Complex power distribution network energy storage locating and sizing method, system, equipment and medium

Abstract

The invention relates to a complex power distribution network energy storage locating and sizing method, system and device and a medium, and the method comprises the steps: obtaining operation data, and constructing a corresponding operation constraint condition according to the operation data; based on the operation data and the operation constraint conditions, performing simulation analysis on the operation states of the complex power distribution network at a plurality of preset moments, and determining a key index system; generating a comprehensive target of energy storage optimization configuration according to the key index system; based on the comprehensive target and the operation constraint condition, a preset energy storage optimization configuration double-layer model is adopted, the energy storage power station layout is used as an optimization object through an outer-layer configuration optimization sub-model, an energy storage power station operation strategy is used as an optimization object through an inner-layer scheduling optimization sub-model, iterative solution is conducted on the optimization object according to the comprehensive target, and the energy storage power station layout is obtained. And obtaining an energy storage power station layout and operation strategy until the comprehensive target reaches a preset convergence condition. The method has the effect of improving the effectiveness of the energy storage power station configuration scheme.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power distribution network operation and energy storage optimal configuration, and particularly relates to a complex power distribution network energy storage site selection and capacity determination method, system, device and medium. BACKGROUND

[0002] At present, with a large number of distributed power sources, electric vehicles and adjustable loads connected to the power distribution network, the network structure and operation condition of the power distribution network are becoming increasingly complex, the node voltage level and branch power flow fluctuate continuously in time and space, and the power grid faces more stringent constraint requirements in terms of safe and stable operation, power quality control and power supply reliability guarantee. In order to improve the regulation ability and flexibility of the complex power distribution network, the operation management department begins to configure centralized or station-level energy storage power stations in the power distribution network, hoping to achieve the goals of peak clipping, valley filling, voltage support and loss reduction in various operation scenarios, but the site selection and capacity determination of the energy storage power station often need to consider multiple constraints and requirements such as power grid structure, operation boundary and investment and operation cost in specific projects.

[0003] At present, for the configuration of energy storage power stations in complex power distribution networks, the energy storage configuration scheme is usually constructed based on historical operation data and planning scenarios, and the access location and capacity scale of the energy storage power station are evaluated under typical operation conditions through pre-set operation constraints, so as to give the site and capacity configuration results of the energy storage station, but the configuration process is mostly based on a few representative scenarios or simplified operation boundaries, and the coupling influence of the operation state change of the power distribution network, the power grid vulnerability distribution and the loss level on different time scales is described roughly, and it is often difficult to simultaneously reflect the comprehensive needs of power grid safety, economy and energy loss in a unified framework. SUMMARY

[0004] The purpose of the present application is to provide a complex power distribution network energy storage site selection and capacity determination method, system, device and medium, to solve the technical problem that the existing power distribution network energy storage site selection and capacity determination method adopts a static single-scenario or single-index configuration idea in the multi-time and multi-constraint operation scenarios of the complex power distribution network, resulting in insufficient matching degree of the obtained energy storage power station configuration scheme and the actual operation condition.

[0005] In order to achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: In a first aspect, the present application provides a complex power distribution network energy storage site selection and capacity determination method, which comprises: acquiring operation data, and constructing corresponding operation constraint conditions according to the operation data; based on the operation data and the operation constraint conditions, simulating and analyzing the operation state of the complex power distribution network at a plurality of preset time points, and determining a key index system; generate a comprehensive target of energy storage optimal configuration according to the key index system; Based on the comprehensive target and the operation constraint condition, a preset energy storage optimal configuration double-layer model is adopted, an outer layer configuration optimization sub-model takes the energy storage power station layout as an optimization object, an inner layer scheduling optimization sub-model takes the energy storage power station operation strategy as an optimization object, the optimization objects are iteratively solved according to the comprehensive target, until the comprehensive target reaches a preset convergence condition, and the energy storage power station layout and the operation strategy are obtained.

[0006] By adopting the above technical solution, by acquiring operation data and constructing corresponding operation constraint conditions according to the operation data, the power balance boundary, the energy storage operation boundary and the safe operation boundary of the distribution network can be fully solidified before optimization and solving, so that the subsequent simulation and optimization process is always carried out in the actual feasible operation space, and the physically unrealizable configuration scheme is avoided; by simulating and analyzing the operation state of the complex distribution network at a plurality of preset time points based on the operation data and the operation constraint conditions and determining the key index system, the quantitative relationship of multiple indexes such as power grid vulnerability, energy storage cost and active network loss in the time dimension can be described, so as to provide a unified and measurable evaluation basis for subsequent multi-objective trade-off; by generating a comprehensive target of energy storage optimal configuration according to the key index system, multiple indexes such as safety, economy and loss level can be uniformly mapped into a single comprehensive evaluation quantity, so as to facilitate comparison and convergence judgment in the same optimization framework; by using the preset energy storage optimal configuration double-layer model to take the energy storage power station layout and the operation strategy as the optimization objects for iterative solving based on the comprehensive target and the operation constraint condition, the optimal solution of the comprehensive target can be gradually approached under the linkage adjustment of the outer layer site selection and the inner layer charging and discharging strategy, so that the energy storage power station layout and the operation strategy considering the power grid safety and stability and investment and operation benefit are obtained.

[0007] In an example, the application can be further configured to: the operation data constructing corresponding operation constraint conditions comprises: establishing a power balance constraint based on the active power of each node in the operation data; establishing an energy storage constraint based on the operation parameters of the energy storage power station in the operation data; establishing a safe operation constraint based on the safe operation boundary parameters of the distribution network in the operation data; generating the operation constraint condition according to the power balance constraint, the energy storage constraint and the safe operation constraint.

[0008] By adopting the technical scheme, the active power balance constraint is established based on the active power of each node in the operation data, the active power balance of the source, load, storage and network loss in the power distribution network is ensured at each time, and thus the simulation and optimization process complies with the law of conservation of energy; the storage constraint is established based on the operation parameters of the energy storage power station in the operation data, the charging and discharging power range and the state of charge evolution process of the energy storage power station are accurately limited, and thus an operation scheme exceeding the equipment capacity or being unfavorable to the service life is avoided in the optimization process; the safe operation constraint is established based on the safe operation boundary parameters of the power distribution network in the operation data, the node voltage, current and line current carrying capacity and other safe boundaries are fixed into the model, and thus the candidate scheme does not trigger the operation risks such as voltage out-of-limit and line overload; the operation constraint condition is generated according to the power balance constraint, the storage constraint and the safe operation constraint, a unified constraint set covering the overall operation boundary of the power distribution network is formed, and thus a consistent and complete feasible region is provided for subsequent simulation analysis and double-layer optimization.

