Distribution area flexibility resource scheduling method and system

Abstract

The invention discloses a transformer area flexibility resource scheduling method and system. The method comprises the following steps: collecting historical data of loads and renewable energy sources in a transformer area; establishing a unified energy storage model; establishing a scheduling strategy by using the established unified energy storage model in combination with historical data, and performing flexible resource scheduling simulation; optimizing the unified energy storage model through a genetic algorithm, and improving a scheduling strategy based on an evaluation result; and continuously monitoring the operation data of the load, the renewable energy source and the energy storage system in the transformer area, and adjusting the scheduling strategy according to the operation data. The system comprises a historical data collection module, a unified energy storage model construction module, a resource scheduling simulation module, a simulation result evaluation module, an optimization improvement module and a continuous monitoring module. According to the invention, coding and fitness evaluation are carried out on different resource types, so that the problem of non-uniform and unreasonable resource allocation is solved; reasonable allocation and utilization of resources are realized by setting a fitness function and a fitness threshold.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution network dispatching, and in particular relates to a method and system for dispatching flexible resources in a substation area. Background Art

[0002] In recent years, with the large-scale access of renewable energy and the continuous development of the electricity market, the scheduling and management of flexibility resources in substations have become increasingly important.

[0003] For flexible resource scheduling in substations, the existing technology adopts the following technical solutions:

[0004] Traditional calculation methods (such as greedy algorithms, rule-based scheduling, etc.) are usually limited by fixed rules, static models and simple optimization algorithms, and cannot meet the complex needs and dynamic changes of multi-source flexible resource scheduling in the substation area. Therefore, the unity and flexibility of the energy storage system are often ignored, and there are the following problems:

[0005] 1. Task scheduling optimization problem: poor coordination and optimization scheduling of multi-source flexible resources within the station area;

[0006] 2. Resource allocation problem: the allocation of multi-source flexibility resources in the substation area is uneven and unreasonable;

[0007] Scheduling efficiency issues, low resource scheduling efficiency and low task execution speed.

[0008] Therefore, there is an urgent need for a flexible resource scheduling method in the substation area to adapt to the complex needs and dynamic changes of multi-source flexible resource scheduling within the substation area and to improve resource scheduling efficiency and task execution speed. Summary of the invention

[0009] In order to solve the deficiencies of the prior art, the present invention provides a flexible resource scheduling method for a substation area that can solve the coordination and optimization scheduling problems of multi-source flexible resources in a substation area, realize the reasonable allocation and utilization of resources, and improve the scheduling efficiency and task execution speed. The present invention provides the following technical solutions:

[0010] A flexible resource scheduling method for a substation, the method comprising the following steps:

[0011] Step 1: Collect historical data of load and renewable energy in the substation, where the historical data includes power and time distribution information of load in the substation and energy obtained through renewable energy;

[0012] Step 2: Based on the historical data collected in step 1, a unified energy storage model is established in the substation area;

[0013] Step 3: Use the unified energy storage model established in step 2 and the historical data collected in step 1 to establish a scheduling strategy and perform a flexible resource scheduling simulation;

[0014] Step 4: Perform indicator evaluation based on the flexibility resource scheduling simulation, the indicators including energy utilization rate, load smoothness and renewable energy consumption rate;

[0015] Step 5: Optimize the unified energy storage model through genetic algorithm, and improve the dispatch strategy based on the evaluation results of step 4;

[0016] Step 6: Continuously monitor the operating data of loads, renewable energy and energy storage systems in the substation area, and adjust the dispatch strategy based on the operating data.

[0017] The present invention further includes the following preferred embodiments:

[0018] In step 2, the establishment of the unified energy storage model includes:

[0019] Step 2.1: Construct the state transfer function of the unified energy storage system;

[0020] Step 2.2: Define the reward function R(S(t), A(t), L(t)), which represents the reward obtained by the energy storage system after performing the action (A(t)) under the current energy storage capacity S(t) and the load L(t);

[0021] Step 2.3: Use the dynamic programming algorithm to iteratively calculate the optimal strategy for the energy storage system to perform different operations in different states to maximize the reward function.

