Power grid regulation and control method and device and storage medium

Abstract

The invention discloses a power grid regulation and control method and device and a storage medium. The method comprises the following steps: constructing a demand side regulation and control model and a supply side regulation and control model; wherein the target function of the demand side regulation and control model is constructed according to the clearing price and the regulation and control demand, the target function of the supply side regulation and control model is constructed by taking the optimal bidding strategy as the target, and the capacity adjustment constraint of the supply side regulation and control model is constructed according to the enabled capacity and the bidding capacity of the battery energy storage system; constructing a double-layer regulation and control model according to the demand side regulation and control model and the supply side regulation and control model; and solving the double-layer regulation and control model to obtain a frequency control strategy of the demand side and a bidding strategy of the supplier. According to the invention, the double-layer regulation and control model is constructed according to the demand side regulation and control model and the supply side regulation and control model, the resource allocation in the electricity market can be effectively coordinated and optimized, the method can adapt to the market rule complexity and changeable environment, and then the power grid frequency stability can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid control, and in particular to a power grid control method, device and storage medium. Background Art

[0002] As the global demand for renewable energy increases, a large number of renewable energy sources such as wind and solar energy are connected to the power grid. These renewable energy sources are random and intermittent, which directly leads to frequency fluctuations in the power grid, thus affecting the safety and stability of the power system. In order to ensure the stability of the power grid frequency, various power markets, especially the FCAS (Frequency Control Ancillary Services) market, purchase frequency regulation services through a bidding mechanism to compensate for the fluctuations in the output of renewable energy.

[0003] As an emerging flexible resource, battery energy storage system (BESS) has the advantages of fast response and bidirectional regulation (both charging and discharging) in the power system, and is widely regarded as one of the core tools for frequency regulation in the future power market. Especially in the FCAS market, BESS can provide frequency control auxiliary services for the power grid with its instantaneous power regulation capability to improve the frequency stability of the power grid. However, due to the complex market rules and changing environment, the existing power grid regulation methods are difficult to effectively improve the frequency stability of the power grid. Summary of the invention

[0004] The present invention provides a power grid control method, device and storage medium to solve the technical problem that the existing power grid control method is difficult to effectively improve the power grid frequency stability.

[0005] The present invention provides a power grid control method, comprising:

[0006] Constructing a demand-side regulation model and a supply-side regulation model; wherein the objective function of the demand-side regulation model is constructed based on the clearing price and the regulation demand, the objective function of the supply-side regulation model is constructed based on the optimal bidding strategy, and the capacity adjustment constraint of the supply-side regulation model is constructed based on the enabled capacity and the bidding capacity of the battery energy storage system;

[0007] Constructing a two-layer regulation model according to the demand-side regulation model and the supply-side regulation model;

[0008] Solve the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0009] Furthermore, the objective function of the demand-side regulation model is:

[0010]

[0011] in, represents the clearing price of the mth type of service at time t, Indicates the demand during this period.

[0012] Furthermore, the capacity adjustment constraint of the supply-side regulation model is:

[0013]

[0014] in, The capacity of the battery energy storage system is enabled. Bid capacity for battery energy storage systems.

[0015] Furthermore, solving the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side includes:

[0016] Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment;

[0017] Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0018] Furthermore, the power grid control method also includes: constructing constraints of the deep reinforcement learning model based on potential losses and risk tolerance parameters.

[0019] The present invention also provides a power grid control device, comprising:

[0020] A single-layer control model construction module is used to construct a demand-side control model and a supply-side control model; wherein the objective function of the demand-side control model is constructed based on the clearing price and the control demand, the objective function of the supply-side control model is constructed with the optimal bidding strategy as the goal, and the capacity adjustment constraint of the supply-side control model is constructed based on the enabled capacity and the bidding capacity of the battery energy storage system;

[0021] A two-layer regulation model construction module, used to construct a two-layer regulation model according to the demand-side regulation model and the supply-side regulation model;

[0022] The control model solving module is used to solve the double-layer control model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0023] Furthermore, the control model solving module is also used for:

[0024] Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment;

[0025] Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0026] Furthermore, it also includes constructing constraints of the deep reinforcement learning model based on potential losses and risk tolerance parameters.

[0027] The present invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned power grid control method when executing the computer program.

[0028] The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid control method as described above.

