A method, system, equipment, and medium for integrated planning of wind, solar, hydro, thermal, and energy storage in provincial power grids based on coupling feature quantization.
By calculating the coupling characteristic parameter set of wind, solar, hydro, thermal and energy storage and using a group optimization algorithm, the power structure and energy storage deployment of the provincial power grid are optimized, solving the problems of wind curtailment, solar curtailment and hydro curtailment in the collaborative planning of multiple power sources, and improving the operating efficiency and economy of the power grid.
Patent Information
- Application Number
- CN202611298984.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-26
- Publication Date
- 2026-11-17
AI Technical Summary
In existing provincial power grid planning, the coupling relationship of multiple types of power sources has not been effectively coordinated and determined, resulting in repeated problems of wind curtailment, solar curtailment, and hydropower curtailment. Existing technologies are insufficient to optimize the power structure and energy storage deployment scheme at the overall level.
A planning method based on coupling feature quantization is adopted. By calculating the set of coupling feature parameters of wind, solar, hydro, thermal and energy storage, a group optimization algorithm is used to generate candidate schemes. The simulation program is run to perform iterative optimization to determine the installed capacity, capacity ratio and energy storage layout, so as to achieve the coordinated optimization of multiple types of power sources.
It has improved the utilization level of the complementary relationship and regulation capacity of multiple types of power sources, reduced the curtailment of wind, solar and hydropower, and optimized the economy and feasibility of the power grid.
Smart Images

Figure CN123115667A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of power system planning technology, specifically to a method, system, equipment, and medium for integrated planning of provincial power grid wind, solar, hydro, thermal, and energy storage based on coupling characteristic quantification. Background Technology
[0002] The power structure of provincial power grids is gradually shifting from being dominated by thermal and hydropower to a pattern where wind, solar, hydro, thermal, and energy storage coexist. Different types of power sources differ significantly in their output characteristics: wind and solar power output is dominated by meteorological conditions; hydropower output is constrained by seasonal water inflows and cascade dispatch rules; thermal power has minimum technical output and ramp-up rate limitations; and energy storage needs to switch between charging and discharging states under capacity and lifespan constraints. These different power sources have both complementary and mutually restrictive relationships. Currently, provincial power grid planning generally adopts a step-by-step approach to address the coordination of multiple power sources: first, the development scale of wind and solar power is determined separately; then, thermal and hydropower capacity is arranged according to the remaining load; and finally, energy storage is configured to fill the regulation capacity gap.
[0003] The aforementioned step-by-step approach fragments the coupling relationships between different types of power sources. Each planning step can only make decisions based on local constraints, making it difficult to coordinately determine the installed capacity, capacity ratio, and energy storage deployment schemes for each type of power source at an overall level. Furthermore, the existing planning model lacks a quantitative coupling expression of the cascade scheduling characteristics of hydropower units, the adjustable range after the flexibility upgrade of thermal power plants, and the marginal absorption effect of energy storage on curtailed power. This results in the planning scheme's insufficient utilization of the complementary relationships and adjustment capabilities of multiple power sources, leading to repeated occurrences of wind, solar, and hydropower curtailment in actual operation. Summary of the Invention
[0004] In view of the above-mentioned existing problems, the present invention provides a provincial power grid wind, solar, hydro, thermal and energy storage integrated planning method, system, equipment and medium based on coupling feature quantification, to solve the problem that existing technologies are unable to determine the installed capacity, capacity ratio and energy storage deployment scheme of various types of power sources in a holistic manner, and the problem of repeated wind curtailment, solar curtailment and hydro curtailment.
[0005] To address the aforementioned technical challenges, a provincial power grid integrated planning method based on coupling feature quantization is proposed, comprising: Based on the acquired power output time-series data and operational constraint data of wind, solar, hydro, thermal power, and energy storage, a set of coupling characteristic parameters for wind, solar, hydro, thermal power, and energy storage is calculated. Constraint boundaries for optimizing power generation capacity are set based on these coupling characteristic parameter sets. A swarm optimization algorithm is used to generate candidate planning schemes within these constraints. A simulation program is run to solve the candidate planning schemes, obtaining operating costs and constraint violations. The operating costs and constraint violations are then fed back to the swarm optimization algorithm for iterative optimization, outputting the installed capacity and capacity ratio. The total energy storage capacity is determined based on the installed capacity and capacity ratio. Energy storage site allocation is performed based on the total energy storage capacity, obtaining the rated energy storage capacity and rated power. The rated energy storage capacity and rated power are fed back to the swarm optimization algorithm for iterative updates, outputting an integrated planning scheme.
[0006] As a preferred embodiment of the integrated planning method for provincial power grid wind, solar, hydro, thermal, and energy storage based on coupling feature quantization described in this invention, the simulation program for solving candidate planning schemes includes: Based on the set of coupling feature parameters, establish the operational constraints that the candidate planning scheme should satisfy; Within the entire year time series, with the goal of minimizing operating costs, and under the premise of satisfying the aforementioned operating constraints, the candidate planning scheme is solved, and the operating cost is output. If a candidate planning scheme does not meet the operational constraints, the deviation exceeding the corresponding constraint limit is accumulated to obtain the constraint violation amount corresponding to the candidate planning scheme. The operational cost and the constraint violation amount are then returned to the population optimization algorithm.
[0007] The beneficial effects of this preferred technical solution are as follows: This invention maps the set of coupled feature parameters to the operational constraints that candidate planning schemes must satisfy, and solves the operational costs through year-round time-series simulation, so that the economic evaluation of the scheme is based on the actual operational feasibility; it introduces the constraint violation quantity as a deviation measure independent of the operational cost, so that the group optimization algorithm can continuously perceive the feasibility of the scheme during the optimization process and gradually converge to the optimal solution that satisfies the constraints.
[0008] As a preferred embodiment of the provincial power grid integrated wind-solar-hydro-thermal-storage planning method based on coupling feature quantization described in this invention, wherein: determining the total energy storage capacity includes, Starting with zero energy storage capacity as the initial value, the energy storage capacity is gradually increased according to the preset capacity increment step. The installed capacity and capacity ratio, along with the energy storage capacity after the current increment, are input into the operation simulation program to obtain the annual abandoned power of each node. The annual abandoned power of each node is summed to obtain the total annual abandoned power. Divide the difference in the total annual abandoned electricity before and after two consecutive increases by the capacity increase step size to obtain the marginal energy storage absorption benefit; If the marginal energy storage absorption benefit is greater than or equal to the preset marginal energy storage benefit threshold, the energy storage capacity will continue to increase. If the marginal energy storage absorption benefit is less than the preset marginal energy storage benefit threshold, the increment stops, and the energy storage capacity before the current increment is taken as the total energy storage capacity.
