is evaluated.
Preferably, the adjustable resources of the virtual power plant comprise a gas turbine set, a photovoltaic generator set, a wind turbine set, an energy storage device and adjustable resources on the demand side.
Preferably, the extracting of the relevant information of the adjustable resources of the virtual power plant and the evaluation of the regulation and control potential of the adjustable resources comprise:
acquiring a typical daily load curve of an adjustable resource, and predicting the maximum power load;
calculating an adjustable proportion of the adjustable resources, a single-user adjustment potential evaluation index and a regional adjustment potential evaluation index based on the typical daily load curve and the maximum power load of the adjustable resources;
wherein, for each type of adjustable resource, the adjustable ratio is equal to the adjustable capacity divided by the total capacity;
the regulation and control potential evaluation index of each single user comprises the following steps:
basic indexes are as follows: regulating and controlling capacity, regulating and controlling time, regulating and controlling precision, regulating and controlling speed and duration;
the composite performance index is as follows: comprehensively regulating and controlling a performance index A, a payment acceptance performance index B, a service time reliability index C, a service capacity reliability index D and a capacity rebound index;
and multiplying the various adjustable resource potential evaluation indexes in the region by each region to obtain a region regulation and control potential evaluation index value.
Preferably, the composite performance index calculation formula is:
comprehensive regulation performance index A ═ A1A2A3;
Wherein A is1Is the ratio of the actual control speed to the standard control speed, A2Is the ratio of the actual control precision to the standard control precision, A3The ratio of the actual preparation time to the standard preparation time;
the performance index B is beta1B1+β2B2+β3B3+β4B4+β5B5;
Wherein, B1、B2、B3、B4、B5The ratio of actual value to standard value of preparation time, regulation speed, regulation precision, regulation capacity and regulation time, beta1,β2,β3,β4,β5Are respectively B1、B2、B3、B4、B5The weight value of (1);
service time reliability index C ═ C1/C2;
Wherein, C1For the actual regulation of the time for the capacity to reach 90% of the total capacity, C2Total regulation time;
service capacity reliability index D ═ D (D)1+D2+D3)/D4;
Wherein D is1In response to a time within 5% of the capacity deviation, D2The deviation of the response capacity is 5 to 10 percentTime of (D)3In response to a time of 10% to 20% deviation of capacity, D4Total regulation time;
capacity rebound index E ═ E1/(E2E3);
Wherein E is1To adjust for capacity above baseline after completion, E2As baseline load, E3Is the bounce time.
Preferably, the control tasks in step 2 include frequency adjustment, voltage adjustment, peak clipping and valley filling, and new energy consumption.
Preferably, step 2 is specifically:
classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resources participating in the demand response, the regulation potential, the regulation characteristic and the spatial distribution of the adjustable resources;
based on the cloud edge terminal cooperation and resource layering structure, the regulation and control instruction is issued to the edge agent through the cloud platform and is gradually issued according to the resource layering structure until the intelligent terminal at the bottommost layer receives the regulation and control instruction to complete control, and the whole process forms a multi-layer control framework of the virtual power plant for regulating resources;
in the multilayer control architecture of the virtual power plant adjustable resources, the regulation and control instruction of each layer corresponding to the resource participating in the control task can be decomposed to the next layer according to a decomposition formula until the regulation and control instruction of the granularity of a specific unit or equipment is decomposed.
Preferably, the classifying and layering of the adjustable resources participating in the control task specifically includes:
aiming at a specific demand response control task, corresponding different types of adjustable resources are divided into a first layer, specific resources of the first layer are divided into resource groups of a second layer, the resource groups of the second layer are divided into finer and more specific units or equipment of a third layer, and the like until the granularity of the units or the equipment is divided, so that a layered structure of the adjustable resources of the virtual power plant is obtained.
Preferably, step 3 is specifically:
the method comprises the steps of establishing a virtual power plant adjustable resource optimization control model based on a virtual power plant adjustable resource multi-layer control framework, considering a demand response strategy based on price or based on excitation, a response scene, a response scale and response time of demand response, and establishing a regulation constraint model according to a regulation potential evaluation result of adjustable resources, wherein the optimization control model comprises specific regulation instructions of each layer in the multi-layer framework.
Preferably, in step 3, the adjustable resource optimization control model of the virtual power plant establishes an objective function with the maximum income of the virtual power plant, specifically:
where R (t) is the revenue that can be obtained from an adjustable resource under either price-based or incentive-based demand response strategies, Co(t) virtual plant operating management costs and operating costs of tunable resources, CpAnd (t) penalty cost of the deviation of the actual output of the virtual power plant and the dispatching plan.
Preferably, it is assumed that there is N in a certain control task1The first layer of scalable resource cluster participation, the profit R (t) is expressed as
Wherein, Pi(t) is the output of the ith cluster, namely the regulation and control instruction of the ith cluster of the first layer, and F (t) is a gain function;
the regulation and control instruction of the ith cluster of the first layer is distributed to a specific adjustable resource group of the second layer, and the decomposition formula is
Wherein N is2The number of adjustable resource groups, alpha, corresponding to the ith cluster of the first layer at the second layerjDecomposition parameter, P, for the jth Adjustable resource groupij(t) is a regulation and control instruction decomposed to the jth adjustable resource group of the second layer, and so on to obtain each layerThe regulation and control command of (2) decomposes the relationship.