[0009] In an example, the application can be further configured to: based on the operation data and the operation constraint condition, perform simulation analysis on the operation state of the complex power distribution network at a plurality of preset time points, and determine a key index system, including: perform simulation calculation according to the operation data and the operation constraint condition, to obtain the voltage per unit value of each node at different time points and the active power of the network loss of each branch; based on the voltage per unit value and a preset maximum offset threshold, calculate the power grid vulnerability of each node at different time points, aggregate the power grid vulnerability, and obtain a power grid vulnerability index; calculate the energy storage investment cost and the energy storage operation and maintenance cost as the energy storage cost according to the operation data; obtain an active network loss index according to the cumulative result of the active network loss at different time points; generate the key index system according to the power grid vulnerability index, the energy storage cost and the active network loss index.

[0010] By adopting the technical scheme, the voltage per unit of each node and the active power of network loss of each branch at different time are obtained through simulation calculation according to the operation data and the operation constraint condition, the voltage level and the loss distribution of the complex distribution network under multiple time and multiple working conditions can be reflected, and thus the basic data for subsequent fine calculation of the vulnerability and the network loss index are provided; the comprehensive voltage bearing capacity of the entire distribution network under disturbance or load fluctuation can be quantified by calculating the power grid vulnerability of each node at different time based on the voltage per unit and the preset maximum offset threshold, and thus the basis for paying attention to the weak area during site selection and capacity determination is provided; the energy storage investment cost and the energy storage operation and maintenance cost are calculated according to the operation data as the energy storage cost, the construction and operation and maintenance cost brought by different station sites and capacity combinations can be converted into a unified cost index, and thus the economy and performance improvement can be balanced in the planning stage; the active power loss index is obtained according to the cumulative result of the active power of network loss at different time, the long-term influence of different operation schemes on the power loss can be evaluated, and thus the quantitative reference for reducing the energy loss of the distribution network is provided; the key index system is generated according to the power grid vulnerability index, the energy storage cost and the active power loss index, a multi-dimensional evaluation framework covering safety, economy and loss level can be constructed, and thus the index foundation for subsequent comprehensive target construction and optimization solution is laid.

[0011] The application can be further configured in an example as follows: the comprehensive target of the energy storage optimization configuration generated according to the key index system includes: The power grid vulnerability index, the energy storage cost and the active power loss index are normalized to obtain normalized indexes; The normalized indexes are respectively configured with corresponding preset weights for weighted combination to generate the comprehensive target of the energy storage optimization configuration.

[0012] By adopting the technical scheme, the power grid vulnerability index, the energy storage cost and the active power loss index are normalized, the differences between different indexes in dimension and numerical scale can be eliminated, and thus unreasonable domination of a certain index on the comprehensive evaluation due to too large value magnitude or different dimension can be avoided; the normalized indexes are respectively configured with corresponding preset weights for weighted combination to generate the comprehensive target of the energy storage optimization configuration, the importance of safety, economy and loss control in actual engineering can be quantitatively weighed, and thus the adjustable compromise between multiple targets in the optimization process can be realized.

[0013] The application can be further configured in an example as follows: based on the comprehensive target and the operation constraint condition, a preset energy storage optimization configuration double-layer model is adopted, the configuration optimization sub-model of the outer layer takes the energy storage power station layout as the optimization object, the scheduling optimization sub-model of the inner layer takes the energy storage power station operation strategy as the optimization object, and the optimization objects are iteratively solved according to the comprehensive target, including: access node position, rated power and rated capacity of the energy storage power station and combine them as outer decision variables as the energy storage power station layout scheme; input the energy storage power station layout scheme, the operation data and the operation constraint condition into the inner layer of the energy storage optimization configuration double-layer model, simulate and calculate the energy storage charging and discharging power at a preset time as the inner layer decision variable to obtain the key indicators corresponding to each energy storage power station layout scheme; evaluate the energy storage power station layout scheme according to the key indicators and the comprehensive target, and then iteratively update the outer layer decision variable based on the evaluation result, and generate an updated energy storage power station layout scheme until the comprehensive target reaches a preset convergence condition; in the case where the comprehensive target reaches the preset convergence condition, the corresponding energy storage power station layout scheme and energy storage charging and discharging power are taken as the energy storage power station layout and operation strategy.

[0014] By adopting the above technical solution, by obtaining the access node position, rated power and rated capacity of the energy storage power station and combining them as the outer layer decision variable as the energy storage power station layout scheme, different station sites and fixed capacity combinations can be uniformly expressed at the outer optimization layer, thereby providing a variable basis for systematically searching for multiple energy storage layout schemes. By inputting the energy storage power station layout scheme, the operation data and the operation constraint condition into the inner layer of the energy storage optimization configuration double-layer model, simulating and calculating the energy storage charging and discharging power at a preset time as the inner layer decision variable and obtaining the key indicators corresponding to each energy storage power station layout scheme, the influence of different charging and discharging strategies on the grid vulnerability, cost and network loss can be evaluated under the given layout premise, thereby providing quantitative feedback for the outer layer to judge the pros and cons of the layout scheme. By evaluating the energy storage power station layout scheme according to the key indicators and the comprehensive target and iteratively updating the outer layer decision variable based on the evaluation result, the layout scheme can be gradually improved under the guidance of the comprehensive target, thereby improving the probability of the candidate scheme approaching the global optimum. By taking the corresponding energy storage power station layout scheme and energy storage charging and discharging power as the energy storage power station layout and operation strategy when the comprehensive target reaches the preset convergence condition, an integrated scheme that matches the long-term planning and actual operation demand can be output, thereby improving the overall collaborative effect of energy storage configuration and dispatching in a complex distribution network.

[0015] In an example, the application can be further configured to: simulate and calculate the energy storage charging and discharging power at a preset time as the inner layer decision variable to obtain the key indicators corresponding to each energy storage power station layout scheme, including: take the energy storage power station layout scheme, the operation data and the operation constraint condition as state space data; input the state space data into a preset reinforcement learning model, analyze and adjust the energy storage charging and discharging power with the comprehensive target as an optimization criterion, and obtain second energy storage charging and discharging power; input the second energy storage charging and discharging power and the state space data into an inner simulation model for simulation analysis, obtain the operation state of the complex power distribution network at different time points, and calculate the key indicators of each energy storage power station layout scheme according to the operation state and the key indicator system.