[0009] As a preferred embodiment of the provincial power grid integrated wind-solar-hydro-thermal-storage planning method based on coupling feature quantization described in this invention, the execution of energy storage deployment allocation includes, The ratio of the annual abandoned power of each node to the total annual abandoned power is taken as the abandoned power percentage of each node. Obtain the average upward peak shaving margin of each node during the peak load period of the whole year, and use the ratio of the average upward peak shaving margin to the maximum peak shaving margin as the peak shaving margin ratio of each node. Based on the ratio of abandoned electricity to peak shaving margin of each node, the priority index of energy storage deployment for each node is obtained by weighting according to the preset weighting coefficient. Based on the energy storage deployment priority index, the total energy storage capacity is allocated to each node, and the rated energy storage power of each node is determined according to the energy storage capacity allocated to each node and the preset charging and discharging time.
[0010] As a preferred embodiment of the integrated planning method for provincial power grid wind-solar-hydro-thermal-storage based on coupling feature quantization described in this invention, the step of feeding back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updating includes: The rated energy storage capacity and rated energy storage power of each node are fed back to the group optimization algorithm. The group optimization algorithm and the simulation program are re-executed iteratively to obtain the re-solved installed capacity and capacity ratio. Based on the recalculated installed capacity and capacity ratio, the total energy storage capacity is determined and the energy storage site allocation is carried out. Calculate the relative change in installed capacity obtained during two consecutive iterations; If the relative change is less than the preset convergence difference of the iteration update, the iteration stops, and the power installed capacity, capacity ratio and rated energy storage capacity and rated power of each node corresponding to the current iteration update are output as an integrated planning scheme.
[0011] The beneficial effects of this preferred technical solution are as follows: This invention feeds back the rated capacity and rated power of energy storage to the group optimization algorithm to resolve the installed capacity and capacity ratio, and performs the determination and allocation of total energy storage capacity again, so that the power structure and energy storage configuration can be adapted to each other in the iterative process, avoiding structural mismatch due to unidirectional sequential determination; the relative change of installed capacity is used as the convergence criterion to ensure that the iterative update stops in time after the power structure and energy storage configuration tend to stabilize.
[0012] As a preferred embodiment of the integrated planning method for provincial power grid wind, solar, hydro, thermal, and energy storage based on coupling feature quantization described in this invention, the constraint boundary for setting the installed capacity optimization includes: Based on the wind-solar complementarity coefficient and the time-segmented peak shaving margin, power supply heterogeneity prediction is performed for each node; The power supply dissimilarity prediction includes: if the wind-solar complementarity coefficient of a node is lower than a preset complementarity threshold, and the number of time periods in which the peak-shaving margin is lower than the preset peak-shaving margin threshold exceeds the preset time period threshold, the node is marked as a node with high coupling demand, and a constraint range is applied to the wind power and photovoltaic installed capacity ratio of the node. Otherwise, the node is marked as a regular coupled node, and the ratio of wind power to photovoltaic installed capacity of the node is determined according to the iterative optimization process of the group optimization algorithm.
[0013] As a preferred embodiment of the provincial power grid integrated planning method based on coupling feature quantization described in this invention, the calculated set of coupling feature parameters between wind, solar, hydro, thermal power and energy storage includes: Based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage at each node in the planning area, calculate the wind power output coefficient, photovoltaic output coefficient, hydropower unit output constraint parameters and thermal power unit peak shaving depth parameters. The wind-solar complementarity coefficient is calculated based on the degree of peak misalignment between the wind power output coefficient and the photovoltaic output coefficient in the time dimension. Obtain real-time output data of hydropower units, and calculate the time-shaving peak margin of the hydropower group based on the output constraint parameters of the hydropower units and the real-time output data of the hydropower units. Calculate the marginal energy consumption benefit coefficient of energy storage based on the difference in the amount of electricity abandoned by the system before and after the change in energy storage capacity; The wind-solar complementarity coefficient, time-shaving margin, energy storage marginal absorption benefit coefficient, wind power output coefficient, photovoltaic power output coefficient, hydropower unit output constraint parameters, and thermal power unit peak shaving depth parameters are encapsulated into a set of coupled characteristic parameters.
[0014] As a preferred embodiment of the integrated planning system for provincial power grid wind, solar, hydro, thermal and energy storage based on coupling feature quantization described in this invention, it is characterized by including a parameter calculation module, a group optimization module, a simulation module, a capacity determination module, an allocation module and an output module. The parameter calculation module is used to calculate the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage. The group optimization module is used to set the constraint boundary for power supply capacity optimization based on the set of coupling feature parameters, and to generate candidate planning schemes within the constraint boundary using a group optimization algorithm. The simulation module is used to run a simulation program to simulate and solve candidate planning schemes, obtain operating costs and constraint violations, return the operating costs and constraint violations to the group optimization algorithm for iterative optimization, and output the installed scale and capacity ratio. The capacity determination module is used to determine the total energy storage capacity based on the installed capacity and capacity ratio. The allocation module is used to perform energy storage site allocation according to the total energy storage capacity to obtain the rated energy storage capacity and rated power; The output module is used to feed back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates and output an integrated planning scheme.
[0015] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of a method for integrated planning of wind, solar, hydro, thermal and energy storage in a provincial power grid based on coupling feature quantization.
[0016] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for integrated planning of wind, solar, hydro, thermal, and energy storage in a provincial power grid based on coupling feature quantization.
[0017] The beneficial effects of this invention are as follows: This invention transforms the coupling characteristics of multiple types of power sources into quantifiable planning model inputs, replacing the step-by-step determination of power source scale in existing technologies; it improves the feasibility of candidate planning schemes by predicting the mutuality of power sources at nodes and solving the problem through year-round time-series simulation; it achieves differentiated configuration by using energy storage capacity increment criteria and site priority indicators; and it enables the integrated planning scheme to be coordinated and consistent through iterative convergence of power source structure and energy storage configuration, thereby improving the utilization level of provincial power grids in terms of the complementary relationship and regulation capabilities of multiple types of power sources. Attached Figure Description
[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0019] Figure 1 The following is a flowchart of an integrated planning method for provincial power grid wind, solar, hydro, thermal and energy storage based on coupling feature quantization, provided as an embodiment of the present invention.
[0020] Figure 2 A flowchart of power source dissimilarity prediction is provided for a provincial power grid integrated planning method based on coupling feature quantization, which is an embodiment of the present invention.
