Power distribution microgrid operation optimization method, device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a micro power distribution grid operation optimization method, device and equipment, a medium and a program product. Comprising the following steps: acquiring a distribution microgrid configuration parameter, a candidate distribution scheme set and a distribution microgrid objective function; wherein the distribution microgrid objective function comprises a daily total load fluctuation sub-objective function and an operation cost sub-objective function; initializing a power distribution microgrid operation optimization model according to the power distribution microgrid configuration parameters, the candidate power distribution scheme set and the power distribution microgrid objective function; and performing iterative solution on each candidate power distribution scheme in the candidate power distribution scheme set through the power distribution microgrid operation optimization model, and determining a target power distribution scheme. Reliable power supply of the distributed power distribution network-micro-grid is ensured, the overall system operation cost of the distributed power distribution network-micro-grid is reduced, the load fluctuation of the distributed power distribution network-micro-grid can be minimized, and full consumption of new energy is ensured.

Description

Technical Field

[0001] The present invention relates to the field of power network technology, and in particular to a method, device, equipment, medium and program product for optimizing the operation of a distribution microgrid. Background Art

[0002] With the construction of new power systems based on new energy, the distribution network is gradually transforming from a power network that simply receives and distributes electricity to users to a power network that integrates source, grid, load and storage and is flexibly coupled with microgrids. Its functions in promoting the local consumption of distributed power sources in microgrids and carrying new loads are becoming increasingly significant.

[0003] Distributed distribution networks, or microgrids, connect a variety of power resources within a specific area, including traditional loads, adjustable loads, renewable energy generation, and energy storage. They integrate and distribute these resources safely and quickly, making energy utilization more efficient and reliable. Because microgrids and distribution networks can only maximize the efficiency of a high proportion of distributed power sources when they operate in coordination, existing operational coordination technologies for renewable energy microgrids primarily focus on building multi-objective optimization models and designing optimization algorithms. However, multi-objective optimization methods are often complex, computationally intensive, and difficult to implement, making them unsuitable for determining distribution solutions in the implementation of distributed smart distribution networks. Summary of the Invention

[0004] The present invention provides a distribution and microgrid operation optimization method, device, equipment, medium and program product, which determines the power distribution plan for the distributed distribution network-microgrid system from the perspectives of economy and absorptivity, ensuring the reliable power supply of the distributed distribution network-microgrid while reducing the overall system operation cost of the distributed distribution network-microgrid, and minimizing the load fluctuation of the distributed distribution network-microgrid, thereby ensuring the full absorption of new energy.

[0005] In a first aspect, an embodiment of the present invention provides a method for optimizing the operation of a distribution microgrid, including:

[0006] Obtaining the configuration parameters of the distribution microgrid, a set of candidate distribution schemes, and the distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operating cost sub-objective function;

[0007] Initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function;

[0008] The distribution microgrid operation optimization model is used to iteratively solve each candidate distribution scheme in the candidate distribution scheme set to determine the target distribution scheme.

[0009] In a second aspect, an embodiment of the present invention further provides a distribution microgrid operation optimization device, comprising:

[0010] A parameter acquisition module is used to obtain the distribution microgrid configuration parameters, a set of candidate distribution schemes, and the distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operating cost sub-objective function;

[0011] A model initialization module is used to initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function;

[0012] The scheme determination module is used to iteratively solve each candidate distribution scheme in the candidate distribution scheme set through the distribution microgrid operation optimization model to determine the target distribution scheme.

[0013] In a third aspect, an embodiment of the present invention further provides a distribution microgrid operation optimization device, the distribution microgrid operation optimization device comprising:

[0014] at least one processor; and a memory communicatively coupled to the at least one processor;

[0015] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can implement the distribution microgrid operation optimization method of any embodiment of the present invention.

[0016] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer-executable instructions, which, when executed by a computer processor, are used to execute the distribution microgrid operation optimization method of any embodiment of the present invention.

[0017] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, is used to execute the distribution microgrid operation optimization method of any embodiment of the present invention.

[0018] The embodiments of the present invention provide a distribution microgrid operation optimization method, device, equipment, medium and program product, which obtains the distribution microgrid configuration parameters, a set of candidate distribution schemes and the distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operation cost sub-objective function; initializes the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the set of candidate distribution schemes and the distribution microgrid objective function; and iteratively solves each candidate distribution scheme in the set of candidate distribution schemes through the distribution microgrid operation optimization model to determine the target distribution scheme. By adopting the above technical solution, after obtaining the distribution microgrid configuration parameters, the set of candidate distribution schemes and the distribution microgrid objective function, the distribution microgrid operation optimization model is initialized, and then each candidate distribution scheme in the set of candidate distribution schemes is iteratively solved based on the initialized distribution microgrid operation optimization model to obtain the target distribution scheme that best suits the distribution microgrid operation requirements. Since the distribution microgrid objective function includes both the daily total load fluctuation sub-objective function and the operating cost sub-objective function, that is, when the distribution microgrid operation optimization model solves each candidate distribution scheme through the distribution microgrid objective function configured therein, the target distribution scheme finally solved can meet the determination requirements of the distribution scheme from the perspectives of both cost and load fluctuation, ensuring the reliable power supply of the distributed distribution network-microgrid while reducing the overall system operation cost of the distributed distribution network-microgrid, and minimizing the load fluctuation of the distributed distribution network-microgrid, ensuring the full absorption of new energy.