[0022] In step 2.1, the construction formula of the state transfer function of the unified energy storage system is as follows:

[0023] S(t+1)=f(S(t),A(t),L(t))

[0024] Charging process: S(t+1)=min(S(t)+Pmax*Δt, Cmax)

[0025] Discharge process: S(t+1)=max(S(t)-Pmax*Δt,0)

[0026] No-load process: S(t+1)=S(t)

[0027] Where S(t) represents the energy storage capacity of the energy storage system at time t, S(t+1) represents the energy storage capacity of the energy storage system at time t+1; A(t) represents the operation of the energy storage system at time t: A(t)∈{charge,discharge,idle}; L(t) represents the load of the station; Pmax represents the upper limit of the power output of the energy storage system during charging and discharging, c max is the maximum capacity of the energy storage system, and Δt represents the time interval between two time points.

[0028] In step 2.2, the reward function is defined as follows:

[0029] R(S(t),A(t),L(t))=w1·E(S(t),A(t),L(t))+

[0030] w2·Smoothing(S(t),A(t),L(t))+w3·Renewable int (S(t),A(t),L(t))

[0031] Where E(S(t), A(t), L(t)) represents the energy utilization rate when performing the energy storage system operation A(t) under the current energy storage capacity S(t) and the station load L(t);

[0032] Smoothing(S(t),A(t),L(t)) represents the load smoothness when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t);

[0033] Renewable int (S(t), A(t), L(t)) represents the renewable energy consumption rate when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t), indicating how much renewable energy is used in the current dispatch;

[0034] w1, w2, and w3 represent the weight of each factor, which are used to adjust the importance of each factor in the reward function.

[0035] In step 2.3, maximizing the reward function includes: setting the initial energy storage state S(0); updating the reward function for performing various actions in each state, and selecting the best action that maximizes the overall reward; updating the energy storage state according to the state transition after the energy storage system performs various actions in the current state, and calculating the reward according to the defined reward function; evaluating the value of selecting different actions in each state, updating the strategy according to the reward function and state transition, and stopping the iteration until the algorithm converges, the strategy no longer changes, and the optimal strategy is reached.

[0036] In step 3, establishing a scheduling strategy includes: initializing the parameters of a unified energy storage model, calculating the charging power and discharging power of the energy storage system within a set time step according to the historical data of the load and renewable energy; setting the charging and discharging time of renewable energy according to the calculated charging power and discharging power of the energy storage system, charging during the peak period of renewable energy generation or the trough period of load, and discharging during the trough period of renewable energy generation or the peak period of load.

[0037] In step 5, optimizing the unified energy storage model by genetic algorithm includes:

[0038] Step 5.1: Encode the scheduling strategy parameters into the chromosome code of the genetic algorithm;

[0039] Step 5.2: Construct a fitness function to evaluate the performance of each chromosome;

[0040] Step 5.3: Set the fitness threshold, and based on the evaluation results of the fitness function, select chromosomes with high fitness as the parents of the next generation;

[0041] Step 5.4: Simulate the genetic crossover process, cross multiple parent chromosomes to generate new offspring chromosomes;

[0042] Step 5.5: Introduce the set mutation probability, perform mutation operations on the new generation chromosomes, and increase the diversity of the population;

[0043] Step 5.6: When the set number of iterations is reached or the fitness meets the set threshold, stop the iteration and output the optimal solution.

[0044] In step 5, based on the evaluation results of step 4, the scheduling strategy is improved, including: adjusting the charging and discharging time according to the energy utilization rate; adjusting the time for the load to store and release energy according to the load smoothness; and adjusting the allocation of energy storage capacity according to the renewable energy consumption rate.

[0045] In step 5.2, the fitness function is constructed as follows:

[0046]

[0047] Among them, T 总 represents the total completion time of all tasks; T 执 represents the total execution time of all tasks; U t Represents the total utilization of all resources; R e Represents the total number of available resources in the system; w1 and w2 represent the weights of completion time and resource utilization, respectively.