[0021] Figure 3 The flowchart illustrates the determination of total energy storage capacity using a provincial power grid integrated wind, solar, hydro, thermal, and energy storage planning method based on coupling feature quantization, as provided in one embodiment of the present invention. Detailed Implementation
[0022] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.
[0023] Example 1, referring to Figure 1 As an embodiment of the present invention, a provincial power grid integrated planning method based on coupling feature quantization is provided, comprising: S1: Based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage, the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage is calculated.
[0024] S2: Set the constraint boundary for power supply capacity optimization based on the set of coupling feature parameters, and generate candidate planning schemes within the constraint boundary using a group optimization algorithm.
[0025] S3: Run the simulation program to simulate and solve the candidate planning scheme, obtain the operating cost and constraint violation amount, return the operating cost and constraint violation amount to the group optimization algorithm for iterative optimization, and output the installed scale and capacity ratio.
[0026] S4: Determine the total energy storage capacity based on the installed capacity and capacity ratio.
[0027] S5: Perform energy storage site allocation based on the total energy storage capacity to obtain the rated energy storage capacity and rated power.
[0028] S6: Feed back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates, and output an integrated planning scheme.
[0029] It should be noted that this invention transforms the output characteristics, complementary relationships, and marginal absorption effects of various types of power sources into quantifiable planning inputs by coupling characteristic parameter sets. Based on the prediction of the dissimilarity of node power sources, the criterion for increasing energy storage capacity, and the priority index for site deployment, the invention achieves coordinated iterative convergence of power source structure and energy storage configuration.
[0030] Example 2, refer to Figure 2 - Figure 3 This is a second embodiment of the present invention, which provides a provincial power grid integrated planning method for wind, solar, hydro, thermal and energy storage based on coupling feature quantization, including: Initialize the process, assuming the planned area contains a set of nodes. The set of time periods throughout the year is The length of the time period is taken Hours, total number of time periods .
[0031] In step S1, the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage is calculated, including steps S11~S15: S11: Based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage at each node in the planning area, calculate the wind power output coefficient, photovoltaic output coefficient, hydropower unit output constraint parameters and thermal power unit peak shaving depth parameters.
[0032] Calculate the wind power output factor by obtaining node data from the meteorological reanalysis dataset ERA5. Corresponding geographical location in time period Historical hourly wind speed data, with a time series length set to 10 years, to cover the variation range of different meteorological year types, including wet, normal, and dry years.
[0033] Substituting historical hourly wind speed data into the comprehensive power curve of the wind farm cluster, the theoretical output coefficient of a single wind turbine is obtained, expressed as: in, This represents the theoretical output coefficient of a single wind turbine unit. This is the combined power curve of the wind farm cluster. For nodes During the period Wind speed data.
[0034] It should be noted that the comprehensive power curve of the wind farm group is a piecewise function, and its expression is: in, This refers to the actual wind speed. To cut into wind speed, Rated wind speed, To cut off the wind speed, the specific value is determined by the model parameters of the wind turbine selected at the current node.
[0035] Considering the wake effect of the wind farm cluster and the availability of the units, the theoretical output coefficient of a single wind turbine is reduced to obtain the wind power output coefficient, which is expressed as: in, For nodes During the period The wind power output coefficient, This is the wake reduction factor, reflecting the shading effect of upstream turbines on downstream turbines. It is taken as 0.05~0.15 and is determined by the wind farm layout and the local prevailing wind direction. Unit availability reflects the periods of unavailability caused by equipment maintenance and failures. This was obtained by statistically analyzing historical data.
[0036] Furthermore, the photovoltaic output factor is calculated, and nodes are extracted from the ERA5 reanalysis dataset. Corresponding geographical location in time period Historical hourly total solar irradiance and surface temperature.
[0037] The expression for converting the total horizontal irradiance to the effective irradiance of the tilted surface of the photovoltaic module is: in, For nodes During the period Effective irradiance of the tilted surface of the photovoltaic module For nodes Corresponding geographical location in time period Historical hourly total solar horizontal irradiance This is the irradiance conversion coefficient for the tilted surface, and its value depends on the installation method of the photovoltaic module.
[0038] Considering the impact of temperature on photovoltaic module efficiency, the actual operating temperature of the module is calculated using the following expression: in, This refers to the actual operating temperature of the component. For nodes Corresponding geographical location in time period Surface temperature, The rated operating temperature of the component is 45~48℃, determined by the component model parameters.
[0039] Substituting the effective irradiance and the actual operating temperature of the module into the existing photovoltaic power output model, we obtain the theoretical power output coefficient of a single photovoltaic unit, expressed as: in, This represents the theoretical output coefficient of a single photovoltaic unit. The irradiance is taken as 1000 under standard test conditions. The temperature power coefficient is taken as 0.003~0.005, determined by the component model. This refers to the inverter efficiency.
[0040] Considering factors such as photovoltaic module degradation and dust accumulation, the theoretical output coefficient of a single photovoltaic unit is reduced to obtain the photovoltaic output coefficient, which is expressed as follows: in, For nodes During the period The photovoltaic output coefficient, This is the annual degradation correction factor for the modules, initially set at 0.97, decreasing by 0.5% annually thereafter, and determined by the module model and its lifespan. The dust reduction factor is 0.92 to 0.97, which is determined by local climate conditions and cleaning and maintenance frequency.
[0041] Furthermore, the output constraint parameters of the hydropower units are calculated, assuming the set of hydropower units is... For cascade hydropower stations During the period contribution Determined by the power generation flow rate and water head, the expression is: in, For hydroelectric generator units During the period Power generation capacity, For hydroelectric generator units The overall power generation efficiency, It is the acceleration due to gravity. For time period The head of the power generation water purification system, This refers to the power generation flow rate.
[0042] The recursive calculation of the reservoir's storage capacity should satisfy the water balance equation, expressed as: in, For reservoir exist Water storage volume during a certain period For reservoir The amount of water stored during a given period, For inbound flow, For the discharge flow rate, This is the length of the time period in seconds.
[0043] The water storage capacity of a reservoir should meet the storage limit, expressed as: in, The water storage capacity of the reservoir. This represents the minimum water storage capacity corresponding to the dead water level. This represents the maximum water storage capacity corresponding to the normal water storage level.
[0044] Reservoir capacity limits and water balance equations together serve as the output constraint parameters for hydropower units.