[0029] The embodiment of the present invention constructs a two-layer control model based on the demand-side control model and the supply-side control model, which can effectively coordinate and optimize resource allocation in the power market, adapt to the complexity of market rules and the changing environment, and thus effectively improve the frequency stability of the power grid.

[0030] Furthermore, the embodiment of the present invention introduces a deep reinforcement learning model and constructs the constraints of the deep reinforcement learning model according to the potential loss and risk tolerance parameters. When optimizing the bidding strategy, it can comprehensively consider the uncertainty in the market, especially under extreme market conditions, so as to ensure that the optimal bidding strategy can be obtained. In addition, by introducing a large language model, the intelligence level of the BESS bidding strategy can be effectively improved, and it can cope with complex and changing market environments, and enhance the real-time response capability of the system and the interpretability of decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of a power grid control method provided by an embodiment of the present invention;

[0032] Figure 2 It is a structural schematic diagram of a power grid control device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] In the description of this application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0035] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0036] See also Figure 1 The present invention provides a power grid control method, comprising:

[0037] S1. Construct a demand-side regulation model and a supply-side regulation model; wherein the objective function of the demand-side regulation model is constructed based on the clearing price and regulation demand, the objective function of the supply-side regulation model is constructed based on the optimal bidding strategy, and the capacity adjustment constraint of the supply-side regulation model is constructed based on the enabled capacity and bidding capacity of the battery energy storage system;

[0038] In an embodiment of the present invention, the demander may be a market operator, and the regulation demand may be an FCAS demand, wherein the categories of FCAS demand include upward regulation demand, downward regulation demand, and emergency response demand. In an embodiment of the present invention, the market operator may publish a bidding demand to the market, and purchase services according to the bidding price and capacity allocation to meet its regulation demand.

[0039] In the embodiment of the present invention, the supplier may be a BESS bidder, and the BESS participates in the bidding for services in different frequency bands through a step-by-step bidding method. For each time period t, the BESS may select different bidding prices and capacities in each service category, and may bid for specific capacity. and bidding price They represent the bidding capacity and price of the mth service at time t respectively.

[0040] S2. Construct a two-layer regulation model based on the demand-side regulation model and the supply-side regulation model;

[0041] The embodiment of the present invention constructs a double-layer regulation model based on the demand-side regulation model and the supply-side regulation model, which can accurately simulate the actual operating procedures in the FCAS market and ensure a high degree of consistency between the model and the actual market, so as to solve and obtain reliable frequency control strategies and bidding strategies.

[0042] S3. Solve the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0043] In an embodiment of the present invention, the demand-side regulation model is used to solve the frequency control strategy, and the supply-side regulation model is used to solve the bidding strategy to obtain the maximum economic benefit through bidding. The embodiment of the present invention constructs a two-layer regulation model based on the demand-side regulation model and the supply-side regulation model, which can effectively coordinate and optimize the resource allocation in the power market, adapt to the complexity of market rules and the changing environment, and thus effectively improve the frequency stability of the power grid.

[0044] In one embodiment, the objective function of the demand-side regulation model is:

[0045]

[0046] in, represents the clearing price of the mth type of service at time t, Indicates the demand during this period.

[0047] In one embodiment, the capacity adjustment constraint of the supply-side regulation model is:

[0048]

[0049] in, The capacity of the battery energy storage system is enabled. Bid capacity for battery energy storage systems.

[0050] In one embodiment, the market operator can sort the bids of all participants from low to high according to the price, and gradually enable bidding until the market demand is met. The final clearing price is the highest price enabled. The specific formula is:

[0051]

[0052] in, It is a binary variable, indicating whether the bidding of the kth tier of the nth BESS is enabled.

[0053] In the embodiment of the present invention, the relationship between the bidding capacity and the bidding price is as follows:

[0054]

[0055] In one embodiment, step S3, solving the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side, includes:

[0056] S31. Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment;

[0057] In this embodiment of the present invention, the optimization goal of the deep reinforcement learning model is:

[0058]

[0059] Among them, r t is the profit function at time t, and the profit is directly determined by the bidding strategy of BESS.

[0060] In an embodiment of the present invention, in order to prevent the market from suffering large losses under extreme conditions, the constraint conditions of the deep reinforcement learning model can be constructed according to the potential loss and risk tolerance parameters. The constraint condition is expressed as:

[0061]

[0062] Among them, L represents the potential loss and ξ is the risk tolerance parameter.