[0048] At the same time, the present invention provides a flexible resource scheduling system for a substation, including a historical data collection module, a unified energy storage model construction module, a resource scheduling simulation module, a simulation result evaluation module, an optimization and improvement module, and a continuous monitoring module;

[0049] The historical data collection module is used to collect historical data of loads and renewable energy in the substation area, wherein the historical data includes power and time distribution information of loads in the substation area and energy obtained through renewable energy;

[0050] The unified energy storage model building module builds a unified energy storage model in the substation based on the historical data collected by the historical data collection module;

[0051] The resource scheduling simulation module establishes a scheduling strategy based on the established unified energy storage model and the collected historical data, performs flexibility resource scheduling simulation and optimizes the model;

[0052] The simulation result evaluation module is used to evaluate the scheduling simulation results and analyze the scheduling potential of the flexible resources in the substation area. The indicators include energy utilization rate, load smoothness and renewable energy consumption rate;

[0053] The optimization and improvement module is used to optimize the unified energy storage model and improve the dispatching strategy through a genetic algorithm;

[0054] The continuous monitoring module is used to continuously monitor the operation of the load, renewable energy and energy storage system in the substation area, and adjust the dispatching strategy according to real-time data.

[0055] The unified energy storage model construction module includes a state transfer function calculation unit and a reward function construction unit;

[0056] The state transfer function calculation unit is used to construct a state transfer function of a unified energy storage system;

[0057] The reward function construction unit is used to construct and define a reward function and store the reward obtained after the energy system performs an action.

[0058] A terminal comprises a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of any one of the methods.

[0059] A computer-readable storage medium stores a computer program, which implements the steps of any one of the methods when executed by a processor.

[0060] Beneficial effects of the present invention:

[0061] The present invention solves the coordination and optimal scheduling of multi-source flexible resources in a substation by introducing an energy storage device model and a potential calculation method; solves the problem of uneven and unreasonable resource allocation by encoding scheduling strategy parameters and performing fitness evaluation; realizes reasonable allocation and utilization of resources by setting fitness functions and fitness thresholds; realizes parallel scheduling and optimization of multiple resources by utilizing optimization algorithms such as genetic algorithms, thereby improving scheduling efficiency and task execution speed; sets convergence conditions, effectively controls the running time of the algorithm, and ensures that the optimal solution is found within a certain time. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 A flow chart of a flexible resource scheduling method for a substation area proposed by the present invention;

[0063] Figure 2 The present invention provides a block diagram of a flexible resource scheduling system for a substation. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only embodiments of a part of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the protection scope of the present invention.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0067] The present invention provides a flexible resource scheduling method for a station area, such as Figure 1 The figure shows a flow chart of a flexible resource scheduling method for a substation area proposed by the present invention, and the method comprises the following steps:

[0068] Step 1: Collect historical data of loads and renewable energy in the area, where the historical data includes power and time distribution information of loads in the area and energy obtained through renewable energy.

[0069] Step 2: Based on the historical data collected in step 1, a unified energy storage model is established within the substation.

[0070] In one embodiment of the present invention, in step 2, establishing a unified energy storage model includes:

[0071] Step 2.1: Construct the state transfer function of the unified energy storage system.

[0072] In one embodiment of the present invention, in step 2.1, the construction formula of the state transfer function of the unified energy storage system is as follows:

[0073] S(t+1)=f(S(t),A(t),L(t))

[0074] Charging process: S(t+1)=min(S(t)+Pmax*Δt, C max ) (1) Discharge process: S(t+1)=max(S(t)-Pmax*Δt, 0)

[0075] No-load process: S(t+1)=S(t)

[0076] Where S(t) represents the energy storage capacity of the energy storage system at time t, S(t+1) represents the energy storage capacity of the energy storage system at time t+1, in kilowatt-hours (kWh); A(t) represents the operation of the energy storage system at time t: A(t)∈{charge,discharge,idle}; L(t) represents the load of the station; Pmax represents the upper limit of the power output of the energy storage system during charging and discharging, c max represents the maximum capacity of the energy storage system, and Δt represents the time interval between two time points.

