An energy storage revenue dynamic scheduling method, device, equipment and storage medium

Abstract

The application discloses a kind of energy storage benefit dynamic scheduling method, device, equipment and storage medium.The method comprises: obtaining the energy storage system for storing electric energy, the first energy storage parameter corresponding to the first time.The target solver is determined based on the first energy storage parameter and the first predicted electricity price in the first time according to the first predicted electricity price in the first time in advance, and the first charging and discharging power in the first time is determined.The energy storage system is dynamically scheduled based on the first charging and discharging power to maximize the energy storage benefit of the energy storage system in the first time scheduling period.The application can significantly improve the economic benefit and service life of the energy storage system, so that the energy storage benefit is maximized in the fluctuating power market.

Description

Technical Field

[0001] This invention relates to the field of energy storage technology, and in particular to a method, apparatus, equipment and storage medium for dynamic scheduling of energy storage revenue. Background Technology

[0002] In recent years, with the deepening of electricity market reforms worldwide, the electricity price formation mechanism has shifted from government-set pricing to being dynamically determined by market supply and demand, exhibiting significant volatility.

[0003] Against this backdrop, on the one hand, the high peak-valley electricity price difference provides potential arbitrage opportunities for market participants; on the other hand, the power grid urgently needs effective regulation measures to cope with fluctuations in renewable energy output, smooth out load peaks and valleys, and provide rapid backup support in system emergencies to ensure power supply security and stability. Energy storage systems (ESS), with their rapid and precise energy throughput capabilities and flexible time-scale regulation characteristics, have shown great application potential in addressing these challenges.

[0004] Currently, the main way energy storage systems realize their value in the electricity market is by charging during off-peak hours and discharging during peak hours, thereby profiting directly from market price differences (energy arbitrage). Therefore, designing and implementing efficient and intelligent operation strategies and control systems for energy storage systems in a dynamic and ever-changing electricity market environment to maximize economic benefits and meet grid service demands has become a core focus of current energy storage technology research and development and commercial applications. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and storage medium for dynamic scheduling of energy storage revenue, which significantly improves the economic benefits and service life of energy storage systems, and maximizes the commercial value of energy storage revenue in a fluctuating electricity market.

[0006] According to one aspect of the present invention, a method for dynamic scheduling of energy storage revenue is provided. The method includes:

[0007] Obtain the first energy storage parameter corresponding to the first moment of the energy storage system used to store electrical energy, wherein the first energy storage parameter information includes at least the energy storage charge, the charge and discharge efficiency, and the charge extreme value;

[0008] Based on a pre-built target solver, the first charging and discharging power at the first time is determined according to the first energy storage parameters and the first predicted electricity price at the first time. The target solver is a mixed integer linear programming solver, which includes an energy storage revenue function. The energy storage revenue function is constructed based on the transaction revenue function, system loss function, and energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage load at the last time in the preset prediction window.

[0009] The energy storage load in the energy storage system is dynamically scheduled based on the first charging and discharging power, so as to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment.

[0010] According to another aspect of the present invention, a dynamic scheduling device for energy storage revenue is provided. The device includes:

[0011] An energy storage parameter acquisition module is used to acquire the first energy storage parameters of an energy storage system for storing electrical energy at a first moment, wherein the first energy storage parameter information includes at least the energy storage charge, the charge and discharge efficiency, and the charge extreme value.

[0012] A charge / discharge power determination module is used to determine the first charge / discharge power at the first moment based on a pre-built target solver, according to the first energy storage parameters and a pre-predicted first electricity price at the first moment. The target solver is a mixed integer linear programming solver, and the target solver includes an energy storage revenue function. The energy storage revenue function is constructed based on a transaction revenue function, a system loss function, and an energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage charge at the last moment of the preset prediction window.

[0013] The energy storage dynamic scheduling module is used to dynamically schedule the energy storage load in the energy storage system based on the first charging and discharging power, so as to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the energy storage revenue dynamic scheduling method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the dynamic scheduling method for energy storage revenue as described in any embodiment of the present invention.