[0016] By adopting the above technical solutions, the energy storage power station layout scheme, operation data and operation constraint conditions are taken as state space data, the grid structure, operation condition and constraint boundary information can be embedded in a single state description, thereby providing complete environment representation for subsequent strategy optimization based on learning and simulation; the state space data is input into a preset reinforcement learning model, the energy storage charging and discharging power is analyzed and adjusted with the comprehensive target as an optimization criterion, and the second energy storage charging and discharging power is obtained, the charging and discharging strategy more favorable to the comprehensive target can be adaptively searched without explicitly solving a complex analytical expression, thereby improving the convergence quality of inner strategy solving in a high-dimensional nonlinear scene; the second energy storage charging and discharging power and the state space data are input into an inner simulation model for simulation analysis, and the key indicators of each energy storage power station layout scheme are calculated according to the operation state and the key indicator system, the effect of the charging and discharging strategy learned can be verified under real power flow and operation constraints, thereby ensuring that the evaluation results fed back to the outer layer consider the optimization direction and conform to the physical characteristics of the power grid.

[0017] In an example, the application can be further configured to: the energy storage charging and discharging power is analyzed and adjusted with the comprehensive target as an optimization criterion, and the second energy storage charging and discharging power is obtained, including: the energy storage charging and discharging power is disturbed by a chaotic disturbance rule to generate a plurality of candidate energy storage charging and discharging power schemes; the candidate energy storage charging and discharging power schemes and the state space data are input into a preset reinforcement learning model, the candidate energy storage charging and discharging power schemes are evaluated according to the comprehensive target, and evaluation results of the candidate energy storage charging and discharging power schemes are obtained; According to the evaluation results, the candidate energy storage charging and discharging power scheme with the optimal evaluation result is selected from the candidate energy storage charging and discharging power schemes as the second energy storage charging and discharging power.

[0018] By adopting the technical scheme, the energy storage charging and discharging power is disturbed by the chaotic disturbance rule, a plurality of candidate energy storage charging and discharging power schemes are generated, a diversified action set with ergodicity and randomness can be constructed near the current strategy, so that the strategy optimization process can be prevented from falling into a local extremum; by inputting each candidate energy storage charging and discharging power scheme and state space data into a preset reinforcement learning model, each candidate scheme is evaluated according to the comprehensive target and an evaluation result is obtained, the advantages and disadvantages of different candidate strategies on the comprehensive target can be quantified, so as to provide a reliable criterion for selecting a better charging and discharging scheme; by selecting the candidate scheme with the optimal evaluation result from each candidate energy storage charging and discharging power scheme as the second energy storage charging and discharging power according to the evaluation result, the strategy with the best comprehensive performance can be preferentially retained in each round of update, so as to accelerate the convergence speed of the inner strategy and improve the contribution of the energy storage operation strategy to the overall optimization target.

[0019] In a second aspect, the application provides a complex power distribution network energy storage site selection and capacity determination system, which comprises: A constraint construction module is configured to acquire operation data and construct corresponding operation constraints based on the operation data; A simulation analysis module is configured to simulate and analyze the operation state of the complex power distribution network at a plurality of preset time points based on the operation data and the operation constraints, and determine a key index system; A target generation module is configured to generate a comprehensive target for energy storage optimization configuration according to the key index system; A double-layer optimization module is configured to adopt a preset energy storage optimization configuration double-layer model based on the comprehensive target and the operation constraints, take the energy storage power station layout as an optimization object by an outer configuration optimization sub-model, take the energy storage power station operation strategy as an optimization object by an inner scheduling optimization sub-model, iteratively solve the optimization objects according to the comprehensive target, until the comprehensive target reaches a preset convergence condition, and obtain the energy storage power station layout and the operation strategy.

[0020] By adopting the technical scheme, the power balance boundary, the energy storage operation boundary and the safe operation boundary of the power distribution network are fully solidified before optimization solving by acquiring operation data and constructing corresponding operation constraints, so that the subsequent simulation and optimization process is always carried out in the actual feasible operation space, and the physically unrealizable configuration scheme is avoided; by simulating and analyzing the operation state of the complex power distribution network at a plurality of preset time points based on the operation data and the operation constraints and determining the key index system, the quantitative relationship among the power grid vulnerability, the energy storage cost, the active power loss and other types of indexes in the time dimension is described, so as to provide a unified and measurable evaluation basis for subsequent multi-objective trade-off; by generating the comprehensive target of the energy storage optimization configuration according to the key index system, the safety, the economy and the loss level and other multi-dimensional indexes are uniformly mapped into a single comprehensive evaluation quantity, so as to facilitate comparison and convergence judgment in the same optimization framework; by using the preset energy storage optimization configuration double-layer model to iteratively solve the energy storage power station layout and the operation strategy based on the comprehensive target and the operation constraints, the optimal solution of the comprehensive target is gradually approached under the linkage adjustment of the outer site selection and the inner charging and discharging strategy, so that the energy storage power station layout and the operation strategy considering the power grid safety and stability and the investment and operation benefit are obtained.

[0021] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the complex power distribution network energy storage site selection and capacity determination method when executing the computer program.

[0022] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the complex power distribution network energy storage site selection and capacity determination method. BRIEF DESCRIPTION OF DRAWINGS

[0023] The accompanying drawings, which form a part of the present application, are used to provide a further understanding of the present application, and the illustrative embodiments of the present application and their description serve the purpose of explaining the present application. The present application is not limited by the accompanying drawings. Figure 1 A flowchart of the complex power distribution network energy storage site selection and capacity determination method in the embodiments of the present application; Figure 2 A structure block diagram of the complex power distribution network energy storage site selection and capacity determination system in the embodiments of the present application; Figure 3 A structure block diagram of the electronic device in the embodiments of the present application. DETAILED DESCRIPTION

[0024] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0025] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0026] Example 1 like Figure 1 As shown, this invention discloses a method for site selection and capacity determination of energy storage in complex distribution networks, specifically including the following steps: S10: Obtain runtime data and construct corresponding runtime constraints based on the runtime data.