[0019] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is a flow chart of a distribution microgrid operation optimization method provided in Example 1 of the present invention;

[0022] Figure 2 This is a diagram illustrating an example of a distributed distribution network-microgrid system structure provided in the first embodiment of the present invention;

[0023] Figure 3 A flow chart of a distribution microgrid operation optimization method provided in the second embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the structure of a distribution microgrid operation optimization device provided in the third embodiment of the present invention;

[0025] Figure 5 This is a structural diagram of a distribution microgrid operation optimization device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] Figure 1 This is a flow chart of a distribution microgrid operation optimization method provided in the first embodiment of the present invention. This embodiment of the present invention is applicable to determining the distribution location of a distributed distribution network (microgrid) to optimize the operation of the distribution microgrid. The method can be executed by a distribution microgrid operation optimization device, which can be implemented by software and / or hardware and can be configured in a distribution microgrid operation optimization device. Optionally, the distribution microgrid operation optimization device can be an electronic device, such as a laptop, desktop computer, or smart tablet, which is not limited in this embodiment of the present invention.

[0030] In order to clearly describe this solution, a distributed distribution network-microgrid system structure is provided here, which can also be understood as the system structure of the distribution microgrid proposed in the embodiment of the present invention. Figure 2This is a diagram illustrating the system structure of a distributed distribution network-microgrid provided in the first embodiment of the present invention, in which solid lines represent energy flows and dashed lines with arrows represent information flows. The system may include rigid loads located on the main grid, which can be understood as traditional loads in the distribution network; adjustable loads located on the main grid; and multiple microgrids, each of which may include a new energy generation module, an energy storage module, and a microgrid adjustable load module. The distribution microgrid operation optimization method provided in the embodiment of the present invention is a method for determining a power distribution scheme for the power of the new energy adjustable load and the energy storage charging and discharging power within the microgrid of the distribution microgrid system, with the goal of optimizing the total load fluctuation of the distribution microgrid and the total system operation cost.

[0031] like Figure 1 As shown, an embodiment of the present invention provides a method for optimizing the operation of a distribution microgrid, which specifically includes the following steps:

[0032] S101. Obtain distribution microgrid configuration parameters, a set of candidate distribution schemes, and a distribution microgrid objective function.

[0033] Among them, the distribution microgrid objective function includes the daily total load fluctuation sub-objective function and the operation cost sub-objective function.

[0034] In this embodiment, the configuration parameters of the distribution microgrid can be specifically understood as follows: Figure 2 The distributed distribution network - microgrid shows the inherent characteristic parameters of each component and the set of configuration-related parameters generated during the operation of the power network. The candidate distribution scheme can be specifically understood as a combination of the power of the grid and the adjustable load power of the new energy and the energy storage charging and discharging power in the microgrid system, which can also be understood as an alternative that can be applied to Figure 2 The scheme for parameter configuration of each component in the system shown. In some examples, the candidate power distribution scheme may include the power of the adjustable load module in the microgrid, and the charging power and discharging power of the energy storage module in the microgrid, etc., which is not limited by the embodiment of the present invention. The distribution microgrid objective function can be specifically understood as a function set according to the actual working requirements of the distributed distribution network-microgrid system, and it is expected that the working status of each component in the system when working meets the target requirements. The daily total load fluctuation sub-objective function can be specifically understood as a function with the minimization of the daily load fluctuation of each component in the system when working as the optimization goal. The operating cost sub-objective function can be specifically understood as a function with the lowest overall operating cost of each component in the system when working as the optimization goal.

[0035] Specifically, when optimizing the operation of a distribution microgrid, the inherent characteristic parameters of each component of the distribution microgrid for which the distribution scheme is to be configured, as well as the pre-configured parameters generated during the operation of the power network, are first obtained to obtain the distribution microgrid positioning configuration parameters that can clearly define the normal operation requirements of each component of the distribution microgrid. At the same time, a set of candidate distribution schemes consisting of multiple candidate distribution schemes pre-given according to actual conditions can be obtained, and a distribution microgrid objective function is pre-constructed based on actual needs, with the optimization goals of minimizing system operating costs and minimizing load fluctuations.

[0036] S102: Initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set, and the distribution microgrid objective function.

[0037] In this embodiment, the distribution microgrid operation optimization model can be specifically understood as a reinforcement learning algorithm model built based on the Deep-Q-Network (DQN) algorithm for solving complex decision-making problems.

[0038] Specifically, the distribution microgrid configuration parameters are substituted into the distribution microgrid objective function to complete the initialization of the distribution microgrid objective function. Then, based on the distribution microgrid configuration parameters, the set of candidate distribution schemes and the initialized distribution microgrid objective function, the environmental state space, action space and reward function of the distribution microgrid operation optimization model are initialized respectively to obtain the initialized distribution microgrid operation optimization model.

[0039] S103. Iteratively solve each candidate power distribution scheme in the candidate power distribution scheme set through the distribution microgrid operation optimization model to determine the target power distribution scheme.

[0040] Specifically, based on the solution method of the DQN algorithm, the candidate power distribution scheme to be solved is selected from its action space at a preset exploration rate, and then substituted into the environment state space for solution according to the reward function, and the solution for each candidate power distribution scheme in the candidate power distribution scheme set is iterated in sequence. When the iterative exit condition is met, the candidate power distribution scheme that best meets the target demand is selected from each candidate power distribution scheme according to the reward function value obtained by solving each candidate power distribution scheme, and it is determined as the target power distribution scheme.