Preferably, in step 3, considering a gas turbine set, an energy storage device, a photovoltaic generator set, a wind turbine set and a demand side adjustable load of the virtual power plant, establishing the following regulation and control constraint model:
regulating capacity constraint Pmin≤P≤Pmax;
Wherein P ismin,PmaxRespectively, the minimum value and the maximum value of the capacity;
adjusting speed constraint Smin≤P(t)-P(t-1)≤Smax;
Wherein Smin,SmaxMinimum and maximum values of speed, respectively;
wherein T isPA time period available for adjustment;
Wherein P isrealIn order to be able to adjust the actual output of the resource,respectively, the minimum value and the maximum value of the precision;
constraint of comprehensive control performance Amin≤A≤Amax;
Amin,AmaxRespectively the minimum value and the maximum value of the comprehensive performance;
performance constraint of acceptance Bmin≤B≤Bmax;
Bmin,BmaxRespectively the minimum value and the maximum value of the payment acceptance performance.
Preferably, in step 4, the optimized control model established in step 3 is solved by using a multi-layer deep reinforcement learning algorithm with multi-layer task cooperation, the adjustable resource control task of the virtual power plant is decomposed to form multi-layer subtasks, each layer seeks a local optimal solution for each current layer subtask through the deep reinforcement learning algorithm to obtain a regulation instruction of each layer, and the optimized solution of the whole control problem is completed through the multi-layer deep reinforcement learning algorithm, specifically:
when the control instructions are automatically and optimally decomposed and issued layer by layer from top to bottom, decomposition parameters are introduced, the decomposition and the issuing of the control instructions of each layer are realized by a deep reinforcement learning algorithm of the layer, a reward function is the sum of the output deviation and the operating cost of the adjustable resources of the layer, the observed quantity is the control instructions of the layer which receives the previous layer, the action is the decomposition parameters of the control instructions of the layer, and the reinforcement learning strategy is that the mapping relation between the observed quantity and the action is established by a deep neural network.
The beneficial effect that this application reached:
1. the method evaluates the regulation and control potential of the adjustable resources of the virtual power plant, and the evaluation result can be used for the subsequent classification and layering of the adjustable resources and the formation of regulation and control constraint, so that the practicability and the accuracy of the accurate control method can be improved.
2. The invention provides a reliable and rapid communication framework for realizing the method for accurately controlling the adjustable resources of the virtual power plant by adopting the technologies of edge computing, cloud-edge-end cooperation, network reconstruction and the like.
3. According to the method, the adjustable resources are layered, the adjustable resource control task of the virtual power plant is decomposed to form a multi-layer subtask, and a method for automatically and optimally decomposing and issuing the regulating and controlling instruction from top to bottom layer by layer is provided, so that the accuracy of the adjustable resource control can be improved, and the accurate control of the adjustable resources of the virtual power plant with fine granularity in different demand response scenes can be realized.
4. The invention solves the layered optimal control problem by adopting a layered deep reinforcement learning algorithm, and can process nonlinearity, randomness and uncertainty in actual control.
Drawings
FIG. 1 is a flow chart of a method for accurately controlling adjustable resources of a virtual power plant in consideration of demand response according to the present invention.
Detailed Description
The present application is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present application is not limited thereby.
As shown in FIG. 1, the method for accurately controlling the adjustable resources of the virtual power plant in consideration of demand response comprises the following steps:
step 1: the method comprises the steps of acquiring adjustable resource information of the virtual power plant based on a cloud side architecture, and evaluating the regulation and control potential of the adjustable resource, and specifically comprises the following steps:
the method comprises the following steps of sensing data such as models, parameters and states of the adjustable resources of the virtual power plant by using an intelligent terminal, receiving the sensed data by an edge server, extracting relevant information of the adjustable resources of the virtual power plant through edge calculation, and evaluating the regulation and control potential of the adjustable resources, wherein the data comprises the following steps:
acquiring a typical daily load curve of an adjustable resource, and predicting the maximum power load;
calculating an adjustable proportion of the adjustable resources, a single-user adjustment potential evaluation index and a regional adjustment potential evaluation index based on the typical daily load curve and the maximum power load of the adjustable resources;
wherein, for each type of adjustable resource, the adjustable ratio is equal to the adjustable capacity divided by the total capacity;
the regulation and control potential evaluation index of each single user comprises the following steps:
basic indexes such as regulation capacity, regulation time, regulation precision, regulation speed, duration and the like;
comprehensively regulating and controlling composite performance indexes such as a performance index A, a payment acceptance performance index B, a service time reliability index C, a service capacity reliability index D, a capacity rebound index E and the like;
and multiplying the various adjustable resource potential evaluation indexes in the region by each region to obtain a region regulation and control potential evaluation index value.
The composite performance index calculation formula is as follows:
comprehensive regulation performance index A ═ A1A2A3;
Wherein A is1Is the ratio of the actual control speed to the standard control speed, A2Is the ratio of the actual control precision to the standard control precision, A3The ratio of the actual preparation time to the standard preparation time;
the performance index B is beta1B1+β2B2+β3B3+β4B4+β5B5;
Wherein, B1、B2、B3、B4、B5The ratio of actual value to standard value of preparation time, regulation speed, regulation precision, regulation capacity and regulation time, beta1,β2,β3,β4,β5Are respectively B1、B2、B3、B4、B5The weight value of (1);
service time reliability index C ═ C1/C2;
Wherein, C1For the actual regulation of the time for the capacity to reach 90% of the total capacity, C2Total regulation time;
service capacity reliability index D ═ D (D)1+D2+D3)/D4;
Wherein D is1In response to a time within 5% of the capacity deviation, D2In response to a time of 5% to 10% deviation of capacity, D3In response to a time of 10% to 20% deviation of capacity, D4Total regulation time;
capacity rebound index E ═ E1/(E2E3);
Wherein E is1To adjust for capacity above baseline after completion, E2As baseline load, E3Is the bounce time.