[0027] Specifically, from historical operational measurement data, online monitoring data, and planning scenario data of complex distribution networks, under a unified time scale and node numbering rules, the voltage, current, active power, reactive power, distributed power generation output, load power, and operating parameters of candidate energy storage power stations at multiple typical moments are collected for each node. The collected operational data is formatted and its completeness is checked, obviously abnormal data is removed and missing values ​​are filled in, and a set of parameters describing the power grid operation boundary and equipment operation capability is extracted. On this basis, according to the topology and scheduling cycle of the complex distribution network, the parameters related to power flow balance, equipment capacity, and safe operation are organized and classified to generate a set of operational constraints that match the subsequent simulation analysis and optimization solution.

[0028] S20: Based on operational data and operational constraints, conduct simulation analysis on the operational status of complex power distribution networks at several preset times to determine the key indicator system.

[0029] Specifically, under a unified simulation time step, the operating data and operating constraints are input into the power flow calculation and time-series simulation program. For several preset representative moments, the power flow distribution and node voltage and current states of the complex distribution network at each moment are solved successively. During the simulation, intermediate variables such as voltage limit exceedance related to grid security, energy storage output and operating cost data related to economy, and network loss active power related to energy loss are recorded. The temporal and spatial variation characteristics of these intermediate variables are statistically analyzed. From the operational level, the vulnerability degree, energy storage configuration cost level, and active power loss level of the complex distribution network under different operating scenarios are quantitatively characterized. This provides basic data and analytical basis for the subsequent construction of a key indicator system that includes multi-dimensional evaluation indicators such as grid vulnerability, energy storage cost, and active power loss.

[0030] S30: Generate comprehensive targets for optimal energy storage configuration based on the key indicator system.

[0031] Specifically, based on the key indicator system, various indicators used to characterize grid vulnerability, energy storage costs, and active power losses are used as evaluation dimensions in multi-objective optimization. The value range, dimensions, and sensitivity of each indicator are sorted out and unified according to the preset trade-off strategy. Within a unified measurement space, a weighted combination objective function is constructed to transform each evaluation indicator from a single objective into a comprehensive objective value. This comprehensive objective can simultaneously reflect the safety, economy, and energy loss requirements of complex distribution networks after energy storage site selection and capacity determination within the same framework, providing a clear optimization direction and evaluation criteria for solving the subsequent two-level optimization model.

[0032] S40: Based on the comprehensive objectives and operational constraints, a two-layer model for pre-set energy storage optimization configuration is adopted. The outer configuration optimization sub-model takes the layout of the energy storage power station as the optimization object, and the inner scheduling optimization sub-model takes the operation strategy of the energy storage power station as the optimization object. The optimization objects are iteratively solved according to the comprehensive objectives until the comprehensive objectives reach the pre-set convergence conditions, thus obtaining the layout and operation strategy of the energy storage power station.

[0033] Specifically, in the constructed two-layer model for optimal energy storage configuration, the decision variables of the outer layer, which characterize the layout scheme of the energy storage power station, and the decision variables of the inner layer, which characterize the energy storage charging and discharging strategy, are modeled hierarchically. Under the premise of meeting the operating constraints, the outer layer searches and updates the access node locations of different energy storage power stations and their combinations of rated power and rated capacity around the comprehensive objective. Given a certain layout scheme of the outer layer, the inner layer performs operation simulation and effect evaluation on the corresponding energy storage charging and discharging power time series. The outer layer evaluates the merits of the current layout scheme and adjusts the outer layer decision variables based on the key indicators and comprehensive objective values ​​returned by the inner layer. The inner layer repeats the simulation calculation based on the updated layout scheme. The outer layer and the inner layer are iteratively coupled through the above evaluation and feedback process until the change of the comprehensive objective in several consecutive iterations meets the preset convergence condition, and the corresponding energy storage power station layout and operation strategy is output.

[0034] In one embodiment, step S10, namely constructing corresponding operational constraints based on operational data, includes: S11: Establish power balance constraints based on the active power of each node in the operating data.

[0035] Specifically, let This represents the active power injected into the distribution network at time t. This represents the active power of the energy storage power station at time t during charging and discharging at node a. Let represent the active power output by distributed power source node b at time t. This represents the active power of the total load of the distribution network at time t. Let t represent the active power loss of the distribution network at time t. Then, at every time t, the power balance constraint must be satisfied. Where NES represents the number of energy storage power stations participating in the calculation, and NDG represents the number of distributed power units participating in the calculation, thereby ensuring that the active power generated and consumed in the system remains in balance at any given time through the aforementioned power balance constraints.

[0036] S12: Establish energy storage constraints based on the operating parameters of the energy storage power station in the operating data.

[0037] Specifically, the charging and discharging power of each energy storage power station at any given time t. Apply upper and lower power limits And adopt the energy state update equation as well as The evolution of residual energy during the discharge and charging processes is described, and the state of charge is also discussed. Apply The constraints, among which, Let σ be the remaining power of the a-th energy storage station at time t, η be the self-discharge rate, η be the charge and discharge efficiency, and Δt be the time interval between two adjacent times. The above constraints limit the charge and discharge power, energy state, and state of charge of the energy storage station to within the allowable range.

[0038] S13: Establish safe operation constraints based on the boundary parameters of safe operation of the distribution network in the operation data.

[0039] Specifically, for N bus In a distribution network consisting of nodes, the per-unit voltage values ​​of each node are recorded at any time t. and node current Restricted to and Within the interval, where and Let be the lower and upper voltage limits for node i, respectively. and Let $i$ be the lower and upper limits of the current at node $i$, respectively. The above inequality constraints ensure that the voltage and current of each node in the distribution network are within the safe operating boundary range throughout the entire simulation process.

[0040] S14: Generate operating constraints based on power balance constraints, energy storage constraints, and safe operation constraints.

[0041] Specifically, power balance constraints, energy storage constraints, and safe operation constraints are summarized and organized according to time and node dimensions. The constraint expressions for each simulation moment, each node, and each energy storage power station are uniformly numbered and archived to form a set of operating constraints that simultaneously covers all simulation moments, all nodes, and all energy storage power stations. In the subsequent power flow simulation calculation and the solution of the two-layer model for energy storage optimization configuration, this set of operating constraints is used as a whole as the feasible region to restrict the search range of the outer layer energy storage power station layout scheme and the inner layer energy storage charging and discharging strategy, ensuring that any candidate solution meets the basic requirements of the grid operation boundary and the equipment operation boundary during the solution process.