[0045] Furthermore, the peak-shaving depth parameters of the thermal power unit are calculated, assuming the thermal power unit is... The output of thermal power units Define the peak-shaving depth of thermal power units, constrained by minimum and maximum technical output. The ratio of the unit's adjustable range to its maximum output is expressed as: in, For thermal power units Peak-shaving depth, To the maximum output of the unit, Minimize the technical output of the generator unit.
[0046] S12: Calculate the wind-solar complementarity coefficient based on the degree of peak misalignment between the wind power output coefficient and the photovoltaic power output coefficient in the time dimension.
[0047] The physical essence of the wind-solar complementarity coefficient is to measure the degree to which wind power and solar power output simultaneously in time. If both frequently reach high output at the same time, it indicates strong synchronicity and weak complementarity; if their peak-shifting is significant, then their complementarity is strong.
[0048] Therefore, the complementarity coefficient can be defined as the proportion of synchronous output to the total synchronous output. First, calculate the total annual synchronous output, as expressed by: in, To ensure that the total annual output is synchronized, For time period The wind power output coefficient, For time period The photovoltaic output coefficient, This represents the annual average value of the photovoltaic power output coefficient. This represents the annual average value of the wind power output coefficient. For time period index, This represents the total number of time periods throughout the year.
[0049] Furthermore, the total synchronous output is calculated using the following expression: in, This refers to the total output power during synchronization.
[0050] Therefore, the wind-solar complementarity coefficient can be defined as follows: in, The wind-solar complementarity coefficient, It is a very small positive number, and its value is [value]. .
[0051] It should be noted that the closer the wind-solar complementarity coefficient is to 1, the lower the proportion of simultaneous wind and solar power output and the stronger the complementarity. The closer the wind-solar complementarity coefficient is to 0, the higher the synchronicity between the two and the weaker the complementarity.
[0052] S13: Obtain the real-time output data of the hydropower units, and calculate the time-sharing peak-shaving margin of the hydropower group based on the output constraint parameters of the hydropower units and the real-time output data of the hydropower units.
[0053] The time-of-use peak-shaving margin of a hydropower group depends on the difference between the current output and the maximum and minimum output, defining the nodes. Hydropower group during time period The upward and downward peaking margins are expressed as follows: in, For nodes Hydropower group during time period The upward peaking margin, For nodes Hydropower group during time period Downward peaking margin, For nodes A collection of hydroelectric power units, and The units Maximum and minimum technical output at the current water head For the unit During the period The actual power generation capacity.
[0054] S14: Calculate the marginal energy storage absorption benefit coefficient based on the difference in the amount of abandoned electricity in the system before and after the change in energy storage capacity.
[0055] The marginal absorption benefit coefficient of energy storage is defined as the additional amount of wind and solar power curtailment that can be absorbed for each additional unit of energy storage capacity. The expression is: in, This represents the marginal utilization benefit coefficient of energy storage. To increase the reduction in the annual amount of abandoned electricity before and after energy storage, For the increment of the rated capacity of energy storage, The larger the value, the more effective energy storage is in reducing power curtailment under the current power structure.
[0056] S15: Encapsulate the wind-solar complementarity coefficient, time-shaving peak margin, energy storage marginal absorption benefit coefficient, wind power output coefficient, photovoltaic power output coefficient, hydropower unit output constraint parameters and thermal power unit peak shaving depth parameters into a set of coupled characteristic parameters.
[0057] In step S2, setting the constraint boundary for optimizing installed capacity includes performing power supply reciprocity prediction on each node based on the wind-solar complementarity coefficient and the time-of-use peak-shaving margin. Performing power supply reciprocity prediction includes steps S21 to S22: S21: If the wind-solar complementarity coefficient of a node is lower than the preset complementarity threshold, and the number of time periods in which the peak-shaving margin is lower than the preset peak-shaving margin threshold exceeds the preset time period threshold, the node will be marked as a node with high coupling demand, and a constraint range will be applied to the wind power and photovoltaic installed capacity ratio of the node.
[0058] Specifically, the preset complementarity threshold is taken as follows: The preset peak-shaving margin threshold is based on the current total installed capacity of hydropower at the node. With preset peak shaving margin warning coefficient The product is represented as, The value is set to 0.3, which means the preset peak shaving margin threshold is... The preset time period threshold is set to The statistics cover peak load periods throughout the year.
[0059] If node Wind-solar complementarity coefficient Below Furthermore, during the peak load period throughout the year, the upward peak regulation margin of hydropower at this node is lower than... If the number of time periods exceeds 200 hours, the node is marked as a high-coupling-demand node, and a constraint range is applied to the wind power installed capacity ratio of that node, expressed as: in, To constrain the upper limit of the interval, This is to constrain the lower limit of the interval.
[0060] S22: Otherwise, the node is marked as a regular coupled node, and the wind power and photovoltaic installed capacity ratio of the node is determined according to the iterative optimization process of the group optimization algorithm.
[0061] The ratio between wind power and photovoltaic (PV) installed capacity at conventional coupled nodes is not subject to any constraint range restrictions. It only requires that the upper and lower limits of the respective physical exploitable capacity of wind power and PV be met. The optimal value of the wind-PV ratio at each node is autonomously determined by the swarm optimization algorithm during the iterative optimization process based on the fitness evaluation results of candidate planning schemes. Figure 2 As shown.
[0062] Furthermore, in step S2, the generation of candidate planning schemes within the constraint boundary using a swarm optimization algorithm includes the following steps: The population optimization algorithm used in this invention is the immune ant colony algorithm. The algorithm flow of the immune ant colony algorithm includes: Initialization operation, setting population size Memory capacity Maximum number of iterations Crossover probability Probability of mutation and diversity threshold .
[0063] Candidate planning schemes that satisfy the constraint boundaries are randomly generated as the initial antibody population.
[0064] The fitness of the initial antibody population is calculated. The fitness value consists of the running cost and penalty term returned by the simulation program, expressed as follows: in, For planning scheme fitness value, As a maximum penalty factor, In order to plan Next, calculate the sum of the operating costs and penalty terms obtained from the full-year simulation. The total cost of power supply installation investment. This represents the expected annual power shortage for the system. To allow for the maximum power shortage, As the upper limit for carbon emissions, This represents the system's total annual carbon emissions.
[0065] It should be noted that, whether in the initial population or the offspring population generated in subsequent iterations, the swarm optimization algorithm itself is only responsible for encoding decision variables and searching the feasible solution space; it does not directly possess the ability to perform cost accounting and constraint verification for candidate solutions. For each candidate planning scheme, decision variables (including wind power installed capacity, photovoltaic installed capacity, and flexible retrofitting methods for thermal power units at each node) must be used as input parameters, and a simulation program must be run to perform a time-series simulation of 8760 hours throughout the year. After the inner simulation program completes the solution, it returns the total annual operating cost and constraint violation amount under the candidate scheme to the swarm optimization algorithm, which then calculates the fitness value based on this.