[0077] Step 2.2: Define the reward function R(S(t), A(t), L(t)), which represents the reward obtained by the energy storage system after performing the action (A(t)).

[0078] Preferably, in step 2.2, the formula of the reward function is as follows:

[0079] R(S(t),A(t),L(t))=w1·E(S(t),A(t),L(t))+

[0080] w2·Smoothing(S(t),A(t),L(t))+w3·Renewable int (S(t),A(t),L(t)) (2)

[0081] Where E(S(t), A(t), L(t)) represents the energy utilization rate when performing the energy storage system operation A(t) under the current energy storage capacity S(t) and the station load L(t);

[0082] Smoothing(S(t),A(t),L(t)) represents the load smoothness when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t);

[0083] Renewable int (S(t), A(t), L(t)) represents the renewable energy consumption rate when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t), indicating how much renewable energy is used in the current dispatch;

[0084] w1, w2, w 3 is the weight of each factor, which is used to adjust the importance of each factor in the reward function. In this embodiment, w1=0.4, w2=0.3, w3=0.3 are set based on experience, historical data and expert opinions.

[0085] The input is the state S(t) of the energy storage system, the operation A(t), and the substation load L(t); the output is a reward value calculated according to the given weight and the defined formula. The higher the reward value, the better the effect of the system after the operation is performed. In this embodiment, the reward function can consider multiple factors, including energy utilization efficiency, smoothness of substation load, and renewable energy consumption rate.

[0086] Step 2.3: Use the dynamic programming algorithm to iteratively calculate the optimal strategy for the energy storage system to perform different operations in different states to maximize the reward function.

[0087] In one embodiment of the present invention, maximizing the reward function includes: setting an initial energy storage state S(0);

[0088] Update the reward function for performing various actions in each state, and select the best action that maximizes the overall reward; update the energy storage state according to the state transition after the energy storage system performs various actions in the current state, and calculate the reward according to the defined reward function; evaluate the value of selecting different actions in each state, and update the strategy according to the reward function and state transition until the algorithm converges, the strategy no longer changes, and the iteration stops when the optimal strategy is reached.

[0089] Preferably, an initial energy storage state S(0) is set, and a suitable initial value can usually be selected, such as zero or the average value of the load in the substation; a reward function is initialized to evaluate the benefits brought by the actions in each state;

[0090] Update the reward function for performing various actions in each state, and select the best action that maximizes the overall reward, specifically including: determining the state of the chromosome and the optional operation, that is, the state represents the current status of the chromosome, and the action represents the adjustment of the chromosome; in this embodiment, it also includes formulating the transition rules between states, that is, how the chromosome enters the next state after performing different operations in different states; the transition rules between states are as follows:

[0091] When charging is performed, the state of the energy storage system will be adjusted accordingly based on the charging efficiency and charging power; the transfer rules include considering factors such as charging power and battery charging efficiency to determine the next state, such as the energy storage capacity after charging and charging loss.

[0092] When performing a discharge operation, the state of the energy storage system is adjusted according to the discharge power and discharge efficiency; the transfer rules include considering factors such as discharge power and battery discharge efficiency to determine the next state, such as the energy storage capacity after discharge and the discharge loss.

[0093] If no action is taken in a certain state, the state of the energy storage system will remain unchanged or slightly adjusted based on factors such as natural discharge; the transfer rule takes into account the natural loss of the energy storage system to determine the next state.

[0094] Recursively update the value function of each state, consider the effects of performing different actions, and select the optimal operation; consider maximizing the utilization of the energy storage system and the smoothness of the grid load as the optimization goal. The value function is defined as the long-term average reward brought by performing a certain action in a certain state. The formula of the value function is as follows:

[0095]

[0096] Where a represents the discount factor, which is used to balance the importance of current rewards and future rewards, R(s t ,a t ) means in state s t Next, perform action a t The instant reward obtained, T represents the number of time steps, which is used to represent the time range considered.

[0097] Based on the updated value function, determine the best action to maximize the overall reward. Continue to iterate and update the value function until the best strategy is found.