During specific implementation, the adjustable resources of the virtual power plant comprise a gas turbine set, a photovoltaic generator set, a wind turbine generator set, energy storage equipment, adjustable resources of demand sides such as industrial loads, commercial loads and residential loads, and the like.
The cloud side architecture comprises a cloud platform, an edge server and an intelligent terminal;
the intelligent terminal is deployed on the resource-adjustable equipment of the virtual power plant, comprises a sensor and an actuator and is used for state sensing and control;
forming edge agents based on the cooperation of the cloud platform and the edge server, wherein all the edge agents are uniformly managed by the cloud platform, and the edge agents and the cloud platform carry out information interaction through communication networks such as public networks and optical fibers;
the method comprises the steps that an edge agent distributes information such as equipment codes, equipment numbers, user names and passwords to an intelligent terminal connected with an edge server, receives and processes data of the intelligent terminal, sends a state sensing result obtained through processing to a cloud platform, receives a regulation and control instruction of the cloud platform and sends the regulation and control instruction to the intelligent terminal;
the cooperation of the cloud platform and the edge server comprises the supplement and cooperation of cloud and edge computing resources, the cooperative security defense in the data communication process and the cooperative completion of the accurate control task of the adjustable resources of the virtual power plant.
The cloud side architecture corresponds to a layered structure of adjustable resources of the virtual power plant, the cloud platform is responsible for management and regulation of the whole virtual power plant, the intelligent terminal is responsible for sensing and control of specific adjustable equipment on the bottommost layer, the edge agent is responsible for management and regulation of resources on the middle layer, and information interaction is carried out among the cloud platform, the edge server and the intelligent terminal through a communication network.
When the type, the quantity, the distribution, the management authority, the regulation mode and the like of the adjustable resources are changed, a virtual power plant communication network architecture capable of adapting to the change is established by utilizing a network reconstruction technology.
The middle layer resource responsible for the edge agent comprises a multilayer structure comprising a cluster layer, an adjustable resource group, a specific adjustable resource and other levels, and the arrangement of the edge server and the connection between the intelligent terminal and the edge agent are completed by adopting an optimization method.
Step 2: classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resource participating in the demand response and the regulation and control information of the adjustable resources, and constructing a multilayer control framework of the adjustable resources of the virtual power plant corresponding to different types of control tasks by combining a cloud side framework, specifically:
classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resources participating in the demand response and factors such as the regulation potential, the regulation characteristic and the spatial distribution of the adjustable resources, and the method specifically comprises the following steps:
aiming at a specific demand response control task, corresponding different types of adjustable resources are divided into a first layer, specific resources of the first layer are divided into resource groups of a second layer, the resource groups of the second layer are divided into finer and more specific units or equipment of a third layer, and the like until the granularity of the units or the equipment is divided, so that a layered structure of the adjustable resources of the virtual power plant is obtained.
Further based on the cloud edge terminal cooperation and resource layering structure, the regulation and control instruction is issued to the edge agent through the cloud platform and is gradually issued according to the resource layering structure until the intelligent terminal at the bottommost layer receives the regulation and control instruction to complete control, and the whole process forms a multi-layer control framework of the virtual power plant for regulating resources;
in the multilayer control architecture of the virtual power plant adjustable resources, the regulation and control instruction of each layer corresponding to the resource participating in the control task can be decomposed to the next layer according to a decomposition formula until the regulation and control instruction of the granularity of a specific unit or equipment is decomposed.
The specific embodiment of step 2 is as follows:
first, the adjustable resources with the same regulation and control characteristics and closer spatial distribution distance are integrated into a polymer with larger capacity, such as an electronics factory polymer, an air conditioner polymer, a lithium battery energy storage polymer, and the like.
And then, layering the adjustable resources of the virtual power plant from the system level according to the adjustable capacity and the adjustable speed which can be provided by participating in frequency modulation.
According to the order of participating in frequency modulation, the first layer is a cluster layer and comprises: the system comprises an adjustable load cluster, an energy storage cluster, a gas turbine set cluster, a wind generating set cluster and a photovoltaic generating set cluster.
The second layer is an adjustable resource group, for example, for an industrial load group, the adjustable resource group includes an industrial load group 1, an industrial load group 2, an industrial load group 3, and the like, and is ordered according to the order participating in frequency modulation.
The third layer is a specific tunable resource, such as the industrial load group 1 including electronics plant aggregates, metal processing plant aggregates, cement manufacturing plant aggregates, etc., and is also ordered according to the order of participation in frequency modulation.
Finally, in order to realize accurate control of the adjustable resources, the granularity of the unit or the equipment is further layered, such as specific adjustable equipment of an electronic factory, specific energy storage devices of an energy storage station and the like.
Based on a network reconstruction technology among a cloud platform, an edge server and an edge agent, a multi-layer control framework of multi-type, multi-scene and multi-time scale virtual power plant adjustable resources can be formed by combining a cooperation-self-control coupling optimization control method and a small micro-terminal level edge optimization method.