[0041] The technical solution of this embodiment obtains the distribution microgrid configuration parameters, the set of candidate distribution schemes, and the distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operating cost sub-objective function; initializes the distribution microgrid operation optimization model based on the distribution microgrid configuration parameters, the set of candidate distribution schemes, and the distribution microgrid objective function; and iteratively solves each candidate distribution scheme in the set of candidate distribution schemes through the distribution microgrid operation optimization model to determine the target distribution scheme. By adopting the above technical solution, after obtaining the distribution microgrid configuration parameters, the set of candidate distribution schemes, and the distribution microgrid objective function, the distribution microgrid operation optimization model is initialized, and then, based on the initialized distribution microgrid operation optimization model, each candidate distribution scheme in the set of candidate distribution schemes is iteratively solved to obtain the target distribution scheme that best suits the distribution microgrid operation requirements. Since the distribution microgrid objective function includes both the daily total load fluctuation sub-objective function and the operating cost sub-objective function, that is, when the distribution microgrid operation optimization model solves each candidate distribution scheme through the distribution microgrid objective function configured therein, the target distribution scheme finally solved can meet the determination requirements of the distribution scheme from the perspectives of both cost and load fluctuation, ensuring the reliable power supply of the distributed distribution network-microgrid while reducing the overall system operation cost of the distributed distribution network-microgrid, and minimizing the load fluctuation of the distributed distribution network-microgrid, ensuring the full absorption of new energy.

[0042] Example 2

[0043] Figure 3A flow chart of a distribution microgrid operation optimization method provided in the second embodiment of the present invention is further optimized on the basis of the above-mentioned optional technical solutions. By first obtaining time-of-use electricity price data, as well as rigid load parameter information, main grid adjustable load parameter information and microgrid parameter information in the distribution microgrid, load forecast of the main grid rigid load and adjustable load within the time period required to determine the distribution plan of the distribution network, as well as new energy power generation forecast and rigid load forecast of the microgrid, all the obtained information and calculated prediction data are used as the distribution microgrid configuration parameters. At the same time, constraint conditions are constructed to ensure that each candidate distribution scheme in the candidate distribution scheme set meets the constraint conditions before being solved by the distribution microgrid operation optimization model, thereby avoiding invalid calculations of the distribution microgrid operation optimization model. Then, according to the distribution microgrid configuration parameters, the set of candidate distribution schemes that meet the constraints and the distribution microgrid objective function, the distribution microgrid operation optimization model is initialized. The distribution microgrid objective function that includes both the daily total load fluctuation sub-objective function and the operation cost sub-objective function is adopted. The applicability of the reward value relied on in the iterative solution process of the distribution microgrid operation optimization model to the distributed distribution network-microgrid system is improved, and the ability to select solutions to complex problems required by the dynamically changing distributed distribution network-microgrid system is enhanced. The distribution scheme determination requirements are met from the two perspectives of minimizing system operating costs and minimizing net load fluctuations. While ensuring the reliable power supply of the distributed distribution network-microgrid, the overall system operation cost of the distributed distribution network-microgrid is reduced, and the load fluctuation of the distributed distribution network-microgrid can be minimized, ensuring the full absorption of new energy.

[0044] like Figure 3 As shown, an embodiment of the present invention provides a method for optimizing the operation of a distribution microgrid, which specifically includes the following steps:

[0045] S201. Obtain time-of-use electricity price data, as well as rigid load parameter information in the distribution microgrid, main grid adjustable load parameter information, and microgrid parameter information.

[0046] In this embodiment, the time-of-use electricity price data can be specifically understood as dividing the 24 hours of a day into several time periods according to the load characteristics of the power system in different time periods, and formulating different electricity price data for different time periods. Figure 2 The distributed distribution network-microgrid system shown in FIG. Rigid load parameter information can be specifically understood as parameter information used to determine the power consumption of the main grid rigid load in the distributed distribution network-microgrid system during the time period for which a power distribution plan needs to be determined. For example, the rigid load parameter information may include the power consumption of the rigid load at each time point during the time period for which a power distribution plan needs to be determined.

[0047] In this embodiment, the main grid adjustable load parameter information can be specifically understood as parameter information used to determine the power consumption of the main grid adjustable load in the distributed distribution network-microgrid system during the time period for which the power distribution plan needs to be determined. For example, the main grid adjustable load parameters may include the power consumption and power consumption change of the main grid adjustable load at each time point during the time period for which the power distribution plan needs to be determined.

[0048] In this embodiment, microgrid parameter information can be specifically understood as information used to determine the construction and production costs of each microgrid in the distributed distribution network-microgrid system, inherent equipment parameters and usage, and parameter information related to power generation and load over a period of historical time. For example, the microgrid parameter information may include historical new energy output data, historical load data, new energy capacity values, energy storage capacity values, new energy power generation rated power, energy storage rated power, new energy equipment age, energy storage equipment age, depreciation rate, new energy operating cost coefficient, energy storage operating cost coefficient, microgrid adjustable load adjustment cost coefficient, etc., and this embodiment of the present invention is not limited to this.

[0049] S202: Perform new energy power generation forecast and load forecast based on rigid load parameter information, main grid adjustable load parameter information, and microgrid parameter information to determine new energy power generation forecast value and load forecast value.

[0050] Among them, the load forecast value includes the main grid rigid load forecast value, the main grid adjustable load forecast value and the microgrid rigid load forecast value.

[0051] Specifically, the rigid load parameter information, the main grid adjustable load parameter information, and the microgrid parameter information are substituted into the pre-trained power generation forecast model and load forecast model to obtain the new energy power generation forecast value of each new energy power generation module in the microgrid during the time period when the power distribution plan needs to be determined, as well as the power consumption of each load in the distribution network during the time period when the power distribution plan needs to be determined, i.e., the load forecast value. This load forecast value may include the main grid rigid load forecast value for rigid loads in the main grid, the main grid adjustable load forecast value for adjustable loads in the main grid, and the microgrid rigid load forecast value for rigid loads in the microgrid.