[0042] In one embodiment, in step S20, based on operational data and operational constraints, the operational state of a complex power distribution network at a preset number of time points is simulated and analyzed to determine a key indicator system, including: S21: Based on the operating data and operating constraints, perform simulation calculations to obtain the per-unit voltage values ​​of each node at different times and the network loss active power of each branch.

[0043] Specifically, given the operating data and constraints, power flow calculations or time-series simulations can be used to solve the operating state of the complex distribution network at several preset time points, and the per-unit voltage value of each node can be obtained at each time point t. The active power flow of each branch is also recorded, and the per-unit voltage values ​​of each node and the active power loss of each branch at different times are compiled into time-series data, which will be used as the basis for subsequent calculations of grid vulnerability indicators, active power loss indicators and energy storage costs.

[0044] S22: Calculate the grid vulnerability of each node at different times based on the voltage per unit value and the preset maximum offset threshold, and aggregate the grid vulnerability to obtain the grid vulnerability index.

[0045] Specifically, based on the per-unit voltage value of each node at each time point. and the maximum allowable offset under normal operating conditions Computation node vulnerability ,in, Let be the per-unit voltage value at node i at time t. Umax is the maximum allowable offset threshold for the power grid under normal operating conditions. Then, a weighted average of the vulnerability of each node is calculated across the entire distribution network and over all preset time periods to obtain the overall vulnerability index of the distribution network. , where N bus V represents the total number of nodes in the distribution network, T represents the number of moments within the statistical period, and V represents the total number of nodes in the distribution network. t,min With V t,maxThese are the minimum and maximum values ​​of the voltage offset at time t, respectively, used to characterize the comprehensive sensitivity of a complex distribution network to disturbances or faults at different operating times.

[0046] S23: Calculate the energy storage investment cost and energy storage operation and maintenance cost based on the operating data as the energy storage cost.

[0047] Specifically, in energy storage cost calculation, the energy storage cost C can be expressed as the investment cost C. inv With maintenance costs C om The sum of Among them, investment costs Operation and maintenance costs Where r is the discount rate and y is the service life of the energy storage power station. and Let be the rated power and rated capacity of the a-th energy storage power station, respectively. , The corresponding investment cost per unit power and per unit capacity, , Given the corresponding unit power and unit capacity operation and maintenance costs, the energy storage investment cost and energy storage operation and maintenance cost are determined based on the above relationship and operating data, resulting in the energy storage cost index C.

[0048] S24: Based on the cumulative results of the active power loss at different times, the active power loss index is obtained.

[0049] Specifically, based on the admittance parameter G obtained from the power flow simulation ij B ij and the voltage amplitude U at each node i U j and phase angle θ i θ j ,use Calculate the active power loss of the distribution network at each time point, and statistically analyze or average the network losses at several preset time points to obtain the active power loss index P, which characterizes the level of active power loss. loss .

[0050] S25: Generate a key indicator system based on grid vulnerability indicators, energy storage costs, and active power loss indicators.

[0051] Specifically, the power grid vulnerability index V g Energy storage cost C and active power loss index P loss The combination constitutes a key indicator system, with {V g C,P loss The features are stored or output in the form of} and used as the input feature set for subsequent comprehensive objective construction and optimization.

[0052] In one embodiment, step S30, namely generating a comprehensive target for optimal energy storage configuration based on a key indicator system, includes: S31: Normalize the grid vulnerability index, energy storage cost, and active power loss index to obtain normalized indexes.

[0053] Specifically, regarding the power grid vulnerability index V g Energy storage cost C and active power loss index P loss Based on their historical range or the maximum and minimum values ​​obtained from simulation, the indicators are standardized to the same dimension and numerical range according to a unified rule. This makes the three types of indicators comparable when they are weighted and combined in the future, and avoids the unreasonable dominant role of a certain indicator on the comprehensive goal due to differences in dimension or numerical magnitude.

[0054] S32: Assign corresponding preset weights to the normalized indicators and combine them in a weighted manner to generate a comprehensive target for energy storage optimization.

[0055] Specifically, preset weights w1, w2, and w3 are assigned to the normalized grid vulnerability index, energy storage cost, and active power loss index, respectively, and a comprehensive objective function F is constructed to achieve the desired result. In this example, w1+w2+w3=1. In a typical embodiment, w1=0.3, w2=0.3, and w3=0.4 can be selected to weight the three indicators. The resulting F is used as the comprehensive optimization target of the two-layer model for energy storage optimization configuration, which is used to evaluate the advantages and disadvantages of different energy storage power station layouts and operation strategies.

[0056] In one embodiment, in step S40, based on the comprehensive objective and operational constraints, a preset two-layer energy storage optimization configuration model is adopted. The outer configuration optimization sub-model optimizes the layout of the energy storage power station, while the inner scheduling optimization sub-model optimizes the operation strategy of the energy storage power station. The optimization objects are iteratively solved according to the comprehensive objective, including: S41: Obtain the location, rated power, and rated capacity of the access node of the energy storage power station and combine them into outer-layer decision variables as the layout scheme of the energy storage power station.

[0057] Specifically, based on the topology and planning scheme of the complex distribution network, nodes that meet the site construction conditions and have access capabilities are selected as candidate energy storage access nodes. For each candidate node, several combinations of rated power and rated capacity are determined according to planning requirements and equipment selection. The node location, corresponding rated power, and rated capacity are encoded according to the variable format of the outer optimization model and combined to form a set of energy storage power station layout schemes for outer search. In a specific embodiment, based on the multi-node distribution network structure adopted in the technical solution document, all candidate nodes and their rated parameters can be included in the definition scope of the outer decision variables.

[0058] S42: Input the energy storage power station layout scheme, operation data and operation constraints into the inner layer of the two-layer model of energy storage optimization configuration, and use the energy storage charging and discharging power at the preset time as the inner layer decision variable for simulation calculation to obtain the key indicators of each energy storage power station layout scheme.

[0059] Specifically, after determining a certain energy storage power station layout scheme, the layout scheme, along with the corresponding operating data and operating constraints, is input into the inner layer of the two-layer model for energy storage optimization configuration. In the inner layer, the energy storage charging and discharging power at a preset time is used as the decision variable to be optimized. Iterative exploration and simulation calculations are performed on different charging and discharging power combinations throughout the entire scheduling cycle. Each simulation calls the power flow analysis and operation evaluation process under the premise of meeting the operating constraints. The aforementioned key indicator system is used to quantitatively evaluate the grid vulnerability, energy storage cost, and active power loss of the layout scheme under the current charging and discharging strategy. Finally, a set of corresponding key indicators is formed for each candidate energy storage power station layout scheme.