[0098] In each iteration, the state transition of the energy storage system after performing various actions in the current state is considered, the energy storage state is updated, and the reward is calculated according to the defined reward function;

[0099] After multiple iterations, the value of choosing different actions in each state is evaluated, and the strategy is updated according to the reward function and state transition until the algorithm converges, that is, the strategy no longer changes and the iteration is stopped when the optimal strategy is reached, that is, the best action that maximizes the overall reward is selected; the evaluation of the value of choosing different actions in each state is usually reflected in the estimation of the long-term cumulative reward or utility obtained by performing each action in each state; it can be calculated by the value function of performing each action in each state.

[0100] The model established above can describe the behavior of the energy storage system, including charging, discharging and energy storage efficiency, and take into account the technical parameters and capacity limitations of the energy storage system; this model can provide a dynamic scheduling strategy for the energy storage system within the substation to achieve efficient use of energy and smooth regulation of substation loads.

[0101] Step 3: Use the unified energy storage model established in step 2 and the historical data collected in step 1 to establish a scheduling strategy, perform flexibility resource scheduling simulation, and optimize the model.

[0102] In one embodiment of the present invention, establishing a scheduling strategy includes:

[0103] Initialize the parameters of the unified energy storage model and calculate the charging power and discharging power of the energy storage system based on the historical data of load and renewable energy within the set time step;

[0104] The charging and discharging time of renewable energy is set according to the calculated charging power and discharging power of the energy storage system, and charging is performed during the peak period of renewable energy generation or the low load period, and discharging is performed during the low period of renewable energy generation or the peak load period. In this embodiment, the parameters for initializing the unified energy storage model include the charging efficiency Eff charge and discharge efficiency Eff discharge , charge and discharge rate limit P max , the initial energy storage state S(0).

[0105] Among them, optimize the charging efficiency Eff charge and discharge efficiency Eff discharge It can improve the efficiency of the energy storage system in the energy conversion process and reduce energy loss; optimize the charge and discharge rate limit P max The power output of the energy storage system can be better controlled to avoid system overload or inefficiency. Optimizing the initial energy storage state S(0) can affect the system's initial performance and scheduling effect.

[0106] Step 4: Perform indicator evaluation based on the flexibility resource scheduling simulation, the indicators including energy utilization, load smoothness and renewable energy consumption rate.

[0107] In one embodiment of the present invention, the index can be evaluated by using, for example, a root mean square error (RMSE) or a standard deviation to measure the degree of difference between the simulated load curve and the ideal smooth curve.

[0108] Step 5: Optimize the unified energy storage model through genetic algorithm, and improve the dispatching strategy based on the evaluation results of step 4.

[0109] In one embodiment of the present invention, in step 5, optimizing the unified energy storage model by using a genetic algorithm includes:

[0110] Step 5.1: Encode the scheduling strategy parameters into the chromosome code of the genetic algorithm; for example, encode the execution order and time window of each task into a part of the chromosome; the scheduling strategy parameters include energy utilization, load smoothness, total task completion time and resource utilization.

[0111] Step 5.2: Design a fitness function to evaluate the performance of each chromosome.

[0112] In one embodiment of the present invention, the fitness function takes into account indicators such as task completion time and resource utilization, so as to associate them with the actual evaluation results; the formula of the fitness function is as follows:

[0113]

[0114] Among them, T 总 represents the total completion time of all tasks; T 执 represents the total execution time of all tasks; U t Represents the total utilization of all resources; R e It represents the total number of available resources in the system, which is set in advance or actually determined according to the resource capacity of the system; w1 and w2 represent the weights of the two indicators, completion time and resource utilization, respectively. The weight parameters generally need to be set according to specific needs and the importance of the indicators, and can be determined through experimental tests or according to business needs.

[0115] Step 5.3: Set the fitness threshold and select chromosomes with high fitness as the parents of the next generation based on the evaluation results of the fitness function.