[0066] The most fit first Each antibody is stored in a memory bank and reserved as an elite.
[0067] Calculate antibody concentration and stimulation level, antibody concentration Using antibodies The reciprocal measure of the average Euclidean distance to other antibodies in the population.
[0068] The expression for the degree of motivation is: in, Antibody The incentive value, The sum of total cost and penalty items. It is a concentration regulator used to promote the selection of low-concentration antibodies.
[0069] Based on the incentive level, a roulette wheel selection is used to form a mating pool. The specific steps include: Calculate the selection probability, assuming the current population has a total of The first antibody, the first The activation level of each antibody is The sum of population motivation is calculated using the following expression: in, This represents the total current population incentive level.
[0070] Then the first The probability expression for an antibody being selected is: Obviously, the higher the level of stimulation of the antibody, The higher the value, the greater the chance of being selected.
[0071] Roulette selection, The interval is based on the probability of each antibody. Divided into There are several continuous sub-intervals, each with a length equal to the selection probability of the corresponding antibody. The sector area occupied by the antibody on the roulette wheel is proportional to the antibody activation level. In practice, a total of [number] sub-intervals are executed. Each independent choice, each time in A uniformly random number is generated for each interval. The antibody whose sub-interval the uniformly random number falls into is selected and entered into the mating pool. The same antibody is allowed to be selected multiple times.
[0072] Repeat the above operation in the output mating pool. Next, get included The mating pool of antibodies serves as the input for the next cross-operation. Individuals with high stimulation in the mating pool will appear multiple times with a high probability, thereby passing on superior genes to the next generation.
[0073] Perform a crossover operation, pairing antibodies in the mating pool together according to probability. Perform arithmetic or discrete crossover; use simulated binary crossover for continuous variables and uniform crossover for integer variables.
[0074] Perform mutation operations, according to probability. Gaussian mutations were performed on each gene locus.
[0075] Perform a population update, merging parent populations, crossover offspring, and memory bank antibodies, reordering them by fitness and concentration, and selecting the top [population]. Each antibody forms a new generation of population.
[0076] Set a termination condition if the maximum number of iterations is reached. or continuous The improvement in optimal fitness is less than the threshold. The antibody with the lowest fitness in the memory is output as the optimal planning scheme; otherwise, return to step 2.
[0077] The thresholds in the above steps were all set based on historical experience.
[0078] In step S3, running the simulation program to simulate and solve the candidate planning scheme includes steps S31 to S33: It should be noted that each candidate planning scheme output by the outer-layer immune ant colony algorithm needs to undergo a time-series simulation of 8760 hours throughout the year through the inner-layer running simulation to evaluate the operating cost and constraint satisfaction of the scheme. To incorporate hydropower nonlinear constraints into a unified optimization framework, this invention employs a piecewise linearization method to process the relevant nonlinear terms. This piecewise linearization transforms the simulation program into a standard mixed-integer linear programming (MILP) problem, which can be solved using mature commercial solvers.
[0079] S31: Based on the set of coupling feature parameters, establish the operational constraints that the candidate planning scheme should satisfy.
[0080] The inner-layer operation simulation must meet the following operational constraints: (1) at any time The total power generation of the system equals the total load power, expressed as: in, For nodes During the period Wind power output, For nodes During the period Photovoltaic power output, For nodes A collection of thermal power units, For nodes During the period The load power, The total number of nodes. For nodes During the period The energy storage discharge power, For nodes During the period Energy storage charging power.
[0081] (2) Operating constraints of hydropower units: The output of hydropower units must meet the technical output range under the current water head, expressed as: in, Indicates hydroelectric power unit During the period The minimum power generation capacity, Indicates hydroelectric power unit During the period The maximum power generation capacity.
[0082] (3) Peak shaving depth constraint for thermal power: The output of thermal power units must be within the allowable range of peak shaving depth, expressed as: in, To provide power to thermal power units, This indicates the maximum output of the thermal power unit. This indicates the frequency regulation depth of a thermal power unit.
[0083] S32: Within the entire time series, with the goal of minimizing operating costs, and under the premise of satisfying the operating constraints, solve the candidate planning scheme and output the operating cost.
[0084] Specifically, the simulation program aims to minimize the system's operating cost, and solves for the time-series operation plan for the entire year (8760 hours) under a given planning scheme X. The objective function expression is: in, For the annual cost of thermal power fuel, The total penalty cost for abandoning wind, solar, and hydropower throughout the year.
[0085] S33: If there are unmet operational constraints, accumulate the deviations that exceed the corresponding constraint limits to obtain the constraint violation amount corresponding to the candidate planning scheme, and return the operational cost and the constraint violation amount to the group optimization algorithm.
[0086] In step S4, determining the total energy storage capacity includes steps S41 to S44: S41: Starting with zero energy storage capacity as the initial value, the energy storage capacity is increased step by step according to the preset capacity increment step. The installed capacity and capacity ratio and the energy storage capacity after each increment are input into the running simulation program to obtain the annual abandoned power of each node. The annual abandoned power of each node is summed to obtain the total annual abandoned power.
[0087] The overall process for determining the total energy storage capacity is as follows: Figure 2 As shown, specifically, let the number of iterations... Initial energy storage capacity Set the incremental step size of energy storage capacity In this embodiment, 100MWh is used.
[0088] In the In the next iteration, let: in, For the first Energy storage capacity at the next iteration For the first Energy storage capacity at the next iteration.
[0089] The wind power installed capacity of each node determined in step S3 Photovoltaic installed capacity Flexibility retrofitting scheme for thermal power units and peak shaving depth after retrofitting With the energy storage capacity after the increase The simulation program is run by inputting common data to solve the time-series operation plan for 8760 hours throughout the year, and to collect statistics for each node. Waste of electricity throughout the year The total annual power consumption is obtained by summing up the total amount of power wasted at each node throughout the year. The expression is: S42: Divide the difference between the total annual abandoned electricity before and after two consecutive increases by the capacity increase step size to obtain the marginal energy storage absorption benefit.
[0090] The expression for the marginal absorption benefit of energy storage is: in, Indicates the first The marginal absorption benefit of energy storage in the next iteration For the first The total amount of electricity wasted throughout the year in the next iteration. For the first The total amount of electricity wasted throughout the year in the next iteration. The larger the value, the more effective the addition of energy storage will be in reducing power curtailment under the current power structure.