[0060] S43: Evaluate the layout scheme of energy storage power stations based on key indicators and comprehensive objectives, and then iteratively update the outer decision variables based on the evaluation results, and generate an updated layout scheme of energy storage power stations until the comprehensive objectives reach the preset convergence conditions.

[0061] Specifically, key indicators are substituted into the comprehensive objective expression constructed from the key indicator system to calculate the comprehensive objective value of each layout scheme in the current iteration round. Based on the magnitude of the comprehensive objective value, the advantages and disadvantages of different layout schemes are ranked or evaluated. According to the preset outer layer search strategy, the node access location, rated power and rated capacity in the outer layer decision variables are adjusted and updated to generate a new energy storage power station layout scheme, which is then submitted to the inner layer for simulation evaluation. This process is repeated iteratively until the change in the comprehensive objective of several adjacent iterations meets the preset convergence condition.

[0062] S44: When the comprehensive objective reaches the preset convergence condition, the corresponding energy storage power station layout scheme and energy storage charging and discharging power will be used as the energy storage power station layout and operation strategy.

[0063] Specifically, when the comprehensive objective reaches the preset convergence condition and the outer search process ends, the energy storage power station layout scheme with the optimal comprehensive objective value or that meets the planning requirements is selected from the iteration history. At the same time, the energy storage charging and discharging power timing sequence obtained by the inner layer under the layout scheme is extracted. The two are combined to form a complete energy storage power station layout and operation strategy, which is used to guide the complex distribution network to implement energy storage site selection, capacity setting and charging and discharging control in subsequent operation.

[0064] In one embodiment, in step S42, the energy storage charging and discharging power at a preset time is used as an inner-layer decision variable for simulation calculation to obtain the key indicators of each energy storage power station layout scheme, including: S421: Use the layout scheme, operation data and operation constraints of the energy storage power station as state space data.

[0065] Specifically, before performing the inner-layer simulation calculation, the current energy storage power station layout scheme given by the outer layer, along with the corresponding operating data and operating constraints, are organized according to a unified data structure. The information on the location of access nodes, rated power, and rated capacity contained in the layout scheme is combined with the load of each node and at each time in the operating data, the output of distributed power sources, line parameters, and various boundary parameters in the operating constraints to form state-space data covering both spatial and temporal dimensions. This data is used to characterize the operating environment and constraint background of the complex distribution network under the current layout scheme.

[0066] S422: Input the state space data into the preset reinforcement learning model, use the comprehensive objective as the optimization criterion, analyze and adjust the energy storage charging and discharging power to obtain the second energy storage charging and discharging power.

[0067] Specifically, state space data is fed into a pre-defined reinforcement learning model as an input variable. In this model, the comprehensive objective of energy storage optimization is used as the evaluation criterion, and the energy storage charging and discharging power at a preset time is regarded as the action quantity that needs to be adjusted. Through the policy update and value evaluation mechanism inside the reinforcement learning model, the comprehensive objective performance corresponding to different charging and discharging power values ​​in the current state space is analyzed. The differences in long-term returns or cumulative rewards of each alternative action are compared, and the energy storage charging and discharging power value that is more conducive to reducing the comprehensive objective in the current state space is derived as the second energy storage charging and discharging power output.

[0068] S423: Input the second energy storage charging and discharging power and state space data into the inner simulation model for simulation analysis to obtain the operating status of the complex distribution network at different times, and calculate the key indicators of each energy storage power station layout scheme based on the operating status and key indicator system.

[0069] Specifically, the second energy storage charging and discharging power and state space data are input into the inner simulation model. Under the premise of meeting the operating constraints, the operation status of the complex distribution network during the entire scheduling cycle is simulated by power flow and time series analysis. The voltage per unit value of each node, the network loss active power of each branch, and the power and energy state information related to energy storage operation are obtained at different times. Then, based on the grid vulnerability calculation formula, energy storage cost calculation formula, and active power loss calculation formula in the aforementioned key indicator system, the grid vulnerability index, energy storage cost index, and active power loss index of the energy storage power station layout scheme under the second energy storage charging and discharging power are calculated and summarized, thereby forming key indicators for outer evaluation.

[0070] In one embodiment, step S422, which uses the comprehensive objective as the optimization criterion to analyze and adjust the energy storage charging and discharging power to obtain the second energy storage charging and discharging power, includes: S4221: The energy storage charging and discharging power is perturbed by the chaotic perturbation rule to generate several candidate energy storage charging and discharging power schemes.

[0071] Specifically, based on the current energy storage charging and discharging power, a perturbation mechanism based on chaotic sequences is introduced. A perturbation factor sequence with ergodicity and randomness within a given interval is generated by selecting a preset chaotic mapping rule. This perturbation factor sequence is combined with the current energy storage charging and discharging power by element-wise multiplication or superposition to obtain several candidate energy storage charging and discharging power schemes distributed around the current energy storage charging and discharging power. By controlling the perturbation intensity and the number of iterations, the candidate schemes can cover a large search space while avoiding leaving the allowable operating range of the energy storage device.

[0072] S4222: Input each candidate energy storage charging and discharging power scheme and state space data into a preset reinforcement learning model, evaluate each candidate energy storage charging and discharging power scheme according to the comprehensive objective, and obtain the evaluation results of each candidate energy storage charging and discharging power scheme.

[0073] Specifically, each candidate energy storage charging and discharging power scheme is synthesized into a candidate state-action pair with the state space data one by one, and then input into a preset reinforcement learning model. Under the premise of keeping the comprehensive goal as the optimization criterion unchanged, the comprehensive goal performance that different candidate energy storage charging and discharging power schemes may achieve in the current state space is evaluated. The reinforcement learning model can output the corresponding evaluation result or reward value for each candidate scheme based on the built-in value function or strategy evaluation mechanism, thereby forming a set of evaluation results that correspond one-to-one with each candidate energy storage charging and discharging power scheme.

[0074] S4223: Based on the evaluation results, select the candidate energy storage charging and discharging power scheme with the best evaluation results from among all candidate energy storage charging and discharging power schemes, and use it as the second energy storage charging and discharging power.