[0019] The technical solution of this invention obtains the first energy storage parameters of an energy storage system for storing electrical energy at a first moment. Based on a pre-built target solver, a first charge / discharge power is determined at the first moment according to the first energy storage parameters and a pre-predicted first electricity price at the first moment. The energy storage load in the energy storage system is dynamically scheduled based on the first charge / discharge power to maximize the energy storage revenue of the energy storage system within the scheduling period at the first moment. This effectively solves the core problem of balancing economy and safety in real-time electricity market transactions for electrochemical energy storage. It dynamically optimizes the charge / discharge strategy under complex electricity price environments, enhances the economic value of energy storage throughout its entire lifecycle, ensures the safe operation of the energy storage system, and maximizes the net revenue of energy storage.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a dynamic scheduling method for energy storage revenue provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a structural diagram of an energy storage revenue dynamic scheduling device provided in embodiments two and three of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the dynamic scheduling method for energy storage revenue according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This is a flowchart of a dynamic scheduling method for energy storage revenue provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the charging and discharging strategy of an energy storage system is dynamically determined in future time periods based on the goal of maximizing net energy storage revenue. This method can be executed by a dynamic scheduling device for energy storage revenue, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0029] S101. Obtain the first energy storage parameters corresponding to the first moment of the energy storage system used to store electrical energy.

[0030] The "first moment" can refer to the moment when dynamic adjustments to energy storage are required, such as the current moment or a future moment. For example, the first energy storage parameter information includes at least the energy storage charge, charge / discharge efficiency, and extreme charge values.

[0031] Specifically, by querying on-site or remotely calling parameters, the first energy storage parameters of the energy storage system that needs to be mobilized at the first moment can be queried.

[0032] S102. Based on the pre-built target solver, determine the first charging and discharging power at the first time according to the first energy storage parameters and the first predicted electricity price at the first time in the electricity price prediction sequence.

[0033] The objective solver is a mixed-integer linear programming solver. In the technical solution of this invention, the objective solver plays the role of the core computing engine. Under multiple parameter conditions, it can transform the theoretical model into the optimal charging and discharging power sequence that satisfies all safety constraints and maximizes economic benefits.

[0034] For example, the objective solver includes an energy storage revenue function, which is constructed based on a transaction revenue function, a system loss function, and an energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage charge at the last moment of the preset prediction window.

[0035] It should be noted that the electricity price prediction sequence is obtained based on a pre-trained target prediction model. The electricity price prediction sequence includes the predicted electricity price for each future prediction time.

[0036] Specifically, the first energy storage parameters and the first predicted electricity price are input into a pre-built target solver, and the first charging and discharging power at the first moment is determined based on the output of the target solver.

[0037] For example, the step of determining the first charging and discharging power at the first time based on the pre-built target solver, according to the first energy storage parameters and the first predicted electricity price at the first time, includes: inputting the first predicted electricity price and the first energy storage parameters into the target solver to perform power sequence prediction, and obtaining a first charging and discharging power sequence of charging and discharging power at each time within the prediction window from the first time based on the output of the target solver; and determining the first charging and discharging power in the first charging and discharging power sequence as the first charging and discharging power corresponding to the first time.

[0038] The first charge / discharge power sequence can refer to a sequence that includes the charge / discharge power at each time point within the prediction window, starting from the first time point.

[0039] Specifically, the first predicted electricity price and the first energy storage parameters are input into the target solver to predict the power sequence, and the first charge-discharge power sequence is obtained based on the output of the target solver. The first charge-discharge power sequence is analyzed, and the first charge-discharge power is determined as the first charge-discharge power corresponding to the first time point.

[0040] It should be noted that the process of determining the charging and discharging power at other times is similar to that of determining the charging and discharging power at the first time. Both require determining the charging and discharging power sequence corresponding to that time and determining the first charging and discharging power as the charging and discharging power corresponding to that time.