[0091] S43: If the marginal energy storage absorption benefit is greater than or equal to the preset marginal energy storage benefit threshold, continue to increase the energy storage capacity.
[0092] Set a threshold for the marginal benefit of energy storage. Its value is determined from the perspective of the economic balance between energy storage investment costs and curtailment penalty costs. The annualized investment cost required to increase unit energy storage capacity is... The amount of electricity wasted that this unit capacity can reduce during the entire year's operation is The resulting economic benefits are Only when the annual revenue from reducing curtailment is not less than the annual cost of energy storage investment is increasing energy storage deployment economically justifiable, as expressed in the following formula: in, The penalty cost per unit of abandoned electricity.
[0093] Therefore, the marginal benefit threshold can be obtained. The theoretical expression is: in, Let $\frac{ ... The service life is Year, discount rate Then the expression for the annualized investment cost per unit capacity of energy storage is: When the investment cost of energy storage units decreases or the cost of curtailment penalties increases... A corresponding decrease means that a lower marginal absorption capacity is needed to support the economic viability of energy storage investment, thereby encouraging the allocation of larger capacity energy storage; conversely, As energy levels rise, the optimal capacity for energy storage configuration will shrink.
[0094] In this embodiment, calculations are performed based on typical parameters. Values , 10, The value is 6%. The value is taken as 500, and the final calculation is as follows: That is, the annual amount of abandoned electricity consumed per MWh of newly added energy storage capacity is less than When the capacity reaches MWh, no further energy storage will be added.
[0095] like This indicates that increasing the allocation of energy storage is still economically reasonable at present, making Then return to step S41 to continue increasing the energy storage capacity.
[0096] S44: If the marginal energy storage absorption benefit is less than the preset marginal energy storage benefit threshold, stop increasing the capacity and use the energy storage capacity before the current increase as the total energy storage capacity.
[0097] like This indicates that the economic benefits of continuing to increase energy storage cannot cover the corresponding investment costs. Therefore, the increase should be stopped, and the energy storage capacity before this increase should be taken as the recommended configuration value for the total energy storage capacity. The expression is: in, This represents the final recommended configuration value for the total energy storage capacity. For the first Rated energy storage capacity at the next iteration.
[0098] It should be noted that in practical applications, it is recommended to calculate the baseline threshold using the cost parameters of the current year, and then adjust it based on the sensitivity of the scenario assumptions. Different provincial power grids can combine their own cost and policy data to adjust the threshold accordingly. Calibration is performed; in this embodiment, the following is taken: These are reference values estimated based on typical parameters, and can be adjusted according to actual conditions in specific applications.
[0099] In step S5, the energy storage deployment allocation includes steps S51 to S54: S51: The ratio of the annual abandoned power of each node to the total annual abandoned power is taken as the abandoned power ratio of each node.
[0100] Specifically, for nodes The proportion of abandoned electricity The calculation expression is: in, For nodes Annual power wastage Indicates the first During the subsequent iteration of energy storage capacity increment, the total annual power curtailment for all nodes in the entire system is obtained from the operational simulation program in step S4. Power curtailment percentage Reflects the nodes The larger the proportion of the total amount of curtailed electricity in the entire system, the more prominent the curtailment problem at that node, and the greater the urgency of configuring energy storage.
[0101] S52: Obtain the average upward peak shaving margin of each node during the peak load period of the whole year, and use the ratio of the average upward peak shaving margin to the maximum peak shaving margin as the peak shaving margin ratio of each node.
[0102] Specifically, based on the nodes defined in step S13 Hydropower group during time period Upward peaking margin Statistics on peak load periods throughout the year In this embodiment, the peak load period is defined as the period when the daily load factor is higher than 0.85, and the calculation node... Average upward peak shaving margin during peak load periods The expression is: in, The peak load margin ratio represents the total number of peak load periods throughout the year. The calculation expression is: in, The peak shaving margin ratio is the maximum average upward peak shaving margin across all nodes. The value is between 0 and 1. The smaller the value, the less the hydropower peak-shaving capacity of the node is, and the more it needs to be supported by energy storage.
[0103] It should be noted that the maximum technical output of the hydropower unit and minimum technical output It varies with the water head. The upward peak-shaving margin reflects the space that the hydropower unit can increase its output under the current operating conditions. The smaller this space is, the closer the hydropower regulation capacity is to the upper limit, and the greater the peak-shaving pressure the system faces.
[0104] S53: Based on the ratio of abandoned electricity to peak shaving margin of each node, the priority index of energy storage deployment for each node is obtained by weighting according to the preset weight coefficient.
[0105] Specifically, define nodes Energy storage point priority indicators By the proportion of abandoned electricity Complementary quantity to peak shaving margin ratio The weighted summation yields the expression: in, For nodes The peak shaving margin ratio.
[0106] Right now: in, This is the curtailment weighting factor. For peak shaving weighting coefficients, satisfying , The higher the value, the higher the priority of configuring energy storage on the node.
[0107] and The baseline ratio is set to and The proportion is expressed as: In lack In the case of detailed data, it can be approximated as It equals the cold start cost of thermal power units divided by the duration of a typical peak-shaving gap, or simply take... This is because insufficient peak shaving often results in greater losses than simply curtailing electricity.
[0108] From this, we can deduce that The baseline value is approximately , Approximately In this embodiment, we take... , .
[0109] S54: Based on the energy storage deployment priority index, allocate the total energy storage capacity to each node, and determine the rated energy storage power of each node based on the energy storage capacity allocated to each node and the preset charging and discharging time.
[0110] Specifically, according to Sort the nodes in descending order of energy storage capacity, and calculate the total energy storage capacity determined in step S44. The allocation is sequentially distributed to each node until the total amount is allocated. The allocation logic is as follows: For the node with the highest priority... The allocated capacity is ,in The upper limit of energy storage capacity for nodes after considering factors such as site conditions and access conditions; for nodes with lower priority... No more than the remaining capacity shall be allocated Part of it, up to the total energy storage capacity. Allocation complete, or all configurable energy storage nodes have been allocated; the rated energy storage power allocated to each node. Energy storage capacity allocated according to the current node With preset charging and discharging time Confirmed, the expression is: in, The preset charging and discharging time of the energy storage system is taken in this embodiment. Hours or The specific value for the hour depends on the application scenario and technology type of the energy storage. For example, power-type energy storage takes 2 hours, and energy-type energy storage takes 4 hours.