[0116] In one embodiment of the present invention, the fitness function comprehensively considers the two indicators of completion time and resource utilization, and assigns weights to different indicators according to specific needs; for example:

[0117] Fitness function = w1·energy utilization rate + w2·load smoothness + w3·renewable energy consumption rate - w4·total task completion time + w5·resource utilization rate; w1, w2, w3, w4, w5 are the weights of each indicator, which are used to adjust the importance of each indicator in the fitness function.

[0118] In this embodiment, a fixed fitness threshold is set according to experiments or prior knowledge. For example, in the optimization problem, the fitness value is determined to be 0.9 through experiments. A chromosome with high fitness will show that: high positive indicators (such as energy utilization, load smoothness, renewable energy consumption rate, resource utilization, etc.) have high values, and low negative indicators (such as the total task completion time, etc.) have low values.

[0119] Step 5.4: Simulate the genetic crossover process, cross multiple parent chromosomes to produce new offspring chromosomes; single-point crossover, multi-point crossover and other methods can be used.

[0120] Step 5.5: Introduce the set mutation probability and perform mutation operations on the new generation chromosomes to increase the diversity of the population, which helps to escape the local optimal solution.

[0121] In one embodiment of the present invention, the mutation probability is set to a value between 1% and 5%.

[0122] Step 5.6: When the set number of iterations is reached or the fitness meets the set threshold, the iteration is stopped and the optimal solution is output.

[0123] In one embodiment of the present invention, by setting a fitness threshold, the iteration is stopped when the fitness of the chromosome in the population reaches or exceeds the threshold; the fitness threshold in the fitness function is set to 0.9, and when the fitness of the chromosome in the population reaches or exceeds 0.9, the algorithm will stop iterating and output the optimal solution; the fitness value range is usually between 0 and 1, so 0.9 can be regarded as a higher fitness threshold, indicating that a very high level of performance has been achieved; by setting the fitness threshold, the convergence of the algorithm can be effectively controlled to ensure that the iteration is stopped after reaching a certain fitness level, avoiding overfitting and long-term operation. In addition, setting the fitness threshold also helps to improve the efficiency of the algorithm, so that it can quickly find the optimal solution under certain conditions, and in each iteration, the fitness value of each chromosome in the current population is evaluated. If it is found that the fitness value of any chromosome reaches or exceeds the set threshold of 0.9, the iteration is stopped immediately and the chromosome is output as the optimal solution. The maximum number of iterations Nmax is set to 1000 times; even if the fitness of any chromosome does not reach the preset threshold, the algorithm will be forced to stop after 1000 iterations and output the currently found optimal solution.

[0124] In one embodiment of the present invention, in step 5, based on the evaluation result of step 4, improving the scheduling strategy includes:

[0125] Adjust the charging and discharging time according to the energy utilization rate;

[0126] According to the load smoothness, adjust the time for load to store energy and release energy;

[0127] And adjust the energy storage capacity according to the renewable energy consumption rate.

[0128] Step 6: Continuously monitor the operating data of loads, renewable energy and energy storage systems in the substation area, and adjust the dispatch strategy based on the operating data.

[0129] In one embodiment of the present invention, the adjustment of some parameters involved in the steps and methods of the present invention can be adaptively adjusted according to real-time data changes, which can be achieved through an intelligent monitoring system to ensure the real-time and effectiveness of the scheduling strategy.

[0130] At the same time, the present invention discloses a flexible resource scheduling system for a station area, such as Figure 2The figure shows a block diagram of a flexible resource scheduling system for a substation proposed in the present invention. The system includes a historical data collection module, a unified energy storage model construction module, a resource scheduling simulation module, a simulation result evaluation module, an optimization and improvement module, and a continuous monitoring module.

[0131] The historical data collection module is used to collect historical data of loads and renewable energy in the substation area, wherein the historical data includes power and time distribution information of loads in the substation area and energy obtained through renewable energy;

[0132] The unified energy storage model building module builds a unified energy storage model in the substation based on the historical data collected by the historical data collection module;

[0133] The resource scheduling simulation module establishes a scheduling strategy based on the established unified energy storage model and the collected historical data, performs flexibility resource scheduling simulation and optimizes the model;

[0134] The simulation result evaluation module is used to evaluate the scheduling simulation results and analyze the scheduling potential of the flexible resources in the substation area. The indicators include energy utilization rate, load smoothness and renewable energy consumption rate;

[0135] The optimization and improvement module is used to optimize the unified energy storage model and improve the dispatching strategy through a genetic algorithm;

[0136] The continuous monitoring module is used to continuously monitor the operation of the load, renewable energy and energy storage system in the substation area, and adjust the dispatching strategy according to real-time data.