[0041] It is worth noting that the reason for determining the charge / discharge power sequence at this moment is that the objective solver includes an energy storage penalty function. This function penalizes situations where the battery charge deviates from a predetermined reference charge at the last moment of the prediction window. The energy storage penalty function is designed to prevent the objective solver from prioritizing short-term gains by pushing the energy storage system's charge close to 0% or 100% without considering the energy storage space required for the next mobilization, and also to maintain the battery's health and ensure its availability for future mobilization.

[0042] For example, the objective solver is represented in the following form:

[0043]

[0044] in, This represents the minimum negative cost of predicting energy storage revenue during the scheduling period at time k, i.e., maximizing the positive cost; Represents the profit function of a transaction; C deg ∑ k |P k |Δt represents the system loss function; λ(E t+H -E ref ) 2 Represents the energy storage penalty function;

[0045] Among them, P k u represents the charging and discharging power during the scheduling period at time k; k It is a binary variable used to distinguish between the charging and discharging processes. During the charging process, u k =1, during the discharge process, u k =0; Represents the predicted electricity price at time k; Δt represents the dispatch period; C deg E represents the decay cost per cycle; λ represents the penalty weight; t+H E represents the stored energy charge at the last time t+H within the preset prediction window H; ref Indicates the reference charge.

[0046] For example, the single-cycle decay cost is expressed in the following form:

[0047]

[0048] Among them, C deg This refers to the cost of decay per cycle; C cell This refers to the cost of the battery cell; N EFC It refers to the equivalent total cycle life; DoD refers to the depth of discharge; γ refers to the depth factor.

[0049] S103. Based on the first charging and discharging power, the energy storage load in the energy storage system is dynamically scheduled to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment.

[0050] Specifically, after determining the first charging and discharging power at the first moment, the energy storage load in the energy storage system is dynamically scheduled according to the first charging and discharging power, so as to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment.

[0051] For example, after determining the first charge / discharge power at the first moment, the method further includes:

[0052] Determine the second actual electricity price and the second predicted electricity price for each moment within a preset historical period, starting from the first moment.

[0053] Based on the second actual electricity price and the second predicted electricity price, determine whether the average absolute prediction error within the preset historical period exceeds a preset error threshold.

[0054] If the mean absolute prediction error exceeds a preset error threshold, an error correction function is constructed based on the error electricity price at the first moment, and the predicted electricity price in the electricity price prediction sequence is corrected for error based on the error correction function.

[0055] Furthermore, the model parameters in the target prediction model are updated and optimized based on the error electricity price at the first moment.

[0056] The second actual electricity price can refer to the actual electricity price at any point within a preset historical period, and the second predicted electricity price can refer to the predicted electricity price at any point within a preset historical period. The preset error threshold can be set according to actual conditions.

[0057] Specifically, determining whether the average absolute prediction error within the preset historical period exceeds a preset error threshold can be achieved in the following way:

[0058]

[0059] Where, δ t This refers to prediction error. π t This refers to the second actual electricity price. This refers to the second predicted electricity price; W refers to the W times within the preset historical period; and ε refers to the preset error threshold.

[0060] If the mean absolute prediction error exceeds a preset error threshold, an error correction function is constructed based on the error price at the first time point, and the predicted electricity price in the electricity price prediction sequence is corrected according to the error correction function. This can be achieved in the following way:

[0061]

[0062] Among them, the left side of the arrow This refers to the revised forecast electricity price, to the right of the arrow. This refers to the predicted electricity price before the revision, κ·δ t e -βτ This refers to the error modification function, where k is the learning rate, β is the decay coefficient, and δ is the error correction function. t This refers to the error price of electricity at the first moment.

[0063] Furthermore, the technical solution of this invention can also update and optimize the model parameters in the target prediction model based on the error electricity price at the first moment, so as to improve the prediction accuracy of the target prediction model in subsequent processes.