[0111] It should be noted that if a node is allocated zero energy storage capacity during the allocation process, that node will not be configured with energy storage facilities. After allocation is completed, each node... The energy storage configuration results are in binary form. This indicates that it serves as the input variable for the iterative feedback in step S6.
[0112] In step S6, feeding back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates includes steps S61-S63: S61: Feed back the rated energy storage capacity and rated energy storage power of each node to the group optimization algorithm. The group optimization algorithm and simulation program are re-executed iteratively to obtain the re-solved installed capacity and capacity ratio. Based on the re-solved installed capacity and capacity ratio, the total energy storage capacity is determined and the energy storage site is allocated.
[0113] Specifically, after step S5 is completed, each node The energy storage configuration results are in binary form. It means that will The feedback is sent to the immune ant colony algorithm in step S2 as known input parameters for running the simulation program.
[0114] The variables passed from S2 to S3 and subsequent steps include: Wind power installed capacity at each node ; Photovoltaic installed capacity at each node ; Whether each thermal power unit has undergone flexibility modifications and the resulting peak-shaving depth. .
[0115] The variables that S5 feeds back to S2 include: Rated energy storage capacity of each node ; Rated power of energy storage at each node .
[0116] Steps S3, S4, and S5 provide the power structure and optimize the energy storage configuration based on it; the energy storage configuration result in S5 changes the net load characteristics and power curtailment distribution of each node, and the group optimization algorithm re-optimizes the power structure.
[0117] In each iteration, the rated energy storage capacity of each node output by S5 is... and rated power As known parameters, the objective function and constraints from step S2 are substituted into the algorithm, and the population initialization, fitness evaluation, selection, crossover, mutation, and population update processes of the immune ant colony algorithm are re-executed to obtain a new round of power generation capacity and capacity ratio. Based on this, the total energy storage capacity determination in step S4 and the energy storage site allocation in step S5 are executed again, forming a complete iterative update.
[0118] S62: Calculate the relative change in installed capacity obtained during two adjacent iterations.
[0119] Using the relative change magnitude as the convergence criterion, for the th The power supply installation scheme after the next iteration and the The solution after the second iteration Calculate the relative change in wind power installed capacity. The expression is: Furthermore, the relative change in photovoltaic installed capacity is calculated. The expression is: in, and The first After the second iteration, the node The installed capacity of wind power and photovoltaic power, and The first The total installed capacity of wind power and photovoltaic power in the entire system after each iteration is taken as the maximum relative change as the iteration deviation for this round: in, This represents the maximum value of the relative change.
[0120] S63: If the relative change is less than the preset iteration update convergence difference, stop the iteration and output the power installed capacity, capacity ratio and the rated capacity and rated power of each node as an integrated planning scheme corresponding to the current iteration update.
[0121] Set a preset iterative update convergence difference In this embodiment, .when When the iteration is considered to have converged, the power source obtained at this time is... The energy storage solution is the integrated optimal planning solution. Stop the iteration and output the result corresponding to this iteration update: Wind power installed capacity at each node ; Photovoltaic installed capacity at each node ; Flexible retrofitting scheme for thermal power units and peak shaving depth after retrofitting ; Rated energy storage capacity of each node ; Rated power of energy storage at each node .
[0122] The maximum number of iterations is set to Under normal convergence conditions, the maximum number of iterations is usually 5 to 8 iterations, and 15 iterations provides sufficient margin.
[0123] If executed The condition was still not satisfied after that. The convergence conditions are handled in the following three cases: Scenario 1: If in the last 3 iterations exist The fluctuations indicate that the scheme is close to stabilization, with only minor oscillations. At this point, the arithmetic average of the installed capacity of each power source obtained from the last three iterations is taken as the final recommended scheme.
[0124] Scenario 2: If exist If the total cost of each iteration fluctuates repeatedly and the difference between the total costs of each iteration does not exceed 3%, then the iteration with the lowest total cost is selected as the final recommended solution.
[0125] Scenario 3: If If the number of iterations continues to increase, the total cost fluctuates by more than 5%, or the energy storage capacity jumps between zero and a maximum value at a certain node during the iteration process, it is determined to be an iteration divergence. At this time, it is necessary to return to step S2, adjust the wind-solar complementarity coefficient threshold and the preset peak-shaving margin warning coefficient, relax some hard constraints, and restart the iteration.
[0126] Example 3 is the third embodiment of the present invention. This embodiment provides a provincial power grid wind-solar-hydro-thermal-storage integrated planning system based on coupling feature quantization, including a parameter calculation module, a group optimization module, a simulation module, a capacity determination module, an allocation module, and an output module. The parameter calculation module is used to calculate the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage. The group optimization module is used to set the constraint boundary for power supply capacity optimization based on the set of coupling feature parameters, and to generate candidate planning schemes within the constraint boundary using a group optimization algorithm. The simulation module is used to run simulation programs to simulate and solve candidate planning schemes, obtain operating costs and constraint violations, return the operating costs and constraint violations to the group optimization algorithm for iterative optimization, and output the installed scale and capacity ratio. The capacity determination module is used to determine the total energy storage capacity based on the installed capacity and capacity ratio. The allocation module is used to perform energy storage site allocation according to the total energy storage capacity to obtain the rated energy storage capacity and rated power. The output module is used to feed back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates and output an integrated planning scheme.
[0127] 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 preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.
[0128] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that: If the aforementioned functions 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, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0129] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.
[0130] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.
[0131] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
Claims
1. A provincial power grid wind, light, water, fire and storage integrated planning method based on coupling characteristics, characterized by: include, Based on the obtained power output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage, the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage is calculated. Based on the set of coupling feature parameters, the constraint boundary for optimizing power supply installed capacity is set, and a group optimization algorithm is used to generate candidate planning schemes within the constraint boundary. The simulation program is run to simulate and solve the candidate planning schemes, and the operating cost and constraint violation amount are obtained. The operating cost and constraint violation amount are returned to the group optimization algorithm for iterative optimization, and the installed scale and capacity ratio are output. The total energy storage capacity is determined based on the installed capacity and capacity ratio. Based on the total energy storage capacity, energy storage site allocation is performed to obtain the rated energy storage capacity and rated power. The rated capacity and rated power of energy storage are fed back to the group optimization algorithm for iterative updates, and an integrated planning scheme is output.