[0052] S203: Determine the time-of-use electricity price data, microgrid parameter information, new energy power generation forecast value, and load forecast value as distribution microgrid configuration parameters, and execute S205.

[0053] S204: Obtain a set of candidate power distribution schemes and a distribution microgrid objective function, and execute S205.

[0054] Among them, the distribution microgrid objective function includes the daily total load fluctuation sub-objective function and the operation cost sub-objective function.

[0055] Among them, each candidate power distribution scheme satisfies the constraints determined based on the configuration parameters of the distribution microgrid;

[0056] Among them, the constraints include at least: power balance constraints, new energy output constraints and energy storage equipment constraints.

[0057] Among them, the distribution microgrid objective function is:

[0058]

[0059] in, is the daily total load fluctuation sub-objective function; is the operating cost sub-objective function; P SLoad (t) is the predicted value of the main grid rigid load during period t; P VLoad (t) is the forecast value of the main grid adjustable load during period t; P MGrid,n (t) is the net load power of microgrid n in period t; C Load is the main network load operating cost; is C MGrid (n) is the operating cost of microgrid n; T is the time to be optimized; N is the number of microgrids in the distribution microgrid.

[0060] In this embodiment, the net load power can be specifically understood as the load demand that needs to be met by traditional energy generation equipment in the microgrid in addition to the power that can be generated by the microgrid, that is, the power that needs to be purchased from the main grid.

[0061] Among them, P MGrid,n (t) is determined by

[0062] P MGrid,n (t) = P SLoad,n (t)+P VLoad,n (t)+P Store,n (t)-P RES,n (t)

[0063] Among them, P SLoad,n (t) is the predicted value of the microgrid rigid load of microgrid n; P VLoad,n (t) is the adjustable load power of microgrid n; P Store,n (t) is the charging and discharging power of the energy storage device in microgrid n; P RES,n (t) is the predicted value of renewable energy power generation of microgrid n.

[0064] In this embodiment, P VLoad,n (t) and P Store,n (t) is the changing value to be evaluated, which can also be understood as the value given in the candidate power distribution scheme.

[0065] Among them, C MGrid (n) is determined by

[0066] C MGrid (n) = C RES (n)+C VLoad (n)+C Store (n)+C Buy (n)

[0067] Among them, C RES (n) is the cost of renewable energy generation in microgrid n; C VLoad (n) is the regulation cost of the adjustable load of microgrid n; C Store (n) is the charging and discharging cost of the energy storage equipment in microgrid n; C Buy (n) is the cost of electricity purchased from microgrid n to the main distribution grid.

[0068] In this embodiment, the renewable energy power generation cost of the microgrid n can be specifically understood as the cost incurred when the power generation of the microgrid n reaches the predicted renewable energy power generation value during the time period when the power distribution plan needs to be determined.

[0069] In this embodiment, the adjustment cost of the adjustable load of microgrid n can be specifically understood as the cost incurred by the adjustable load module of microgrid n due to electricity consumption during the time period when the power distribution plan needs to be determined, that is, the cost incurred due to the adjustable load power of microgrid n.

[0070] In this embodiment, the charging and discharging cost of the energy storage device of microgrid n can be specifically understood as the cost incurred by the operation of the energy storage module of microgrid n due to charging or discharging during the time period when the power distribution plan needs to be determined.

[0071] in,

[0072] Among them, Y is the life of new energy and energy storage equipment; r is the depreciation rate; σ RES is the new energy operation cost coefficient; σ Store is the energy storage operation cost coefficient; ρ is the microgrid adjustable load adjustment cost coefficient; S t is the time-of-use electricity price during period t.

[0073] Among them, C Load The method of determining

[0074] C Load =S t ·(P SLoad +ρP VLoad )

[0075] In some examples, the power balance constraint may be expressed as:

[0076]

[0077] Among them, PBuy,n (t) is the power purchased by microgrid n from the distribution network during period t, which is generally the net load power P mentioned above. MGrid,n (t); is the renewable energy power abandoned by microgrid n during period t.

[0078] In some examples, the renewable energy output constraint can be expressed as:

[0079] 0≤P RES,n (t)+P Drop,n (t)≤P E

[0080] Among them, P E is the rated power of the new energy power generation module in the microgrid.

[0081] In some examples, the energy storage device constraint can be expressed as:

[0082] 0≤|P Store (t)|≤P S

[0083] Among them, P S is the charging / discharging rated power of the energy storage module in the microgrid.

[0084] S205. Initialize the environmental state space of the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters.

[0085] Specifically, the distribution microgrid operation optimization model built based on the DQN algorithm must first set the triple {S, A, R} before solving it, where S is the environment state space, A is the action space, and R is the reward function. Before it is put into use, the triples will first be initialized based on the distribution microgrid configuration parameters, the set of candidate distribution schemes, and the distribution microgrid objective function. The initialization of the environment state space can be achieved by jointly initializing the renewable energy generation power, the main grid rigid load power, and the time-of-use electricity price for the previous 24 hours. That is, the initialized environment state space S can be expressed by the following formula:

[0086] S=[P RES (0),…,P RES (23),P SLoad (0),…,P SLoad (23),S(0),…,S(23)]

[0087] S206. Initialize the action space of the distribution microgrid operation optimization model according to the candidate distribution scheme set.

[0088] Specifically, the action space can be initialized based on each candidate power distribution scheme that meets the constraint conditions in the candidate power distribution scheme set, that is, each candidate power distribution scheme that meets the constraint conditions is initialized as an action in the action space and enters the action space.