[0064] The technical solution of this invention obtains the first energy storage parameters of an energy storage system for storing electrical energy at a first moment. Based on a pre-built target solver, a first charge / discharge power is determined at the first moment according to the first energy storage parameters and a pre-predicted first electricity price at the first moment. The energy storage load in the energy storage system is dynamically scheduled based on the first charge / discharge power to maximize the energy storage revenue of the energy storage system within the scheduling period at the first moment. This effectively solves the core problem of balancing economy and safety in real-time electricity market transactions for electrochemical energy storage. It dynamically optimizes the charge / discharge strategy under complex electricity price environments, enhances the economic value of energy storage throughout its entire lifecycle, ensures the safe operation of the energy storage system, and maximizes the net revenue of energy storage.

[0065] Based on the above embodiments, the construction process of the target solver includes: setting a preset prediction window, scheduling period and reference charge, and constructing a charge state function according to the energy storage parameters of the energy storage system; constructing an energy storage revenue function based on the charge state function, according to the preset prediction window, scheduling period and reference charge; performing piecewise linearization on the energy storage revenue function in sequence, introducing binary variables and solving optimization processing to obtain the target solver.

[0066] Here, the prediction window is set to H, the scheduling period is Δt, and the reference charge is E. ref In this invention, the charge state function and constraints that change with time can be implemented in the following way:

[0067]

[0068] E min ≤E t ≤E max ,|P t |≤P max ;

[0069] Among them, E t E refers to the charge at time t. t+1 η refers to the charge at time t+1, Δt refers to the scheduling period, and η is the charge at time t+1. c This refers to charging efficiency, η d This refers to discharge efficiency, P t This refers to the charging and discharging power, P during charging. t ≥0, P during discharge t <0. E min This refers to the lower limit of charge, E max This refers to the upper limit of charge, P max This refers to the maximum charging and discharging power.

[0070] The constructed energy storage revenue function is shown below:

[0071]

[0072] Where λ is the terminal penalty weight, E ref For reference charge, P refers to the predicted electricity price at time k. t This refers to the charging and discharging power, Δt refers to the scheduling period, and C deg This refers to the cost of decay per cycle, E k+H This refers to the charge at time k+1. It should be noted that the energy storage benefit function means controlling the charging and discharging power from time t to t+H-1 to maximize its value.

[0073] After obtaining the energy storage benefit function, the energy storage benefit function is linearized by piecewise charging and discharging. A binary variable is introduced, and optimization processing is performed to obtain a MILP-form objective solver, as shown below:

[0074]

[0075]

[0076] 0≤u k ≤1,-P max (1-u k )≤P k ≤P max u k ;

[0077] E min ≤Ek ≤E max ;

[0078] Among them, P k This represents the charging and discharging power during the scheduling period at time k; u k It is a binary variable used to distinguish between the charging and discharging processes. During the charging process, u k =1, during the discharge process, u k =0; Represents the predicted electricity price at time k; Δt represents the dispatch period; C deg E represents the decay cost per cycle; λ represents the penalty weight; k+H E represents the stored energy charge at the last moment k+H within the preset prediction window H; ref Indicates the reference charge.

[0079] The above process is the solution to the MPC optimization problem, yielding the MILP form. Its purpose is to transform the "maximization" payoff function and complex nonlinear state equations / constraints into a mathematically easier-to-solve mixed-integer linear programming (MILP) problem. The term "min" is used because a positive "max" is transformed into an equivalent negative "min".

[0080] For example, the energy storage revenue function construction process includes: constructing a transaction revenue function within the preset prediction window based on the predicted electricity price, charging / discharging power, and scheduling cycle at the first prediction time in the preset prediction window; constructing a system loss function within the preset prediction window based on the single-cycle attenuation cost, the charging / discharging power, and the scheduling cycle; determining the energy storage load at the last prediction time in the preset prediction window based on the state of charge function and the energy storage load at the first prediction time in the preset prediction window, and constructing an energy storage penalty function based on the energy storage load and a reference load; and constructing an energy storage revenue function based on the transaction revenue function, the system loss function, and the energy storage penalty function.