2. The provincial power grid wind, light, water, fire and storage integrated planning method based on coupling feature quantization according to claim 1, characterized in that: The process of running the simulation program to simulate and solve the candidate planning schemes includes... Based on the set of coupling feature parameters, establish the operational constraints that the candidate planning scheme should satisfy; Within the entire year time series, with the goal of minimizing operating costs, and under the premise of satisfying the aforementioned operating constraints, the candidate planning scheme is solved, and the operating cost is output. If a candidate planning scheme does not meet the operational constraints, the deviation exceeding the corresponding constraint limit is accumulated to obtain the constraint violation amount corresponding to the candidate planning scheme. The operational cost and the constraint violation amount are then returned to the population optimization algorithm.
3. The method of claim 2, wherein the method is based on the coupling characteristics of the wind, solar, water, and thermal power and storage. The determination of the total energy storage capacity includes, Starting with zero energy storage capacity as the initial value, the energy storage capacity is gradually increased according to the preset capacity increment step. The installed capacity and capacity ratio, along with the energy storage capacity after the current increment, are input into the operation simulation program to obtain the annual abandoned power of each node. The annual abandoned power of each node is summed to obtain the total annual abandoned power. Divide the difference in the total annual abandoned electricity before and after two consecutive increases by the capacity increase step size to obtain the marginal energy storage absorption benefit; If the marginal energy storage absorption benefit is greater than or equal to the preset marginal energy storage benefit threshold, the energy storage capacity will continue to increase. If the marginal energy storage absorption benefit is less than the preset marginal energy storage benefit threshold, the increment stops, and the energy storage capacity before the current increment is taken as the total energy storage capacity.
4. The provincial power grid wind, light, water, fire and storage integrated planning method based on coupling feature quantization according to claim 3, characterized in that: The execution of energy storage deployment and allocation includes, The ratio of the annual abandoned power of each node to the total annual abandoned power is taken as the abandoned power percentage of each node. Obtain the average upward peak shaving margin of each node during the peak load period of the whole year, and use the ratio of the average upward peak shaving margin to the maximum peak shaving margin as the peak shaving margin ratio of each node. Based on the ratio of abandoned electricity to peak shaving margin of each node, the priority index of energy storage deployment for each node is obtained by weighting according to the preset weighting coefficient. Based on the energy storage deployment priority index, the total energy storage capacity is allocated to each node, and the rated energy storage power of each node is determined according to the energy storage capacity allocated to each node and the preset charging and discharging time.
5. The provincial power grid wind, light, water, fire and storage integrated planning method based on coupling feature quantization according to claim 4, characterized in that: The step of feeding back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates includes... The rated energy storage capacity and rated energy storage power of each node are fed back to the group optimization algorithm. The group optimization algorithm and the simulation program are re-executed iteratively to obtain the re-solved installed capacity and capacity ratio. Based on the recalculated installed capacity and capacity ratio, the total energy storage capacity is determined and the energy storage site allocation is carried out. Calculate the relative change in installed capacity obtained during two consecutive iterations; If the relative change is less than the preset convergence difference of the iteration update, the iteration stops, and the power installed capacity, capacity ratio and rated energy storage capacity and rated power of each node corresponding to the current iteration update are output as an integrated planning scheme.
6. The provincial power grid wind, light, water, fire and storage integrated planning method based on coupling feature quantization according to claim 5, characterized in that: The constraints for optimizing the installed capacity include, Based on the wind-solar complementarity coefficient and the time-shaving peak margin, power supply heterogeneity prediction is performed for each node; The power supply dissimilarity prediction includes: if the wind-solar complementarity coefficient of a node is lower than a preset complementarity threshold, and the number of time periods in which the peak-shaving margin is lower than the preset peak-shaving margin threshold exceeds the preset time period threshold, the node is marked as a node with high coupling demand, and a constraint range is applied to the wind power and photovoltaic installed capacity ratio of the node. Otherwise, the node is marked as a regular coupled node, and the ratio of wind power to photovoltaic installed capacity of the node is determined according to the iterative optimization process of the group optimization algorithm.
7. The provincial power grid wind, light, water, fire and storage integrated planning method based on coupling feature quantization according to claim 6, characterized in that: The calculated set of coupling characteristic parameters between wind, solar, hydro, thermal power and energy storage includes: Based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage at each node in the planning area, calculate the wind power output coefficient, photovoltaic output coefficient, hydropower unit output constraint parameters and thermal power unit peak shaving depth parameters. The wind-solar complementarity coefficient is calculated based on the degree of peak misalignment between the wind power output coefficient and the photovoltaic output coefficient in the time dimension. Obtain real-time output data of hydropower units, and calculate the time-shaving peak margin of the hydropower group based on the output constraint parameters of the hydropower units and the real-time output data of the hydropower units. Calculate the marginal energy consumption benefit coefficient of energy storage based on the difference in the amount of abandoned electricity in the system before and after the change in energy storage capacity; The wind-solar complementarity coefficient, time-shaving margin, energy storage marginal absorption benefit coefficient, wind power output coefficient, photovoltaic power output coefficient, hydropower unit output constraint parameters, and thermal power unit peak shaving depth parameters are encapsulated into a set of coupled characteristic parameters.
8. A provincial power grid wind-solar-hydro-thermal-storage integrated planning system based on coupling feature quantization, applying a provincial power grid wind-solar-hydro-thermal-storage integrated planning method based on coupling feature quantization according to any one of claims 1-7, characterized in that, It includes a parameter calculation module, a population optimization module, a simulation module, a capacity determination module, an allocation module, and an output module; The parameter calculation module is used to calculate the set of coupling characteristic parameters of wind, solar, hydro, thermal power and energy storage based on the obtained output time series data and operation constraint data of wind, solar, hydro, thermal power and energy storage. The group optimization module is used to set the constraint boundary for power supply capacity optimization based on the set of coupling feature parameters, and to generate candidate planning schemes within the constraint boundary using a group optimization algorithm. The simulation module is used to run a simulation program to simulate and solve candidate planning schemes, obtain operating costs and constraint violations, return the operating costs and constraint violations to the group optimization algorithm for iterative optimization, and output the installed scale and capacity ratio. The capacity determination module is used to determine the total energy storage capacity based on the installed capacity and capacity ratio. The allocation module is used to perform energy storage site allocation according to the total energy storage capacity to obtain the rated energy storage capacity and rated power; The output module is used to feed back the rated energy storage capacity and rated power to the group optimization algorithm for iterative updates and output an integrated planning scheme.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of any one of claims 1 to 7 of the integrated planning method for provincial power grid wind, solar, hydro, thermal and storage based on coupling feature quantization.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of any one of the claims 1 to 7: a provincial power grid integrated planning method based on coupling feature quantization for wind, solar, hydro, thermal and energy storage.