Corresponding to the layered structure of the adjustable resources of the virtual power plant, the cloud platform is responsible for management and regulation of the whole virtual power plant, the intelligent terminal is responsible for sensing and control of specific adjustable equipment at the bottom layer, the edge agent is responsible for management and regulation of resources at the middle layer, and information interaction is carried out among the cloud platform, the edge server and the intelligent terminal through a communication network.
When the type, the quantity, the distribution, the management authority, the regulation mode and the like of the adjustable resources are changed, a virtual power plant communication network architecture capable of adapting to the change is established by utilizing a network reconstruction technology.
The middle layer resource responsible for the edge agent comprises a multilayer structure comprising a cluster layer, an adjustable resource group, a specific adjustable resource and other levels, and the arrangement of the edge server and the connection between the intelligent terminal and the edge agent are completed by adopting an optimization method.
The adjustable resources of the virtual power plant can be matched to correspond to specific types suitable in the multiple types of adjustable resources according to different control tasks, the regulation and control instruction is issued to the edge agent through the cloud platform and is gradually issued to the lower-layer system according to the layered structure until the intelligent terminal at the bottommost layer receives the regulation and control instruction to complete control, and a multi-layer control framework of the multiple types, multiple scenes and multiple time scales of the adjustable resources of the virtual power plant is formed.
And step 3: the method comprises the steps of establishing a virtual power plant adjustable resource optimization control model based on a virtual power plant adjustable resource multi-layer control framework, considering a demand response strategy based on price or based on excitation, a response scene, a response scale and response time of demand response, and establishing a regulation constraint model according to a regulation potential evaluation result of adjustable resources, wherein the optimization control model comprises specific regulation instructions of each layer in the multi-layer framework.
Namely, the optimization control model is not established in a layered mode, but a layered structure is considered, specific regulating and controlling instructions of each layer are considered, the process that the regulating and controlling instructions of the previous layer are decomposed to the next layer is achieved through a reinforcement learning task corresponding to each layer. And 4, solving the optimized control model established in the step 3 to obtain the regulation and control instruction of each layer.
Specifically, the adjustable resource optimization control model of the virtual power plant establishes an objective function with the maximum income of the virtual power plant:
where R (t) is the revenue that can be obtained from an adjustable resource under either price-based or incentive-based demand response strategies, Co(t) virtual plant operating management costs and operating costs of tunable resources, CpAnd (t) penalty cost of the deviation of the actual output of the virtual power plant and the dispatching plan.
Suppose there is N in a certain control task1The first layer of scalable resource cluster participation, the profit R (t) is expressed as
Wherein, Pi(t) is the output of the ith cluster, namely the regulation and control instruction of the ith cluster of the first layer, and F (t) is a gain function;
first layer ith clusterThe regulating instruction is distributed to a specific adjustable resource group of the second layer, and the decomposition formula is
Wherein N is2The number of adjustable resource groups, alpha, corresponding to the ith cluster of the first layer at the second layerjDecomposition parameter, P, for the jth Adjustable resource groupijAnd (t) decomposing the regulation and control instruction of the jth adjustable resource group on the second layer, and repeating the steps to obtain the regulation and control instruction decomposition relation of each layer.
Considering the gas turbine set, the energy storage equipment, the photovoltaic generator set, the wind generating set and the adjustable load of the demand side of the virtual power plant, establishing the following regulation and control constraint model:
regulating capacity constraint Pmin≤P≤Pmax;
Wherein P ismin,PmaxRespectively, the minimum value and the maximum value of the capacity;
adjusting speed constraint Smin≤P(t)-P(t-1)≤Smax;
Wherein Smin,SmaxMinimum and maximum values of speed, respectively;
wherein T isPA time period available for adjustment;
Wherein P isrealIn order to be able to adjust the actual output of the resource,respectively, the minimum value and the maximum value of the precision;
constraint of comprehensive control performance Amin≤A≤Amax;
Amin,AmaxRespectively the minimum value and the maximum value of the comprehensive performance;
performance constraint of acceptance Bmin≤B≤Bmax;
Bmin,BmaxRespectively the minimum value and the maximum value of the payment acceptance performance.
The method can also comprise the following steps that the sum of the lower-layer regulation and control instructions is equal to the equality constraint of the upper-layer issued instructions, the inequality constraint of the ramp rate limit of the output of the gas turbine unit and the upper and lower limits of the regulation capacity, the charge-discharge constraint and the residual capacity constraint of the energy storage equipment, the regulation capacity constraint of resources such as a photovoltaic generator set, a wind turbine generator set and a demand-side adjustable load and the like.
And 4, step 4: and (3) solving the optimized control model established in the step (3) by utilizing a multi-layer deep reinforcement learning algorithm of multi-layer task cooperation to obtain a regulation and control instruction of each layer, and then issuing an instruction according to a cloud edge architecture to control specific adjustable resources to participate in a control task:
the optimized control model established in the step 3 is solved by utilizing a multilayer depth reinforcement learning algorithm of multilayer task cooperation, the adjustable resource control task of the virtual power plant is decomposed to form multilayer subtasks, each layer seeks a local optimal solution to each current layer subtask through the depth reinforcement learning algorithm to obtain a regulation and control instruction of each layer, and the optimized solution of the whole control problem is completed through the multilayer depth reinforcement learning algorithm, specifically:
when the control instructions are automatically and optimally decomposed and issued layer by layer from top to bottom, decomposition parameters are introduced, the decomposition and the issuing of the control instructions of each layer are realized by a deep reinforcement learning algorithm of the layer, a reward function is the sum of the output deviation and the operating cost of the adjustable resources of the layer, the observed quantity is the control instructions of the layer which receives the previous layer, the action is the decomposition parameters of the control instructions of the layer, and the reinforcement learning strategy is that the mapping relation between the observed quantity and the action is established by a deep neural network.