[0081] In the energy storage revenue function, Represents the profit function of a transaction; Represents the system loss function; λ(E) t+H -E ref ) 2 Represents the energy storage penalty function;

[0082] in, Let P represent the predicted electricity price at time k. k C represents the charging and discharging power during the scheduling period at time k, and Δt represents the scheduling period; deg E represents the decay cost per cycle; λ represents the penalty weight. k+HE represents the energy storage charge at the last moment k+H within the preset prediction window H. ref Indicates the reference charge.

[0083] It's important to note that the trading revenue function, system loss function, and energy storage penalty function are the three key factors of the energy storage revenue function. Maximizing trading profits through the trading revenue function is the core of energy storage revenue. The system loss function considers the lifespan of the energy storage system to minimize battery degradation costs. The energy storage penalty function ensures the long-term sustainability of the scheduling strategy and battery health.

[0084] Example 2

[0085] Figure 2 This is a schematic diagram of a dynamic scheduling device for energy storage revenue provided in Embodiment 2 of the present invention. Figure 2 As shown, the device includes:

[0086] The energy storage parameter acquisition module 201 is used to acquire the first energy storage parameters of the energy storage system for storing electrical energy at a first moment, wherein the first energy storage parameter information includes at least the energy storage charge, the charge and discharge efficiency and the charge extreme value.

[0087] The charge / discharge power determination module 202 is used to determine the first charge / discharge power at the first moment based on a pre-built target solver, according to the first energy storage parameters and the first predicted electricity price at the first moment. The target solver is a mixed integer linear programming solver, and the target solver includes an energy storage revenue function. The energy storage revenue function is constructed based on a transaction revenue function, a system loss function, and an energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage charge at the last moment of the preset prediction window.

[0088] The energy storage dynamic scheduling module 203 is used to dynamically schedule the energy storage load in the energy storage system based on the first charging and discharging power, so as to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment.

[0089] For example, the objective solver is represented in the following form:

[0090]

[0091] in, This represents the minimum negative cost of predicting energy storage revenue during the scheduling period at time k, i.e., maximizing the positive cost; Represents the profit function of a transaction; C deg ∑ k |P k |Δt represents the system loss function; λ(Et+H -E ref ) 2 Represents the energy storage penalty function;

[0092] Among them, P k This represents the charging and discharging power during the scheduling period at time k; u k It is a binary variable used to distinguish between the charging and discharging processes. During the charging process, u k =1, during the discharge process, u k =0; Represents the predicted electricity price at time k; Δt represents the dispatch period; C deg E represents the decay cost per cycle; λ represents the penalty weight; k+H E represents the stored energy charge at the last moment k+H within the preset prediction window H; ref Indicates the reference charge.

[0093] Optionally, the charge / discharge power determination module 202 is specifically used for:

[0094] The first predicted electricity price and the first energy storage parameters are input into the target solver to predict the power sequence, and the first charge and discharge power sequence is obtained based on the output of the target solver at each time point within the prediction window starting from the first time point.

[0095] The first charge / discharge power in the first charge / discharge power sequence is determined as the first charge / discharge power corresponding to the first moment.

[0096] Optionally, the apparatus further includes a solver construction module, which includes:

[0097] The parameter setting unit is used to set the preset prediction window, scheduling period and reference charge, and to construct the charge state function based on the energy storage parameters of the energy storage system.

[0098] The function construction unit is used to construct an energy storage revenue function based on the energy load state function, according to a preset prediction window, scheduling period and reference energy load.

[0099] The solver construction unit is used to sequentially perform piecewise linearization on the energy storage benefit function, introduce binary variables and perform optimization processing to obtain the target solver.