[0063] The embodiment of the present invention can control the losses under extreme conditions by constructing the constraints of the deep reinforcement learning model, so as to solve the optimal bidding strategy.

[0064] S32. Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0065] In the embodiment of the present invention, the intelligent decision-making framework assisted by the large language model can be combined to solve the two-layer control model. Through the natural language processing and reasoning capabilities of the large language model, the deep learning model can be helped to cope with the complex and changing market environment, provide intelligent decision-making support, and further improve the frequency stability of the power grid. Among them, the intelligent decision-making framework assisted by the large language model includes a market analysis module, a strategy recommendation module, and a self-reflection module.

[0066] The market analysis module is used to identify potential market risks and opportunities by analyzing market data and rules. For example, it can identify potential market risks and opportunities when market prices fluctuate abnormally or demand changes significantly.

[0067] The strategy recommendation module is used to provide price reduction strategy suggestions based on its knowledge base and reasoning ability when the deep reinforcement learning model is unable to cope with the situation. These suggestions can be used as a reference for the DRL agent to help it adjust its bidding strategy and enhance the real-time and adaptability of the strategy.

[0068] The self-reflection module is used to identify and correct potential errors in the decision-making process through the collaboration of the large language model and the deep reinforcement learning model, and improve the reliability and interpretability of the decision. For example, when the DRL model makes a poor decision under conditions of volatile market conditions, the LLM can provide feedback and improvement suggestions by analyzing historical decisions and market data, further improving the reliability and interpretability of the decision.

[0069] In a specific embodiment, assuming that the FCAS market demand in a national electricity market (NEM) fluctuates during a certain period of time, the BESS needs to optimize its bidding strategy based on the real-time market price and demand to maximize its economic benefits while meeting the market demand.

[0070] The market environment includes:

[0071] Market demand: During this period, the market demand for frequency regulation services is 100MW, and the demand is distributed in different frequency bands (such as upward regulation services, downward regulation services, etc.).

[0072] Price Fluctuation: Market prices are highly volatile, with forecasts showing prices could fluctuate between 20MW and 100MW.

[0073] BESS status: The current energy storage status of BESS is 80%, and the available charging and discharging power is 50MW.

[0074] Bidding strategy optimization includes:

[0075] State representation: The BESS agent constructs a state vector based on information such as current market demand, price forecast, and energy storage status.

[0076] Action selection: The agent selects the bidding strategy on different frequency bands, including price and bidding capacity. In this example, the bidding capacity of BESS in the up-regulation service is 40MW and the bidding price is 30MW; the bidding capacity in the down-regulation service is 10MW and the bidding price is 50MW.

[0077] Risk management: Due to the large fluctuations in market prices, the agent evaluates the potential risks of different bidding strategies through the CVaR model and selects the optimal strategy that strikes a balance between benefits and risks.

[0078] Strategy adjustment: If the market fluctuates significantly (for example, prices exceed the predicted range), the real-time recommendations provided by LLM will help the DRL agent adjust its bidding strategy, such as increasing the bidding price for upward-adjusted services and reducing the bidding capacity for downward-adjusted services.

[0079] The implementation of the embodiments of the present invention has the following beneficial effects:

[0080] The embodiment of the present invention constructs a two-layer control model based on the demand-side control model and the supply-side control model, which can effectively coordinate and optimize resource allocation in the power market, adapt to the complexity of market rules and the changing environment, and thus effectively improve the frequency stability of the power grid.

[0081] Furthermore, the embodiment of the present invention introduces a deep reinforcement learning model and constructs the constraints of the deep reinforcement learning model according to the potential loss and risk tolerance parameters. When optimizing the bidding strategy, it can comprehensively consider the uncertainty in the market, especially under extreme market conditions, so as to ensure that the optimal bidding strategy can be obtained. By introducing a large language model, the intelligence level of the BESS bidding strategy can be effectively improved, and it can cope with complex and changing market environments, and enhance the real-time response capability of the system and the interpretability of decisions.