[0075] Specifically, the evaluation results are compared and ranked, and the candidate energy storage charging and discharging power scheme with the best evaluation result or that meets the preset selection criteria is selected as the second energy storage charging and discharging power in the current iteration round. The second energy storage charging and discharging power is fed back to the inner layer simulation model for operation state simulation and key index calculation, so as to continuously improve the overall target performance in the subsequent joint iteration of the outer and inner layers.

[0076] Example 2 like Figure 2 As shown, based on the same inventive concept as the above embodiments, the present invention also provides a complex distribution network energy storage location and capacity determination system, comprising: The constraint construction module is used to acquire runtime data and construct corresponding runtime constraints based on the runtime data. The simulation analysis module is used to simulate and analyze the operating status of complex power distribution networks at several preset times based on operating data and operating constraints, and to determine the key indicator system. The target generation module is used to generate comprehensive targets for energy storage optimization configuration based on a key indicator system. The two-layer optimization module is used to optimize the energy storage power station layout based on the comprehensive objectives and operational constraints. It adopts a preset two-layer model for energy storage optimization configuration. The outer configuration optimization sub-model optimizes the layout of the energy storage power station, while the inner scheduling optimization sub-model optimizes the operation strategy of the energy storage power station. The optimization objects are iteratively solved according to the comprehensive objectives until the comprehensive objectives reach the preset convergence conditions, thus obtaining the layout and operation strategy of the energy storage power station.

[0077] Optional, constraint building modules include: The power balance submodule is used to establish power balance constraints based on the active power of each node in the operating data. The energy storage constraint submodule is used to establish energy storage constraints based on the operating parameters of the energy storage power station in the operating data; The safety boundary submodule is used to establish safety operation constraints based on the safety operation boundary parameters of the distribution network in the operational data. The constraint aggregation submodule is used to generate operating constraint conditions based on power balance constraints, energy storage constraints, and safe operation constraints.

[0078] Optionally, the simulation analysis module includes: The state simulation submodule is used to perform simulation calculations based on operating data and operating constraints to obtain the per-unit voltage values ​​of each node and the network loss active power of each branch at different times. The vulnerability assessment submodule is used to calculate the grid vulnerability of each node at different times based on the voltage per unit value and the preset maximum offset threshold, and to aggregate the grid vulnerability to obtain the grid vulnerability index. The cost calculation submodule is used to calculate the energy storage investment cost and energy storage operation and maintenance cost as the energy storage cost based on the operating data. The network loss calculation submodule is used to obtain the active power loss index based on the cumulative results of the active power loss at different times. The system generation submodule is used to generate a key indicator system based on grid vulnerability indicators, energy storage costs, and active power loss indicators.

[0079] Optionally, the target generation module includes: The normalization processing submodule is used to normalize the grid vulnerability index, energy storage cost and active power loss index to obtain normalized indexes. The weighted combination submodule is used to assign corresponding preset weights to the normalized indicators and combine them to generate a comprehensive target for energy storage optimization.

[0080] Optional, the two-layer optimization module includes: The layout variable submodule is used to obtain the location, rated power and rated capacity of the access node of the energy storage power station and combine them into the outer decision variables as the layout scheme of the energy storage power station. The inner simulation submodule is used to input the layout scheme, operation data and operation constraints of the energy storage power station into the inner layer of the two-layer model of energy storage optimization configuration, and to use the energy storage charging and discharging power at a preset time as the inner layer decision variable for simulation calculation to obtain the key indicators of each energy storage power station layout scheme. The outer layer update submodule is used to evaluate the layout scheme of energy storage power stations based on key indicators and comprehensive objectives, and then iteratively update the outer layer decision variables based on the evaluation results, and generate the updated layout scheme of energy storage power stations until the comprehensive objectives reach the preset convergence conditions. The strategy output submodule is used to use the corresponding energy storage power station layout scheme and energy storage charging and discharging power as the energy storage power station layout and operation strategy when the comprehensive objective reaches the preset convergence condition.

[0081] Optionally, the inner simulation submodule includes: State space unit is used to store the layout scheme, operation data and operation constraints of energy storage power station as state space data; The power adjustment unit is used to input state space data into a preset reinforcement learning model, and to analyze and adjust the energy storage charging and discharging power with the comprehensive objective as the optimization criterion to obtain the second energy storage charging and discharging power. The index calculation unit is used to input the second energy storage charging and discharging power and state space data into the inner simulation model for simulation analysis, obtain the operating status of the complex distribution network at different times, and calculate the key indicators of each energy storage power station layout scheme based on the operating status and key index system.

[0082] Optionally, the power adjustment unit includes: The perturbation generation subunit is used to perturb the energy storage charging and discharging power through chaotic perturbation rules, and generate several candidate energy storage charging and discharging power schemes. The scheme evaluation subunit is used to input each candidate energy storage charging and discharging power scheme and state space data into a preset reinforcement learning model, evaluate each candidate energy storage charging and discharging power scheme according to the comprehensive objective, and obtain the evaluation results of each candidate energy storage charging and discharging power scheme. The scheme selection subunit is used to select the candidate energy storage charging and discharging power scheme with the best evaluation results from among the candidate energy storage charging and discharging power schemes, and use it as the second energy storage charging and discharging power.

[0083] Example 3 like Figure 3 As shown, the present invention also provides an electronic device 100 for implementing a method for determining the location and capacity of energy storage in complex power distribution networks; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0084] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the method for selecting and determining the location and capacity of energy storage in a complex distribution network according to Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0085] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0086] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0087] The memory 101 in the electronic device 100 stores multiple instructions to implement a complex distribution network energy storage addressing and capacity determination method, and the processor 102 can execute multiple instructions to achieve the following: Obtain runtime data and construct corresponding runtime constraints based on the runtime data; Based on operational data and constraints, the operational status of a complex power distribution network at several preset times is simulated and analyzed to determine the key indicator system. A comprehensive target for optimal energy storage configuration is generated based on a key indicator system; Based on comprehensive objectives and operational constraints, a two-layer model for pre-defined energy storage optimization configuration is adopted. The outer configuration optimization sub-model optimizes the layout of energy storage power stations, while the inner scheduling optimization sub-model optimizes the operation strategy of energy storage power stations. The optimization objects are iteratively solved according to the comprehensive objectives until the comprehensive objectives reach the pre-defined convergence conditions, thus obtaining the layout and operation strategy of energy storage power stations.