[0089] For example, assuming that an action in the action space A is a, it can be expressed by the following formula:

[0090] a=[P VLoad，n (0),…,P VLoad，n (23),…,P VLoad，1 (0),…,P VLoad，1 (twenty three),

[0091] P Store，n (0),…,P Store，n (23),…,P Store，1 (0),…,P Store，1 (twenty three)]

[0092] Among them, a can be understood as a candidate power distribution scheme in the set of candidate power distribution schemes that meets the constraints.

[0093] S207 : Initialize the reward function of the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters and the distribution microgrid objective function.

[0094] Specifically, the distribution microgrid configuration parameters are substituted into the distribution microgrid objective function to complete the initialization of the distribution microgrid objective function, and then the initialized distribution microgrid objective function is substituted into the reward function of the distribution microgrid operation optimization model to complete the initialization of the reward function.

[0095] For example, the reward function can be expressed as follows:

[0096] R(k)=F1(k)+F2(k)

[0097] Among them, k is the number of iterative solutions, and the reward function can also be understood as the sum of the two sub-objective functions in the distribution microgrid objective function.

[0098] S208 : Select a candidate power distribution scheme from the action space of the distribution microgrid operation optimization model at a preset exploration rate.

[0099] Specifically, in the process of iteratively solving each candidate distribution scheme in the candidate distribution scheme set through the initialized distribution microgrid operation optimization model, the candidate distribution schemes can be selected in turn from the action space of the distribution microgrid operation optimization model at a preset exploration rate, and each candidate distribution scheme will be subsequently solved until all actions in the action space are selected.

[0100] S209. Input the candidate power distribution scheme into the environmental state space of the distribution microgrid operation optimization model, update the environmental state value of the environmental state space, and substitute the updated environmental state value and the candidate power distribution scheme into the reward function of the distribution microgrid operation optimization model to determine the mathematical expectation reward of the candidate power distribution scheme.

[0101] Specifically, the candidate power distribution plan is input into the environmental state space of the distribution microgrid operation optimization model. The environmental state value in the environmental state space is updated to adapt to the scenario corresponding to the candidate power distribution plan, obtaining an updated environmental state value. The updated environmental state value and the subsequent power distribution plan are then substituted into the reward function of the distribution microgrid operation optimization model to obtain the mathematical expectation reward value of the candidate power distribution plan determined based on the reward function.

[0102] For example, the mathematical expected reward can be determined by a predefined state-action-value function, which can be expressed as:

[0103] Q π =E[R(k)|S k =S,a k =a]

[0104] Among them, S k is the kth iteration execution, that is, the environment state value when the kth action is selected; a k The action selected when performing the action for the kth time.

[0105] Furthermore, in the iterative solution process of the distribution microgrid operation optimization model, the Q value of each iteration will be updated according to the above formula, and the update method is as follows:

[0106]

[0107] Among them, α is the learning rate and β is the discount rate.

[0108] S210 , evaluating the mathematical expected reward of each candidate power distribution scheme through a value function, and determining the candidate power distribution scheme with the best evaluation result as the target power distribution scheme.

[0109] Specifically, the mathematical expectation reward value corresponding to each candidate power distribution scheme is substituted into the value evaluation function, and the candidate power distribution scheme corresponding to the mathematical expectation reward value with the best evaluation result is determined as the target power distribution scheme.

[0110] For example, the value evaluation function can be expressed as

[0111]

[0112] Optionally, the distribution microgrid operation optimization model needs to be trained before it is put into use. The training process can be implemented through the following steps:

[0113] Initialization: Initialize learning rate α, discount rate β, sampling sample size W, training cycle T k , experience pool size D.

[0114] Step 1: Enter the current system status S (k) .

[0115] Step 2: Randomly select action a (k) .

[0116] Step 3: Calculate the reward R(k+1) and calculate the next system state S (k+1) .

[0117] Step 4: Replace the escape sequence Δd with {S (k) ,a (k) ,R (k+1) ,S (k+1)}Deposited into experience pool D.

[0118] Step 5: Take W transition sequences from the experience pool.

[0119] Step 6: Obtain the target value based on the above mathematical expected reward formula.

[0120] Step 7: Update the parameters of the current Q network every T k Update the parameters of the delayed Q network to the parameters of the current Q network.

[0121] Step 8: If the training cycle is reached, this round of training ends.

[0122] The technical solution of this embodiment first obtains time-of-use electricity price data, as well as rigid load parameter information, main grid adjustable load parameter information and microgrid parameter information in the distribution microgrid, to complete the load forecast of the main grid rigid load and adjustable load within the time period required to determine the distribution plan, as well as the new energy power generation forecast and rigid load forecast of the microgrid. Then, all the acquired information and calculated prediction data are used as the configuration parameters of the distribution microgrid. At the same time, constraint conditions are constructed to ensure that each candidate distribution scheme in the candidate distribution scheme set meets the constraint conditions before being solved by the distribution microgrid operation optimization model, so as to avoid invalid calculations of the distribution microgrid operation optimization model. Then, according to the distribution microgrid configuration parameters, the set of candidate distribution schemes that meet the constraints and the distribution microgrid objective function, the distribution microgrid operation optimization model is initialized. The distribution microgrid objective function that includes both the daily total load fluctuation sub-objective function and the operation cost sub-objective function is adopted. The applicability of the reward value relied on in the iterative solution process of the distribution microgrid operation optimization model to the distributed distribution network-microgrid system is improved, and the ability to select solutions to complex problems required by the dynamically changing distributed distribution network-microgrid system is enhanced. The distribution scheme determination requirements are met from the two perspectives of minimizing system operating costs and minimizing net load fluctuations. While ensuring the reliable power supply of the distributed distribution network-microgrid, the overall system operation cost of the distributed distribution network-microgrid is reduced, and the load fluctuation of the distributed distribution network-microgrid can be minimized, ensuring the full absorption of new energy.