Specific examples are as follows:
decomposing the adjustable resource control task of the virtual power plant to form a multi-layer subtask, considering the nonlinearity, randomness, uncertainty and complexity of an optimization control problem, solving the optimization control problem by adopting a layered depth reinforcement learning algorithm, automatically and optimally decomposing and issuing a regulation instruction layer by layer from top to bottom, and performing state perception, parameter perception and control perception by using a cloud edge end framework to realize the control of the adjustable resource of the virtual power plant with fine granularity under different demand response scenes.
Taking the virtual power plant resource participating in the power system frequency modulation task as an example, classifying and layering the adjustable resources participating in the frequency modulation, decomposing the regulation and control instruction of each layer corresponding to the resource participating in the frequency modulation to the second layer according to a decomposition formula, decomposing the regulation and control instruction of the second layer to the third layer according to the decomposition formula in the same way until the granularity of a specific unit or equipment is decomposed, and establishing an optimal control model and constraint conditions of the adjustable resources according to the response strategy of an application scene.
For the regulation and control instruction decomposition task of each layer, the deep reinforcement learning algorithm of the corresponding layer is used for learning, and the randomness caused by wind power photovoltaic and the uncertainty caused by participation in demand response in the model can be processed. The established optimization control model is solved by using a multi-layer depth reinforcement learning method of multi-layer task cooperation, the regulation and control instruction of each layer can be obtained, then the instruction is issued according to the cloud-edge-end structure, and the specific adjustable resource can be accurately controlled to participate in frequency modulation.
1. The method evaluates the regulation and control potential of the adjustable resources of the virtual power plant, and the evaluation result can be used for the subsequent classification and layering of the adjustable resources and the formation of regulation and control constraint, so that the practicability and the accuracy of the accurate control method can be improved.
2. The invention provides a reliable and rapid communication framework for realizing the method for accurately controlling the adjustable resources of the virtual power plant by adopting the technologies of edge computing, cloud-edge-end cooperation, network reconstruction and the like.
3. According to the method, the adjustable resources are layered, the adjustable resource control task of the virtual power plant is decomposed to form a multi-layer subtask, the method for automatically and optimally decomposing and issuing the regulating and controlling instruction layer by layer from top to bottom is provided, and the accuracy of adjustable resource control can be improved.
4. The invention solves the layered optimal control problem by adopting a layered deep reinforcement learning algorithm, and can process nonlinearity, randomness and uncertainty in actual control.
The present applicant has described and illustrated embodiments of the present invention in detail with reference to the accompanying drawings, but it should be understood by those skilled in the art that the above embodiments are merely preferred embodiments of the present invention, and the detailed description is only for the purpose of helping the reader to better understand the spirit of the present invention, and not for limiting the scope of the present invention, and on the contrary, any improvement or modification made based on the spirit of the present invention should fall within the scope of the present invention.
Claims (14)
1. The utility model provides a virtual power plant adjustable resource accurate control method considering demand response, which is characterized in that:
the method comprises the following steps:
step 1: acquiring adjustable resource information of the virtual power plant based on the cloud side architecture, and evaluating the regulation and control potential of the adjustable resource;
step 2: classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resource participating in the demand response and the regulation and control information of the adjustable resources, and constructing a multi-layer control framework of the adjustable resources of the virtual power plant corresponding to different types of control tasks by combining a cloud side framework;
and step 3: establishing adjustable resource optimization control models of the virtual power plant and regulation constraint models thereof corresponding to different types of control tasks based on a multilayer control architecture of the adjustable resources of the virtual power plant according to a demand response strategy and an evaluation result of the regulation potential of the adjustable resources;
and 4, step 4: and (3) solving the optimization control model established in the step (3) by using a multi-layer deep reinforcement learning algorithm of multi-layer task cooperation to obtain a regulation and control instruction of each layer, and then issuing an instruction according to the cloud edge architecture to control specific adjustable resources to participate in the control task.
2. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
the cloud side architecture in the step 1 comprises a cloud platform, an edge server and an intelligent terminal;
the intelligent terminal is deployed on the resource-adjustable equipment of the virtual power plant, comprises a sensor and an actuator and is used for state sensing and control;
forming edge agents based on the cooperation of the cloud platform and the edge server, wherein all the edge agents are uniformly managed by the cloud platform, and the edge agents and the cloud platform carry out information interaction through a communication network;
the edge agent distributes equipment codes, equipment numbers, user names and passwords to the intelligent terminals connected with the edge server, receives and processes data of the intelligent terminals, sends processed state sensing results to the cloud platform, receives regulation and control instructions of the cloud platform and sends the regulation and control instructions to the intelligent terminals.
3. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
the step 1 specifically comprises the following steps:
the intelligent terminal is used for sensing the model, the parameters and the state data of the adjustable resources of the virtual power plant, the edge server receives the sensed data and extracts the relevant information of the adjustable resources of the virtual power plant through edge calculation, and the regulation and control potential of the adjustable resources is evaluated.