[0082] See also Figure 2 Based on the same inventive concept as the above embodiment, the present invention further provides a power grid control device, comprising:

[0083] A single-layer control model construction module 10 is used to construct a demand-side control model and a supply-side control model; wherein the objective function of the demand-side control model is constructed based on the clearing price and the control demand, the objective function of the supply-side control model is constructed based on the optimal bidding strategy, and the capacity adjustment constraint of the supply-side control model is constructed based on the enabled capacity and the bidding capacity of the battery energy storage system;

[0084] A two-layer control model construction module 20, used to construct a two-layer control model according to a demand-side control model and a supply-side control model;

[0085] The control model solving module 30 is used to solve the double-layer control model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0086] In one embodiment, the objective function of the demand-side regulation model is:

[0087]

[0088] in, represents the clearing price of the mth type of service at time t, Indicates the demand during this period.

[0089] In one embodiment, the capacity adjustment constraint of the supply-side regulation model is:

[0090]

[0091] in, The capacity of the battery energy storage system is enabled. Bid capacity for battery energy storage systems.

[0092] In one embodiment, the control model solving module 30 is further used to:

[0093] Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment;

[0094] Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

[0095] In one embodiment, constraints for constructing a deep reinforcement learning model are also included based on potential loss and risk tolerance parameters.

[0096] Correspondingly, an embodiment of the present invention also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the power grid control method of any one of the above embodiments is implemented.

[0097] The terminal device of this embodiment includes: a processor, a memory, and a computer program and computer instructions stored in the memory and executable on the processor. When the processor executes the computer program, each step in the above embodiment 1 is implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of each module / unit in the above device embodiment are realized, such as the double-layer control model construction module 20.

[0098] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in a memory and executed by a processor to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing a specific function, and the instruction segments are used to describe the execution process of the computer program in a terminal device. For example, a two-layer control model construction module 20 is used to construct a two-layer control model based on a demand-side control model and a supply-side control model.

[0099] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a terminal device and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the terminal device may also include an input / output device, a network access device, a bus, etc.

[0100] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0101] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0102] Among them, if the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0103] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a power grid control method as described in any one of the above embodiments.

[0104] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power grid control method, characterized in that: include: Constructing a demand-side regulation model and a supply-side regulation model; wherein the objective function of the demand-side regulation model is constructed based on the clearing price and the regulation demand, the objective function of the supply-side regulation model is constructed based on the optimal bidding strategy, and the capacity adjustment constraint of the supply-side regulation model is constructed based on the enabled capacity and the bidding capacity of the battery energy storage system; Constructing a two-layer regulation model according to the demand-side regulation model and the supply-side regulation model; Solve the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

2. The power grid control method according to claim 1, characterized in that: The objective function of the demand-side regulation model is: in, represents the clearing price of the mth type of service at time t, Indicates the demand during this period.

3. The power grid control method according to claim 1, characterized in that: The capacity adjustment constraint of the supply-side regulation model is: in, The capacity of the battery energy storage system is enabled. Bid capacity for battery energy storage systems.

4. The power grid control method according to claim 1, characterized in that: The step of solving the two-layer regulation model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side includes: Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment; Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

5. The power grid control method according to claim 4, characterized in that: It also includes constraints for constructing the deep reinforcement learning model based on potential loss and risk tolerance parameters.

6. A power grid control device, characterized in that: include: A single-layer control model construction module is used to construct a demand-side control model and a supply-side control model; wherein the objective function of the demand-side control model is constructed based on the clearing price and the control demand, the objective function of the supply-side control model is constructed with the optimal bidding strategy as the goal, and the capacity adjustment constraint of the supply-side control model is constructed based on the enabled capacity and the bidding capacity of the battery energy storage system; A two-layer regulation model construction module, used to construct a two-layer regulation model according to the demand-side regulation model and the supply-side regulation model; The control model solving module is used to solve the double-layer control model to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

7. The power grid control device according to claim 6, characterized in that: The control model solving module is also used for: Build a deep reinforcement learning model with the goal of maximizing benefits in an uncertain environment; Combined with the deep reinforcement learning model, the two-layer regulation model is solved to obtain the frequency control strategy of the demand side and the bidding strategy of the supply side.

8. The power grid control device according to claim 7, characterized in that: It also includes constraints for constructing the deep reinforcement learning model based on potential loss and risk tolerance parameters.

9. A terminal device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the power grid control method according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program; wherein, when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the power grid control method according to any one of claims 1 to 5.

Images