[0100] Optionally, the function building unit is used for:

[0101] Based on the predicted electricity price, charging and discharging power, and scheduling cycle at the first prediction time in the preset prediction window, a transaction revenue function is constructed within the preset prediction window;

[0102] Based on the single-cycle attenuation cost, the charging and discharging power, and the scheduling period, a system loss function is constructed within the preset prediction window;

[0103] Based on the energy charge state function, the energy charge at the last prediction time in the preset prediction window is determined according to the energy charge at the first prediction time in the preset prediction window, and an energy storage penalty function is constructed based on the energy charge and the reference energy charge.

[0104] An energy storage revenue function is constructed based on the transaction revenue function, the system loss function, and the energy storage penalty function.

[0105] Optionally, the decay cost per cycle is expressed in the following form:

[0106]

[0107] Among them, C deg This refers to the cost of decay per cycle; C cell This refers to the cost of the battery cell; N EFC It refers to the equivalent total cycle life; DoD refers to the depth of discharge; γ refers to the depth factor.

[0108] Optionally, the electricity price prediction sequence is obtained by predicting based on a pre-trained target prediction model;

[0109] The device also includes an error correction module for...

[0110] After determining the first charge / discharge power at the first moment, the process also includes:

[0111] Determine the second actual electricity price and the second predicted electricity price for each moment within a preset historical period, starting from the first moment.

[0112] Based on the second actual electricity price and the second predicted electricity price, determine whether the average absolute prediction error within the preset historical period exceeds a preset error threshold.

[0113] If the mean absolute prediction error exceeds a preset error threshold, an error correction function is constructed based on the error electricity price at the first moment, and the predicted electricity price in the electricity price prediction sequence is corrected for error based on the error correction function.

[0114] Furthermore, the model parameters in the target prediction model are updated and optimized based on the error electricity price at the first moment.

[0115] The energy storage revenue dynamic scheduling device provided in the embodiments of the present invention can execute the energy storage revenue dynamic scheduling method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0116] Example 3

[0117] Figure 3 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0118] like Figure 3 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0120] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the dynamic scheduling method for energy storage revenue.

[0121] In some embodiments, the energy storage revenue dynamic scheduling method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the energy storage revenue dynamic scheduling method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the energy storage revenue dynamic scheduling method by any other suitable means (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0124] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0126] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0127] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0128] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for dynamic scheduling of energy storage revenue, characterized in that, include: Obtain the first energy storage parameter corresponding to the first moment of the energy storage system used to store electrical energy, wherein the first energy storage parameter information includes at least the energy storage charge, the charge and discharge efficiency, and the charge extreme value; Based on a pre-built target solver, the first charging and discharging power at the first moment is determined according to the first energy storage parameters and the first predicted electricity price at the first moment in the electricity price prediction sequence. The target solver is a mixed integer linear programming solver, which includes an energy storage revenue function. The energy storage revenue function is constructed based on the transaction revenue function, system loss function, and energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage load at the last moment of the preset prediction window. Based on the first charging and discharging power, the energy storage load in the energy storage system is dynamically scheduled to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment. The step of determining the first charging and discharging power at the first moment based on the pre-built target solver, according to the first energy storage parameters and the pre-predicted first predicted electricity price at the first moment, includes: The first predicted electricity price and the first energy storage parameters are input into the target solver to predict the power sequence, and the first charge and discharge power sequence is obtained based on the output of the target solver at each time point within the prediction window starting from the first time point. The first charge / discharge power in the first charge / discharge power sequence is determined as the first charge / discharge power corresponding to the first moment.

2. The method according to claim 1, characterized in that, The objective solver is represented in the following form: ； in, Indicates the prediction in the 1st Minimize the negative cost of energy storage revenue within the time-based scheduling cycle, i.e., maximize the positive cost; Represents the profit function of a transaction; Represents the system loss function; Represents the energy storage penalty function; in, Indicates the first Charging and discharging power within the real-time scheduling cycle; These are binary variables used to distinguish between the charging and discharging processes. During the charging process, During the discharge process, ; Indicates the first Forecasted electricity prices at any given time; Indicates the scheduling period; This represents the decay cost per cycle; Indicates the penalty weight; Indicated in the preset prediction window The last moment The energy storage capacity; Indicates the reference charge.