[0123] Example 3

[0124] Figure 4 This is a structural diagram of a distribution microgrid operation optimization device provided by the third embodiment of the present invention, as shown in FIG. Figure 4 As shown, the distribution microgrid operation optimization device includes a parameter acquisition module 31, a model initialization module 32 and a solution determination module 33.

[0125] Among them, the parameter acquisition module 31 is used to obtain the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function; wherein the distribution microgrid objective function includes the daily total load fluctuation sub-objective function and the operation cost sub-objective function; the model initialization module 32 is used to initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function; the scheme determination module 33 is used to iteratively solve each candidate distribution scheme in the candidate distribution scheme set through the distribution microgrid operation optimization model to determine the target distribution scheme.

[0126] The technical solution of the embodiment of the present invention is to initialize the distribution microgrid operation optimization model after obtaining the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function, and then iteratively solve each candidate distribution scheme in the candidate distribution scheme set based on the initialized distribution microgrid operation optimization model to obtain the target distribution scheme that best suits the distribution microgrid operation requirements. Because the distribution microgrid objective function includes both the daily total load fluctuation sub-objective function and the operation cost sub-objective function, that is, when the distribution microgrid operation optimization model solves each candidate distribution scheme through the distribution microgrid objective function configured therein, the target distribution scheme finally solved can meet the determination requirements of the distribution scheme from both the cost and load fluctuation perspectives, ensuring the reliable power supply of the distributed distribution network-microgrid while reducing the overall system operation cost of the distributed distribution network-microgrid, and minimizing the load fluctuation of the distributed distribution network-microgrid, ensuring the full absorption of new energy.

[0127] Optionally, the parameter acquisition module 31 is specifically configured to:

[0128] Obtain time-of-use electricity price data, as well as rigid load parameter information in the distribution microgrid, main grid adjustable load parameter information and microgrid parameter information;

[0129] Performing new energy power generation forecasting and load forecasting based on rigid load parameter information, main grid adjustable load parameter information, and microgrid parameter information to determine new energy power generation forecast values ​​and load forecast values; wherein the load forecast value includes the main grid rigid load forecast value, the main grid adjustable load forecast value, and the microgrid rigid load forecast value;

[0130] The time-of-use electricity price data, microgrid parameter information, new energy power generation forecast value and load forecast value are determined as the distribution microgrid configuration parameters.

[0131] Optionally, the model initialization module 32 is specifically configured to:

[0132] Initialize the environmental state space of the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters;

[0133] Initialize the action space of the distribution microgrid operation optimization model based on the set of candidate distribution schemes;

[0134] The reward function of the distribution microgrid operation optimization model is initialized according to the distribution microgrid configuration parameters and the distribution microgrid objective function.

[0135] Optionally, the solution determination module 33 is specifically configured to:

[0136] Select candidate distribution schemes from the action space of the distribution microgrid operation optimization model at a preset exploration rate;

[0137] Input the candidate power distribution scheme into the environmental state space of the distribution microgrid operation optimization model, update the environmental state value of the environmental state space, and substitute the updated environmental state value and the candidate power distribution scheme into the reward function of the distribution microgrid operation optimization model to determine the mathematical expectation reward of the candidate power distribution scheme;

[0138] The mathematical expected reward of each candidate power distribution scheme is evaluated through the value function, and the candidate power distribution scheme with the best evaluation result is determined as the target power distribution scheme.

[0139] Optionally, the distribution microgrid objective function is

[0140]

[0141] in, is the daily total load fluctuation sub-objective function; is the operating cost sub-objective function; P SLoad (t) is the predicted value of the main grid rigid load during period t; P VLoad (t) is the forecast value of the main grid adjustable load during period t; P MGrid,n (t) is the net load power of microgrid n in period t; C Load is the main network load operating cost; is C MGrid (n) is the operating cost of microgrid n; T is the time to be optimized; N is the number of microgrids in the distribution microgrid.

[0142] Optional, P MGrid,n (t) is determined by

[0143] P MGrid,n (t) = P SLoad,n (t)+P VLoad,n (t)+P Store,n (t)-P RES,n (t)

[0144] Among them, P SLoad,n (t) is the predicted value of the microgrid rigid load of microgrid n; P VLoad,n (t) is the adjustable load power of microgrid n; P Store,n (t) is the charging and discharging power of the energy storage device in microgrid n; P RES,n (t) is the predicted value of renewable energy power generation of microgrid n.

[0145] Optional, C MGrid (n) is determined by

[0146] C MGrid (n) = C RES (n)+C VLoad (n)+C Store (n)+C Buy (n)

[0147] Among them, C RES (n) is the cost of renewable energy generation in microgrid n; C VLoad (n) is the regulation cost of the adjustable load of microgrid n; C Store (n) is the charging and discharging cost of the energy storage equipment in microgrid n; C Buy (n) is the cost of electricity purchased from microgrid n to the main distribution grid;

[0148] in,

[0149] Among them, Y is the life of new energy and energy storage equipment; r is the depreciation rate; σ RES is the new energy operation cost coefficient; σ Store is the energy storage operation cost coefficient; ρ is the microgrid adjustable load adjustment cost coefficient; S t is the time-of-use electricity price during period t.

[0150] Optionally, each candidate power distribution scheme satisfies constraints determined based on the configuration parameters of the distribution microgrid;

[0151] Among them, the constraints include at least: power balance constraints, new energy output constraints and energy storage equipment constraints.