[0088] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0089] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0090] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0091] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0092] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0093] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions 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 method for site selection and capacity determination of energy storage in complex distribution networks, characterized in that, The method includes: Obtain operational data and construct corresponding operational constraints based on the operational data; Based on the operational data and operational constraints, the operational status of a complex power distribution network at several preset times is simulated and analyzed to determine the key indicator system. A comprehensive target for optimal energy storage configuration is generated based on the aforementioned key indicator system; Based on the comprehensive objective and the operational constraints, a two-layer model for energy storage optimization configuration is adopted. The outer configuration optimization sub-model optimizes the layout of the energy storage power station, while the inner scheduling optimization sub-model optimizes the operation strategy of the energy storage power station. The optimization objects are iteratively solved according to the comprehensive objective until the comprehensive objective reaches the preset convergence condition, thereby obtaining the layout and operation strategy of the energy storage power station.

2. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 1, characterized in that, The step of constructing corresponding operational constraints based on the operational data includes: Power balance constraints are established based on the active power of each node in the operational data. Energy storage constraints are established based on the operating parameters of the energy storage power station in the aforementioned operating data; Establish safe operation constraints based on the safe operation boundary parameters of the distribution network in the aforementioned operational data; The operating constraint conditions are generated based on the power balance constraint, the energy storage constraint, and the safe operation constraint.

3. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 1, characterized in that, Based on the operational data and operational constraints, the simulation analysis of the operational state of a complex power distribution network at several preset time points is performed to determine a key indicator system, including: Simulation calculations are performed based on the operating data and operating constraints to obtain the per-unit voltage values ​​of each node and the network loss active power of each branch at different times. The grid vulnerability of each node at different times is calculated based on the voltage per unit value and the preset maximum offset threshold, and the grid vulnerability is aggregated to obtain a grid vulnerability index. The energy storage investment cost and energy storage operation and maintenance cost are calculated based on the aforementioned operational data as the energy storage cost. Based on the cumulative results of the active power loss at different times, the active power loss index is obtained; The key indicator system is generated based on the grid vulnerability index, the energy storage cost, and the active power grid loss index.

4. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 3, characterized in that, The comprehensive objective for generating optimal energy storage configuration based on the key indicator system includes: The grid vulnerability index, the energy storage cost, and the active power loss index are normalized to obtain normalized indices. The normalized indicators are assigned corresponding preset weights and combined in a weighted manner to generate the comprehensive target for energy storage optimization configuration.

5. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 1, characterized in that, Based on the comprehensive objective and the operational constraints, a pre-defined two-layer model for energy storage optimization configuration is adopted. The outer layer, a configuration optimization sub-model, optimizes the layout of energy storage power stations, while the inner layer, a scheduling optimization sub-model, optimizes the operational strategies of energy storage power stations. The optimization objects are iteratively solved according to the comprehensive objective, including: The location, rated power, and rated capacity of the access nodes of the energy storage power station are obtained and combined into outer-layer decision variables, which serve as the layout scheme for the energy storage power station. The energy storage power station layout scheme, the operating data, and the operating constraints are input into the inner layer of the two-layer model of energy storage optimization configuration. The energy storage charging and discharging power at a preset time is used as the inner layer decision variable for simulation calculation to obtain the key indicators of each of the energy storage power station layout schemes. The energy storage power station layout scheme is evaluated based on the key indicators and the comprehensive objective. Then, the outer decision variables are iteratively updated based on the evaluation results, and an updated energy storage power station layout scheme is generated until the comprehensive objective reaches the preset convergence condition. When the comprehensive objective reaches the preset convergence condition, the corresponding energy storage power station layout scheme and energy storage charging and discharging power will be used as the energy storage power station layout and operation strategy.

6. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 5, characterized in that, The process of using the energy storage charging and discharging power at a preset time as an inner-layer decision variable for simulation calculation yields key indicators for each energy storage power station layout scheme, including: The energy storage power station layout scheme, the operating data, and the operating constraints are used as state space data. The state space data is input into a preset reinforcement learning model, and the energy storage charging and discharging power is analyzed and adjusted using the comprehensive objective as the optimization criterion to obtain the second energy storage charging and discharging power. The second energy storage charging and discharging power and the state space data are input into the inner simulation model for simulation analysis to obtain the operating status of the complex power distribution network at different times. Based on the operating status and the key indicator system, the key indicators of each energy storage power station layout scheme are calculated.

7. The method for site selection and capacity determination of energy storage in complex distribution networks according to claim 6, characterized in that, The step of analyzing and adjusting the energy storage charging and discharging power based on the comprehensive objective as the optimization criterion to obtain the second energy storage charging and discharging power includes: The energy storage charging and discharging power is perturbed by chaotic perturbation rules to generate several candidate energy storage charging and discharging power schemes. Each of the candidate energy storage charging and discharging power schemes and the state space data are input into a preset reinforcement learning model. The candidate energy storage charging and discharging power schemes are evaluated according to the comprehensive objective to obtain the evaluation results of each candidate energy storage charging and discharging power scheme. Based on the evaluation results, the candidate energy storage charging and discharging power scheme with the best evaluation results is selected from among the candidate energy storage charging and discharging power schemes, and is used as the second energy storage charging and discharging power.

8. A location and capacity determination system for energy storage in complex distribution networks, characterized in that, The system includes: The constraint construction module is used to acquire runtime data and construct corresponding runtime constraints based on the runtime data. The simulation analysis module is used to perform simulation analysis on the operation status of a complex power distribution network at a preset number of time points based on the operation data and the operation constraints, and to determine the key indicator system. The target generation module is used to generate a comprehensive target for energy storage optimization configuration based on the key indicator system. The dual-layer optimization module is used to optimize the energy storage power station layout and the operation constraints based on the comprehensive objective and the operation constraints. The outer layer configuration optimization sub-model optimizes the layout of the energy storage power station, while the inner layer scheduling optimization sub-model optimizes the operation strategy of the energy storage power station. The optimization objects are iteratively solved according to the comprehensive objective until the comprehensive objective reaches the preset convergence condition, so as to obtain the layout and operation strategy of the energy storage power station.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the steps of the complex distribution network energy storage location and capacity determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the steps of the complex distribution network energy storage location and capacity determination method as described in any one of claims 1 to 7.

Images