[0137] The state transfer function calculation unit is used to construct a state transfer function of a unified energy storage system;

[0138] The reward function construction unit is used to construct and define a reward function and store the reward obtained after the energy system performs an action.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0140] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0141] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0142] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A flexible resource scheduling method for a substation, characterized in that: The method comprises the following steps: Step 1: Collect historical data of load and renewable energy in the substation, where the historical data includes power and time distribution information of load in the substation and energy obtained through renewable energy; Step 2: Based on the historical data collected in step 1, a unified energy storage model is established in the substation area; Step 3: Use the unified energy storage model established in step 2 and the historical data collected in step 1 to establish a scheduling strategy and perform a flexible resource scheduling simulation; Step 4: Perform indicator evaluation based on the flexibility resource scheduling simulation, the indicators including energy utilization rate, load smoothness and renewable energy consumption rate; Step 5: Optimize the unified energy storage model through genetic algorithm, and improve the dispatch strategy based on the evaluation results of step 4; Step 6: Continuously monitor the operating data of loads, renewable energy and energy storage systems in the substation area, and adjust the dispatch strategy based on the operating data.

2. A flexible resource scheduling method for a substation according to claim 1, characterized in that: In step 2, the establishment of the unified energy storage model includes: Step 2.1: Construct the state transfer function of the unified energy storage system; Step 2.2: Define the reward function R(S(t), A(t), L(t)), which represents the reward obtained by the energy storage system after performing the action (A(t)) under the current energy storage capacity S(t) and the load L(t); Step 2.3: Use the dynamic programming algorithm to iteratively calculate the optimal strategy for the energy storage system to perform different operations in different states to maximize the reward function.

3. A flexible resource scheduling method for a substation according to claim 2, characterized in that: In step 2.1, the construction formula of the state transfer function of the unified energy storage system is as follows: S(t+1)=f(S(t),A(t),L(t)) Charging process: S(t+1)=min(S(t)+Pmax*Δt, Cmax) Discharge process: S(t+1)=max(S(t)-Pmax*Δt,0) No-load process: S(t+1)=S(t) Where S(t) represents the energy storage capacity of the energy storage system at time t, S(t+1) represents the energy storage capacity of the energy storage system at time t+1; A(t) represents the operation of the energy storage system at time t: A(t)∈{charge,discharge,idle}; L(t) represents the load of the station; Pmax represents the upper limit of the power output of the energy storage system during charging and discharging, c max is the maximum capacity of the energy storage system, and Δt represents the time interval between two time points.

4. A flexible resource scheduling method for a substation according to claim 2 or 3, characterized in that: In step 2.2, the reward function is defined as follows: R(S(t),A(t),L(t))=w1·E(S(t),A(t),L(t))+ w2·Smoothing(S(t),A(t),L(t))+w3·Renewable int (S(t),A(t),L(t)) Where E(S(t), A(t), L(t)) represents the energy utilization rate when performing the energy storage system operation A(t) under the current energy storage capacity S(t) and the station load L(t); Smoothing(S(t),A(t),L(t)) represents the load smoothness when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t); Renewable int (S(t), A(t), L(t)) represents the renewable energy consumption rate when the energy storage system operation A(t) is performed under the current energy storage capacity S(t) and the station load L(t), indicating how much renewable energy is used in the current dispatch; w1, w2, and w3 represent the weight of each factor, which are used to adjust the importance of each factor in the reward function.