[0152] The distribution microgrid operation optimization device provided in an embodiment of the present invention can execute the distribution microgrid operation optimization method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0153] Example 4

[0154] Figure 5 A schematic structural diagram of a distribution microgrid operation optimization device provided in Embodiment 4 of the present invention. The distribution microgrid operation optimization device 40 may be 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 distribution microgrid operation optimization device 40 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0155] like Figure 5As shown, the distribution microgrid operation optimization device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 and a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores a computer program executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the read-only memory (ROM) 42 or loaded from the storage unit 48 into the random access memory (RAM) 43. The RAM 43 can also store various programs and data required for the operation of the distribution microgrid operation optimization device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0156] Multiple components in the distribution microgrid operation optimization device 40 are connected to the I / O interface 45, including: an input unit 46, such as a keyboard, a mouse, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a magnetic disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the distribution microgrid operation optimization device 40 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0157] Processor 41 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 41 executes the various methods and processes described above, such as the distribution microgrid operation optimization method.

[0158] In some embodiments, the distribution microgrid operation optimization method can be implemented as a computer program that is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the distribution microgrid operation optimization device 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the distribution microgrid operation optimization method described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the distribution microgrid operation optimization method by any other suitable means (e.g., by means of firmware).

[0159] Optionally, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the distribution microgrid operation optimization method provided by any embodiment of the present invention.

[0160] Various embodiments of the systems and techniques described 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-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] Computer programs for implementing 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 the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0162] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0163] To provide user interaction, the systems and techniques described herein can be implemented on a distribution microgrid operation optimization 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 can provide input to the distribution microgrid operation optimization device. Other types of devices can also be used to provide user interaction; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0165] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0166] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0167] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for optimizing the operation of a distribution microgrid, characterized in that: include: Obtaining distribution microgrid configuration parameters, a set of candidate distribution schemes, and a distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operating cost sub-objective function; Initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function; The distribution microgrid operation optimization model is used to iteratively solve each candidate distribution scheme in the candidate distribution scheme set to determine the target distribution scheme.

2. The method for optimizing the operation of a distribution microgrid according to claim 1, wherein: The obtaining of the distribution microgrid configuration parameters includes: Obtain time-of-use electricity price data, as well as rigid load parameter information in the distribution microgrid, main grid adjustable load parameter information and microgrid parameter information; Performing new energy power generation forecasting and load forecasting based on the rigid load parameter information, the main grid adjustable load parameter information, and the microgrid parameter information to determine a new energy power generation forecast value and a load forecast value; wherein the load forecast value includes a main grid rigid load forecast value, a main grid adjustable load forecast value, and a microgrid rigid load forecast value; The time-of-use electricity price data, the microgrid parameter information, the new energy power generation forecast value and the load forecast value are determined as distribution microgrid configuration parameters.

3. The method for optimizing the operation of a distribution microgrid according to claim 1, wherein: Initializing the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set, and the distribution microgrid objective function includes: Initialize the environmental state space of the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters; Initializing the action space of the distribution microgrid operation optimization model according to the set of candidate distribution schemes; The reward function of the distribution microgrid operation optimization model is initialized according to the distribution microgrid configuration parameters and the distribution microgrid objective function.

4. The method for optimizing the operation of a distribution microgrid according to claim 3, wherein: The iteratively solving each candidate power distribution scheme in the candidate power distribution scheme set by using the distribution microgrid operation optimization model to determine the target power distribution scheme includes: selecting a candidate power distribution scheme from the action space of the distribution microgrid operation optimization model at a preset exploration rate; Inputting the candidate power distribution scheme into the environmental state space of the distribution microgrid operation optimization model, updating the environmental state value of the environmental state space, and substituting the updated environmental state value and the candidate power distribution scheme into the reward function of the distribution microgrid operation optimization model to determine the mathematical expectation reward of the candidate power distribution scheme; The mathematical expected reward of each candidate power distribution scheme is evaluated through a value function, and the candidate power distribution scheme with the best evaluation result is determined as the target power distribution scheme.

5. The method for optimizing the operation of a distribution microgrid according to claim 2, wherein: The distribution microgrid objective function is: Among them, the is the daily total load fluctuation sub-objective function; is the operating cost sub-objective function; the P SLoad (t) is the main grid rigid load forecast value for period t; VLoad (t) is the forecast value of the main grid adjustable load during period t; MGrid,n (t) is the net load power of microgrid n in period t; Load is the main network load operating cost; MGrid (n) The operating cost of microgrid n; T is the time to be optimized; N is the number of microgrids in the distribution microgrid.

6. The method for optimizing the operation of a distribution microgrid according to claim 5, characterized in that: The P MGrid,n (t) is determined by P MGrid,n (t)=P SLoad,n (t)+P VLoad,n (t)+P Store,n (t)-P RES,n (t) Among them, the P SLoad,n (t) is the microgrid rigid load prediction value of microgrid n; VLoad,n (t) is the adjustable load power of microgrid n; Store,n (t) is the charging and discharging power of the energy storage device of microgrid n; RES,n (t) is the predicted value of renewable energy power generation of microgrid n.

7. The method for optimizing the operation of a distribution microgrid according to claim 5, wherein: The C MGrid (n) is determined by C MGrid (n)=C RES (n)+C VLoad (n)+C Store (n)+C Buy (n) Among them, the C RES (n) is the cost of renewable energy generation in microgrid n; VLoad (n) is the adjustment cost of the adjustable load of microgrid n; Store (n) is the charging and discharging cost of the energy storage equipment in microgrid n; Buy (n) is the cost of electricity purchased from microgrid n to the main distribution grid; in, Wherein, Y is the age of new energy and energy storage equipment; r is the depreciation rate; σ RES is the new energy operation cost coefficient; the σ Store is the energy storage operation cost coefficient; ρ is the microgrid adjustable load adjustment cost coefficient; S t is the time-of-use electricity price during period t.