4. The method for accurately controlling the adjustable resources of the virtual power plant in consideration of the demand response according to any one of claims 1 to 3, wherein:
the adjustable resources of the virtual power plant comprise a gas turbine set, a photovoltaic generator set, a wind generating set, energy storage equipment and adjustable resources on a demand side.
5. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 3, wherein:
the method for extracting relevant information of the adjustable resources of the virtual power plant and evaluating the regulation and control potential of the adjustable resources comprises the following steps:
acquiring a typical daily load curve of an adjustable resource, and predicting the maximum power load;
calculating an adjustable proportion of the adjustable resources, a single-user adjustment potential evaluation index and a regional adjustment potential evaluation index based on the typical daily load curve and the maximum power load of the adjustable resources;
wherein, for each type of adjustable resource, the adjustable ratio is equal to the adjustable capacity divided by the total capacity;
the regulation and control potential evaluation index of each single user comprises the following steps:
basic indexes are as follows: regulating and controlling capacity, regulating and controlling time, regulating and controlling precision, regulating and controlling speed and duration;
the composite performance index is as follows: comprehensively regulating and controlling a performance index A, a payment acceptance performance index B, a service time reliability index C, a service capacity reliability index D and a capacity rebound index;
and multiplying the various adjustable resource potential evaluation indexes in the region by each region to obtain a region regulation and control potential evaluation index value.
6. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 5, wherein:
the composite performance index calculation formula is as follows:
comprehensive regulation performance index A ═ A1A2A3;
Wherein A is1Is the ratio of the actual control speed to the standard control speed, A2Is the ratio of the actual control precision to the standard control precision, A3The ratio of the actual preparation time to the standard preparation time;
the performance index B is beta1B1+β2B2+β3B3+β4B4+β5B5;
Wherein, B1、B2、B3、B4、B5The ratio of actual value to standard value of preparation time, regulation speed, regulation precision, regulation capacity and regulation time, beta1,β2,β3,β4,β5Are respectively B1、B2、B3、B4、B5The weight value of (1);
service time reliability index C ═ C1/C2;
Wherein, C1For the actual regulation of the time for the capacity to reach 90% of the total capacity, C2Total regulation time;
service capacity reliability index D ═ D (D)1+D2+D3)/D4;
Wherein D is1In response to a time within 5% of the capacity deviation, D2In response to a time of 5% to 10% deviation of capacity, D3In response to a time of 10% to 20% deviation of capacity, D4Total regulation time;
capacity rebound index E ═ E1/(E2E3);
Wherein E is1To adjust for capacity above baseline after completion, E2As baseline load, E3Is the bounce time.
7. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
and 2, controlling tasks including frequency adjustment, voltage adjustment, peak clipping and valley filling and new energy consumption.
8. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
the step 2 specifically comprises the following steps:
classifying and layering the adjustable resources participating in the control task according to the control task of the adjustable resources participating in the demand response, the regulation potential, the regulation characteristic and the spatial distribution of the adjustable resources;
based on the cloud edge terminal cooperation and resource layering structure, the regulation and control instruction is issued to the edge agent through the cloud platform and is gradually issued according to the resource layering structure until the intelligent terminal at the bottommost layer receives the regulation and control instruction to complete control, and the whole process forms a multi-layer control framework of the virtual power plant for regulating resources;
in the multilayer control architecture of the virtual power plant adjustable resources, the regulation and control instruction of each layer corresponding to the resource participating in the control task can be decomposed to the next layer according to a decomposition formula until the regulation and control instruction of the granularity of a specific unit or equipment is decomposed.
9. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 8, wherein:
the classification and layering of the adjustable resources participating in the control task specifically comprises:
aiming at the demand response control task, the corresponding different types of adjustable resources are divided into a first layer, then the resources of the first layer are divided into resource groups of a second layer, then the resource groups of the second layer are divided into resource groups of a third layer, and the like until the granularity of the groups or equipment is divided, so that the layered structure of the adjustable resources of the virtual power plant is obtained.
10. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
the step 3 specifically comprises the following steps:
the method comprises the steps of establishing a virtual power plant adjustable resource optimization control model based on a virtual power plant adjustable resource multi-layer control framework, considering a demand response strategy based on price or based on excitation, a response scene, a response scale and response time of demand response, and establishing a regulation constraint model according to a regulation potential evaluation result of adjustable resources, wherein the optimization control model comprises specific regulation instructions of each layer in the multi-layer framework.
11. The method for accurately controlling the adjustable resources of the virtual power plant in consideration of the demand response, as claimed in claim 1 or 10, wherein:
in step 3, the adjustable resource optimization control model of the virtual power plant establishes an objective function with the virtual power plant income maximization, specifically:
where R (t) is the revenue that can be obtained from an adjustable resource under either price-based or incentive-based demand response strategies, Co(t) virtual plant operating management costs and operating costs of tunable resources, CpAnd (t) penalty cost of the deviation of the actual output of the virtual power plant and the dispatching plan.
12. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 11, wherein:
suppose there is N in a certain control task1The first layer of scalable resource cluster participation, the profit R (t) is expressed as
Wherein, Pi(t) is the output of the ith cluster, namely the regulation and control instruction of the ith cluster of the first layer, and F (t) is a gain function;
the regulation and control instruction of the ith cluster of the first layer is distributed to a specific adjustable resource group of the second layer, and the decomposition formula is
Wherein N is2The number of adjustable resource groups, alpha, corresponding to the ith cluster of the first layer at the second layerjDecomposition parameter, P, for the jth Adjustable resource groupijAnd (t) decomposing the regulation and control instruction of the jth adjustable resource group on the second layer, and repeating the steps to obtain the regulation and control instruction decomposition relation of each layer.
13. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 11, wherein:
in step 3, considering the gas turbine set, the energy storage equipment, the photovoltaic generator set, the wind turbine generator set and the demand side adjustable load of the virtual power plant, establishing the following regulation and control constraint model:
regulating capacity constraint Pmin≤P≤Pmax;
Wherein P ismin,PmaxRespectively, the minimum value and the maximum value of the capacity;
adjusting speed constraint Smin≤P(t)-P(t-1)≤Smax;
Wherein Smin,SmaxMinimum and maximum values of speed, respectively;
wherein T isPA time period available for adjustment;
Wherein P isrealIn order to be able to adjust the actual output of the resource,respectively, the minimum value and the maximum value of the precision;
constraint of comprehensive control performance Amin≤A≤Amax;
Amin,AmaxRespectively the minimum value and the maximum value of the comprehensive performance;
performance constraint of acceptance Bmin≤B≤Bmax;
Bmin,BmaxRespectively the minimum value and the maximum value of the payment acceptance performance.
14. The method for accurately controlling the adjustable resources of the virtual power plant by considering the demand response as claimed in claim 1, wherein:
in step 4, the optimized control model established in step 3 is solved by using a multilayer deep reinforcement learning algorithm with multilayer task cooperation, the adjustable resource control task of the virtual power plant is decomposed to form multilayer subtasks, each layer seeks a local optimal solution for each current layer subtask through the deep reinforcement learning algorithm to obtain a regulation and control instruction of each layer, and the optimized solution of the whole control problem is completed through the multilayer deep reinforcement learning algorithm, specifically:
when the control instructions are automatically and optimally decomposed and issued layer by layer from top to bottom, decomposition parameters are introduced, the decomposition and the issuing of the control instructions of each layer are realized by a deep reinforcement learning algorithm of the layer, a reward function is the sum of the output deviation and the operating cost of the adjustable resources of the layer, the observed quantity is the control instructions of the layer which receives the previous layer, the action is the decomposition parameters of the control instructions of the layer, and the reinforcement learning strategy is that the mapping relation between the observed quantity and the action is established by a deep neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111171340.7A CN113904380B (en) | 2021-10-08 | 2021-10-08 | Virtual power plant adjustable resource accurate control method considering demand response |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111171340.7A CN113904380B (en) | 2021-10-08 | 2021-10-08 | Virtual power plant adjustable resource accurate control method considering demand response |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113904380A true CN113904380A (en) | 2022-01-07 |
CN113904380B CN113904380B (en) | 2023-06-27 |
Family
ID=79190253
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111171340.7A Active CN113904380B (en) | 2021-10-08 | 2021-10-08 | Virtual power plant adjustable resource accurate control method considering demand response |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113904380B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114219186A (en) * | 2022-02-21 | 2022-03-22 | 南方电网数字电网研究院有限公司 | Optimal regulation and control method for virtual power plant participating in multi-market transaction based on digital twin |
CN114765373A (en) * | 2022-01-21 | 2022-07-19 | 太原理工大学 | Multilayer distribution method for secondary frequency modulation requirements among frequency modulation resources |
CN116544955A (en) * | 2023-07-03 | 2023-08-04 | 阳光慧碳科技有限公司 | Load regulation and control method, device and system |
CN116757445A (en) * | 2023-08-14 | 2023-09-15 | 国网上海能源互联网研究院有限公司 | Method, device, equipment and medium for quickly distributing adjustment capability of virtual power plant |
CN118095806A (en) * | 2024-04-28 | 2024-05-28 | 国网山东省电力公司营销服务中心(计量中心) | Virtual power plant resource scheduling method, system, medium, equipment and program product |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120130556A1 (en) * | 2010-11-18 | 2012-05-24 | Marhoefer John J | Virtual power plant system and method incorporating renewal energy, storage and scalable value-based optimization |
CN103903066A (en) * | 2014-04-04 | 2014-07-02 | 东南大学 | Virtual power plant stratified random optimized dispatching method |
CN110188950A (en) * | 2019-05-30 | 2019-08-30 | 三峡大学 | Virtual plant supply side and Demand-side Optimized Operation modeling method based on multi-agent technology |
CN111245026A (en) * | 2020-03-09 | 2020-06-05 | 国网冀北电力有限公司 | Virtual power plant regulation and control method, system and equipment |
CN111355233A (en) * | 2020-03-18 | 2020-06-30 | 国网浙江嘉善县供电有限公司 | Multi-virtual power plant coordination optimization control method |
CN112928749A (en) * | 2021-01-18 | 2021-06-08 | 西安交通大学 | Virtual power plant day-ahead scheduling method integrating multi-energy demand side resources |
CN113013929A (en) * | 2021-04-20 | 2021-06-22 | 天津大学 | Load curve adjustment-oriented active power distribution network simulation optimization operation method |
-
2021
- 2021-10-08 CN CN202111171340.7A patent/CN113904380B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120130556A1 (en) * | 2010-11-18 | 2012-05-24 | Marhoefer John J | Virtual power plant system and method incorporating renewal energy, storage and scalable value-based optimization |