5. A flexible resource scheduling method for a substation according to claim 4, characterized in that: In step 2.3, the maximization reward function includes: Set the initial energy storage state S(0); Update the reward function for performing various actions in each state and choose the best action that maximizes the overall reward; According to the state transition of the energy storage system after performing various actions in the current state, the energy storage state is updated, and the reward is calculated according to the defined reward function; Evaluate the value of choosing different actions in each state, update the strategy according to the reward function and state transition, and stop iterating when the algorithm converges, the strategy no longer changes, and the optimal strategy is reached.

6. A flexible resource scheduling method for a substation according to claim 1, characterized in that: In step 3, establishing a scheduling strategy includes: Initialize the parameters of the unified energy storage model and calculate the charging power and discharging power of the energy storage system based on the historical data of load and renewable energy within the set time step; The charging and discharging time of renewable energy is set according to the calculated charging power and discharging power of the energy storage system. Charging is performed during the peak period of renewable energy generation or the trough period of load, and discharging is performed during the trough period of renewable energy generation or the peak period of load.

7. A flexible resource scheduling method for a substation according to claim 1, characterized in that: In step 5, optimizing the unified energy storage model by genetic algorithm includes: Step 5.1: Encode the scheduling strategy parameters into the chromosome code of the genetic algorithm; Step 5.2: Construct a fitness function to evaluate the performance of each chromosome; Step 5.3: Set the fitness threshold, and based on the evaluation results of the fitness function, select chromosomes with high fitness as the parents of the next generation; Step 5.4: Simulate the genetic crossover process, cross multiple parent chromosomes to generate new offspring chromosomes; Step 5.5: Introduce the set mutation probability, perform mutation operations on the new generation chromosomes, and increase the diversity of the population; Step 5.6: When the set number of iterations is reached or the fitness meets the set threshold, stop the iteration and output the optimal solution.

8. A flexible resource scheduling method for a substation according to claim 1, characterized in that: In step 5, based on the evaluation results of step 4, the scheduling strategy is improved including: Adjust the charging and discharging time according to the energy utilization rate; According to the load smoothness, adjust the time for load to store energy and release energy; And adjust the energy storage capacity according to the renewable energy consumption rate.

9. A flexible resource scheduling method for a substation according to claim 7, characterized in that: In step 5.2, the fitness function is constructed as follows: Among them, T 总 represents the total completion time of all tasks; T 执 represents the total execution time of all tasks; U t Represents the total utilization of all resources; R e Represents the total number of available resources in the system; w1 and w2 represent the weights of completion time and resource utilization, respectively.

10. A flexible resource scheduling method for a substation according to claim 7, characterized in that: In step 5.5, the mutation probability is set to a value between 1% and 5%.

11. A flexible resource scheduling system for a substation based on the method according to any one of claims 1 to 10, comprising a historical data collection module, a unified energy storage model construction module, a resource scheduling simulation module, a simulation result evaluation module, an optimization and improvement module, and a continuous monitoring module, characterized in that: The historical data collection module is used to collect historical data of loads and renewable energy in the substation area, wherein the historical data includes power and time distribution information of loads in the substation area and energy obtained through renewable energy; The unified energy storage model building module builds a unified energy storage model in the substation based on the historical data collected by the historical data collection module; The resource scheduling simulation module establishes a scheduling strategy based on the established unified energy storage model and the collected historical data, performs flexibility resource scheduling simulation and optimizes the model; The simulation result evaluation module is used to evaluate the scheduling simulation results and analyze the scheduling potential of the flexible resources in the substation area. The indicators include energy utilization rate, load smoothness and renewable energy consumption rate; The optimization and improvement module is used to optimize the unified energy storage model and improve the dispatching strategy through a genetic algorithm; The continuous monitoring module is used to continuously monitor the operation of the load, renewable energy and energy storage system in the substation area, and adjust the dispatching strategy according to real-time data.

12. A flexible resource scheduling system for substations according to claim 11, characterized in that: The unified energy storage model construction module includes a state transfer function calculation unit and a reward function construction unit; The state transfer function calculation unit is used to construct a state transfer function of a unified energy storage system; The reward function construction unit is used to construct and define a reward function and store the reward obtained after the energy system performs an action.

13. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-10.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images