8. The method for optimizing the operation of a distribution microgrid according to any one of claims 1 to 7, characterized in that: Each of the candidate power distribution schemes satisfies the constraints determined according to the configuration parameters of the distribution microgrid; The constraints include at least: power balance constraints, new energy output constraints and energy storage equipment constraints.

9. A distribution microgrid operation optimization device, characterized in that: include: A parameter acquisition module is used to obtain the configuration parameters of the distribution microgrid, a set of candidate distribution schemes, and the distribution microgrid objective function; wherein the distribution microgrid objective function includes a daily total load fluctuation sub-objective function and an operating cost sub-objective function; A model initialization module is used to initialize the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters, the candidate distribution scheme set and the distribution microgrid objective function; The scheme determination module is used to iteratively solve each candidate power distribution scheme in the candidate power distribution scheme set through the distribution microgrid operation optimization model to determine the target power distribution scheme.

10. The microgrid operation optimization device according to claim 9, characterized in that: The parameter acquisition module is specifically used to: Obtain time-of-use electricity price data, as well as rigid load parameter information in the distribution microgrid, main grid adjustable load parameter information and microgrid parameter information; Performing new energy power generation forecasting and load forecasting based on the rigid load parameter information, the main grid adjustable load parameter information, and the microgrid parameter information to determine a new energy power generation forecast value and a load forecast value; wherein the load forecast value includes a main grid rigid load forecast value, a main grid adjustable load forecast value, and a microgrid rigid load forecast value; The time-of-use electricity price data, the microgrid parameter information, the new energy power generation forecast value and the load forecast value are determined as distribution microgrid configuration parameters.

11. The microgrid operation optimization device according to claim 9, characterized in that: The model initialization module is specifically used to: Initialize the environmental state space of the distribution microgrid operation optimization model according to the distribution microgrid configuration parameters; Initializing the action space of the distribution microgrid operation optimization model according to the set of candidate distribution schemes; The reward function of the distribution microgrid operation optimization model is initialized according to the distribution microgrid configuration parameters and the distribution microgrid objective function.

12. The microgrid operation optimization device according to claim 11, characterized in that: The solution determination module is specifically used to: selecting a candidate power distribution scheme from the action space of the distribution microgrid operation optimization model at a preset exploration rate; Inputting the candidate power distribution scheme into the environmental state space of the distribution microgrid operation optimization model, updating the environmental state value of the environmental state space, and substituting the updated environmental state value and the candidate power distribution scheme into the reward function of the distribution microgrid operation optimization model to determine the mathematical expectation reward of the candidate power distribution scheme; The mathematical expected reward of each candidate power distribution scheme is evaluated through a value function, and the candidate power distribution scheme with the best evaluation result is determined as the target power distribution scheme.

13. The microgrid operation optimization device according to claim 10, characterized in that: The distribution microgrid objective function is: Among them, the is the daily total load fluctuation sub-objective function; is the operating cost sub-objective function; the P SLoad (t) is the main grid rigid load forecast value for period t; VLoad (t) is the forecast value of the main grid adjustable load during period t; MGrid,n (t) is the net load power of microgrid n in period t; Load is the main network load operating cost; MGrid (n) The operating cost of microgrid n; T is the time to be optimized; N is the number of microgrids in the distribution microgrid.

14. The distribution microgrid operation optimization device according to claim 13, characterized in that: The P MGrid,n (t) is determined by P MGrid,n (t)=P SLoad,n (t)+P VLoad,n (t)+P Store,n (t)-P RES,n (t) Among them, the P SLoad,n (t) is the microgrid rigid load prediction value of microgrid n; VLoad,n (t) is the adjustable load power of microgrid n; Store,n (t) is the charging and discharging power of the energy storage device of microgrid n; RES,n (t) is the predicted value of renewable energy power generation of microgrid n.

15. The distribution microgrid operation optimization device according to claim 13, characterized in that: The C MGrid (n) is determined by C MGrid (n)=C RES (n)+C VLoad (n)+C Store (n)+C Buy (n) Among them, the C RES (n) is the cost of renewable energy generation in microgrid n; VLoad (n) is the adjustment cost of the adjustable load of microgrid n; Store (n) is the charging and discharging cost of the energy storage equipment in microgrid n; Buy (n) is the cost of electricity purchased from microgrid n to the main distribution grid; in, Wherein, Y is the age of new energy and energy storage equipment; r is the depreciation rate; σ RES is the new energy operation cost coefficient; the σ Store is the energy storage operation cost coefficient; ρ is the microgrid adjustable load adjustment cost coefficient; S t is the time-of-use electricity price during period t.

16. The distribution microgrid operation optimization device according to any one of claims 9 to 15, characterized in that: Each of the candidate power distribution schemes satisfies the constraints determined according to the configuration parameters of the distribution microgrid; The constraints include at least: power balance constraints, new energy output constraints and energy storage equipment constraints.

17. A distribution microgrid operation optimization device, characterized in that: include: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distribution microgrid operation optimization method according to any one of claims 1 to 8.

18. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to execute the distribution microgrid operation optimization method according to any one of claims 1 to 8.

19. A computer program product, characterized in that The method comprises a computer program which, when executed by a processor, implements the method for optimizing the operation of a distribution microgrid according to any one of claims 1 to 8.

Images