CN103903066A (en) * | 2014-04-04 | 2014-07-02 | 东南大学 | Virtual power plant stratified random optimized dispatching method |
CN110188950A (en) * | 2019-05-30 | 2019-08-30 | 三峡大学 | Virtual plant supply side and Demand-side Optimized Operation modeling method based on multi-agent technology |
CN111245026A (en) * | 2020-03-09 | 2020-06-05 | 国网冀北电力有限公司 | Virtual power plant regulation and control method, system and equipment |
CN111355233A (en) * | 2020-03-18 | 2020-06-30 | 国网浙江嘉善县供电有限公司 | Multi-virtual power plant coordination optimization control method |
CN112928749A (en) * | 2021-01-18 | 2021-06-08 | 西安交通大学 | Virtual power plant day-ahead scheduling method integrating multi-energy demand side resources |
CN113013929A (en) * | 2021-04-20 | 2021-06-22 | 天津大学 | Load curve adjustment-oriented active power distribution network simulation optimization operation method |
Non-Patent Citations (2)
Title |
---|
张高;王旭;蒋传文;张裕;王正宇;: "采用双层优化调度的虚拟电厂经济性分析", 电网技术 * |
李作锋,黄奇峰,杨世海: "适应新型电力供需的多元化友好互动体系研究", 江苏电机工程 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114765373A (en) * | 2022-01-21 | 2022-07-19 | 太原理工大学 | Multilayer distribution method for secondary frequency modulation requirements among frequency modulation resources |
CN114765373B (en) * | 2022-01-21 | 2024-03-22 | 太原理工大学 | Multi-layer distribution method for secondary frequency modulation requirements among frequency modulation resources |
CN114219186A (en) * | 2022-02-21 | 2022-03-22 | 南方电网数字电网研究院有限公司 | Optimal regulation and control method for virtual power plant participating in multi-market transaction based on digital twin |
CN116544955A (en) * | 2023-07-03 | 2023-08-04 | 阳光慧碳科技有限公司 | Load regulation and control method, device and system |
CN116544955B (en) * | 2023-07-03 | 2023-11-24 | 阳光慧碳科技有限公司 | Load regulation and control method, device and system |
CN116757445A (en) * | 2023-08-14 | 2023-09-15 | 国网上海能源互联网研究院有限公司 | Method, device, equipment and medium for quickly distributing adjustment capability of virtual power plant |
CN116757445B (en) * | 2023-08-14 | 2023-11-14 | 国网上海能源互联网研究院有限公司 | Method, device, equipment and medium for quickly distributing adjustment capability of virtual power plant |
CN118095806A (en) * | 2024-04-28 | 2024-05-28 | 国网山东省电力公司营销服务中心(计量中心) | Virtual power plant resource scheduling method, system, medium, equipment and program product |
Also Published As
Publication number | Publication date |
---|---|
CN113904380B (en) | 2023-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113904380B (en) | Virtual power plant adjustable resource accurate control method considering demand response | |
Wang et al. | Interactive dispatch modes and bidding strategy of multiple virtual power plants based on demand response and game theory | |
Lv et al. | Interactive energy management of networked microgrids-based active distribution system considering large-scale integration of renewable energy resources | |
Yi et al. | Coordinated operation strategy for a virtual power plant with multiple DER aggregators | |
CN108875992A (en) | A kind of virtual plant Optimization Scheduling a few days ago considering demand response | |
CN114219212B (en) | Flexible scheduling method for demand side resources considering ubiquitous electric power Internet of things and edge calculation | |
Gazijahani et al. | A new point estimate method for stochastic optimal operation of smart distribution systems considering demand response programs | |
CN107492886A (en) | A kind of power network monthly electricity purchasing scheme optimization method containing wind-powered electricity generation under Regional Electric Market | |
CN110518580A (en) | Active power distribution network operation optimization method considering micro-grid active optimization | |
CN113708365A (en) | Virtual power plant energy management and control optimization method and system based on end edge cloud architecture | |
CN114243709A (en) | Scheduling operation method capable of adjusting resource layering and grading at demand side | |
Yang et al. | Multi-Objective optimal scheduling of island microgrids considering the uncertainty of renewable energy output | |
CN107887932A (en) | Virtual power plant is bidded method for organizing in the production of ahead market | |
CN109685287A (en) | Increment power distribution network power supply capacity multiple-objection optimization configuration method | |
CN114612001B (en) | Regulation and control instruction decomposition method and system for cluster electric automobile participating in power grid peak clipping | |
CN114205381B (en) | System comprising virtual power plant load classification, resource modeling and participation in electric power market transaction | |
CN117526454B (en) | Virtual power plant operation management method, device and storage medium | |
Jian et al. | An analytical polytope approximation aggregation of electric vehicles considering uncertainty for the day-ahead distribution network dispatching | |
CN115313361A (en) | Joint optimization control method and device for large-scale adjustable resources | |
CN115000985A (en) | Aggregation control method and system for user-side distributed energy storage facilities | |
Wu et al. | A coordinated model for multiple electric vehicle aggregators to grid considering imbalanced liability trading | |
CN113364043A (en) | Micro-grid group optimization method based on condition risk value | |
Zhang et al. | Nodal dynamic charging price formulation for electric vehicle through the Stackelberg game considering grid congestion | |
CN110556821A (en) | Multi-microgrid double-layer optimization scheduling method considering interactive power control and bilateral bidding transaction | |
CN114549148A (en) | Virtual power plant bidding method, device, equipment and storage medium |
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 |