3. The method according to any one of claims 1-2, characterized in that, The process of constructing the objective solver includes: Set a preset prediction window, scheduling period, and reference charge, and construct a charge state function based on the energy storage parameters of the energy storage system; Based on the aforementioned charge state function, an energy storage revenue function is constructed according to a preset prediction window, scheduling period, and reference charge. The energy storage revenue function is sequentially piecewise linearized, and bivariate variables are introduced and optimization processing is performed to obtain the target solver.

4. The method according to claim 3, characterized in that, The process of constructing the energy storage revenue function includes: Based on the predicted electricity price, charging and discharging power, and scheduling cycle at the first prediction time in the preset prediction window, a transaction revenue function is constructed within the preset prediction window; Based on the single-cycle attenuation cost, the charging and discharging power, and the scheduling period, a system loss function is constructed within the preset prediction window; Based on the energy charge state function, the energy charge at the last prediction time in the preset prediction window is determined according to the energy charge at the first prediction time in the preset prediction window, and an energy storage penalty function is constructed based on the energy charge and the reference energy charge. An energy storage revenue function is constructed based on the transaction revenue function, the system loss function, and the energy storage penalty function.

5. The method according to claim 4, characterized in that, The single-cycle decay cost is expressed in the following form: ； in, This refers to the cost of decay per cycle. This refers to the cost of the battery cells; This refers to the equivalent total cycle life; This refers to the depth of discharge; This refers to the depth coefficient.

6. The method according to claim 1, characterized in that, The electricity price prediction sequence is obtained by predicting based on a pre-trained target prediction model; after determining the first charging and discharging power at the first moment, the method further includes: Determine the second actual electricity price and the second predicted electricity price for each time point within a preset historical period, starting from the first time point; Based on the second actual electricity price and the second predicted electricity price, determine whether the average absolute prediction error within the preset historical period exceeds a preset error threshold. If the mean absolute prediction error exceeds a preset error threshold, an error correction function is constructed based on the error electricity price at the first moment, and the predicted electricity price in the electricity price prediction sequence is corrected for error based on the error correction function. Furthermore, the model parameters in the target prediction model are updated and optimized based on the error electricity price at the first moment.

7. A dynamic scheduling device for energy storage revenue, characterized in that, include: An energy storage parameter acquisition module is used to acquire the first energy storage parameters of an energy storage system for storing electrical energy at a first moment, wherein the first energy storage parameter information includes at least the energy storage charge, the charge and discharge efficiency, and the charge extreme value. A charge / discharge power determination module is used to determine the first charge / discharge power at the first moment based on a pre-built target solver, according to the first energy storage parameters and a pre-predicted first electricity price at the first moment. The target solver is a mixed integer linear programming solver, and the target solver includes an energy storage revenue function. The energy storage revenue function is constructed based on a transaction revenue function, a system loss function, and an energy storage penalty function within a preset prediction window. The energy storage penalty function is constructed based on the energy storage charge at the last moment of the preset prediction window. The energy storage dynamic scheduling module is used to dynamically schedule the energy storage load in the energy storage system based on the first charging and discharging power, so as to maximize the energy storage benefits of the energy storage system within the scheduling period at the first moment. Specifically, the charge / discharge power determination module is used for: The pre-built target solver determines the first charging and discharging power at the first time step based on the first energy storage parameters and the pre-predicted first electricity price at the first time step, including: The first predicted electricity price and the first energy storage parameters are input into the target solver to predict the power sequence, and the first charge and discharge power sequence is obtained based on the output of the target solver at each time point within the prediction window starting from the first time point. The first charge / discharge power in the first charge / discharge power sequence is determined as the first charge / discharge power corresponding to the first moment.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the energy storage revenue dynamic scheduling method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the dynamic scheduling method for energy storage revenue as described in any one of claims 1-6.

Images