39 results about "Long term planning" patented technology

The invention discloses a new energy medium and long term stochastic programming method and system coupled with an electro-hydrogen water regulation power supply, and the method comprises the steps: building a power supply planning model with the minimum planning operation cost as an optimization target; bringing the new energy power supply and energy storage adjusting equipment operation model and the new energy consumption rate upper and lower limit constraint expression into a power supply planning model; in consideration of the randomness of fluctuation at two sides of a source and a load in power supply planning, based on the obtained power system operation scene set S and the power supply planning model, dividing into an investment decision-making layer and an operation simulation layer according to a time period influenced by a decision, and constructing a power supply planning two-stage stochastic optimization model based on a typical scene; and solving the power supply planning two-stage stochastic optimization model under a medium and long term planning framework, and determining the investment planning installed capacity of the adjusting power supply and the new energy in the planning level year. According to the invention, economy of medium and long term planning and power supply capacity configuration of new energy can be improved, and reasonable consumption and flexible adjustment of new energy electric power are promoted.

The invention discloses a power system distribution robust scheduling optimization method based on optimal configuration, and relates to the field of power system robust scheduling, and the method comprises the steps: carrying out the coupling modeling of a power transmission network extension plan, a DPFC and an energy storage device, and solving a model to generate an optimal configuration scheme; constructing an uncertainty set capable of being dynamically updated, and obtaining a day-ahead scheduling scheme by adopting a dual-stage distribution robust optimization method in combination with the optimal configuration scheme; on the basis of a day-ahead scheduling scheme, a hybrid robust and adaptive model prediction control framework is utilized, and a real-time control parameter of the DPFC and a rapid power adjustment instruction of energy storage are generated through rolling optimization; according to the invention, by combining optimal configuration, dual-stage distribution robust optimization and hybrid robust adaptive model prediction control, collaborative optimization of long-term planning and short-term scheduling is realized, and through real-time model parameter updating and dynamic uncertainty processing, real-time scheduling is realized. The problems that a scheduling scheme is insufficient in robustness, and economical efficiency and real-time adaptability are difficult to consider are solved.

The application discloses a kind of based on Copula function's urban water, energy and environmental system optimization decision management method, comprising: S1. the Copula joint distribution function of water environment capacity and available energy amount in urban water is constructed;S2. the resource optimization allocation and joint risk management model of urban water, energy and environmental system is established;S3. the resource optimization allocation and joint risk management model of urban water, energy and environmental system is solved;The method realizes the optimization allocation and joint risk management of urban water-energy-environment system water and energy under uncertain conditions.Provide urban water-energy-environment system resource optimization allocation scheme and long-term planning scheme of sewage treatment process under different risk scenario combinations on the basis of maximum economic benefit, and help decision makers better realize the trade-off between joint default risk and system benefit, to realize urban risk controllable and water-energy-environment collaborative development provides scientific method.

The invention relates to the technical field of integrated energy systems, and particularly provides a multi-energy-flow scheduling method and system for a regional integrated energy system, and the method comprises the steps: S1, carrying out the unified modeling of a DC micro-grid, a heat supply network and a natural gas network based on a circuit comparison method, and obtaining a network model of each energy network; s2, constructing a direct-current micro-grid island hierarchical control strategy; and S3, according to the state parameters of the regional integrated energy system, performing dynamic load flow calculation on the direct-current microgrid under the island hierarchical control strategy based on a decomposition load flow method and the network model of each energy network, performing steady-state load flow calculation on the heat supply network and the natural gas network, and generating a scheduling instruction, so that multi-energy-flow coupling response can be accurately captured, and the scheduling efficiency is improved. According to the method, the model inconsistency error is reduced, the unit calculation burden is reduced, the expandability and fault tolerance of the system are improved, and high-precision support is provided for optimal scheduling and long-term planning.

The application provides a renewable energy supply-distribution-demand-storage system space-time coordination configuration method, relates to the technical field of intelligent energy, and comprises the following steps: acquiring data of multiple regions; calculating time mismatch degrees, space mismatch degrees and space-time coupling mismatch degrees of the regions; decomposing an optimization problem into a long-term planning layer, a medium-term scheduling layer and a short-term real-time layer in a time dimension; constructing multi-objective optimization functions of the time layers; decomposing the optimization problems of the time layers in a space dimension; alternately solving local optimization sub-problems and global coordination problems of the regions by using a distributed iteration method; outputting a configuration result of a current time layer when the algorithm converges; executing a decision of a first time period by each time layer and taking the decision as a constraint condition of a next time layer to obtain power generation installed capacities, power transmission line capacities, energy storage capacities and operation strategies of the regions. The application can improve a renewable energy consumption rate and reduce system operation costs.

The invention provides a power supply and power transmission channel capacity optimization method, system, equipment and medium, and the method comprises the steps: carrying out the iteration solving of a long-term capacity planning model and a short-term operation simulation model in a double-layer model through a double-layer dynamic iteration mechanism based on a new energy and load typical power curve of a set region, and obtaining a new energy and load typical power curve; obtaining a power supply and power transmission channel capacity optimization configuration scheme; the long-term capacity planning model is constructed on the basis of optimization targets of the minimum total power supply cost in a planning period, the highest power supply reliability under the uncertainty of new energy power generation and the maximum new energy consumption amount; the short-term operation simulation model considers changes of power generation cost of a power supply in a power system, new energy power abandoning penalty cost and load shedding penalty cost, considers multiple optimization targets, deeply couples medium and long-term capacity planning with short-term operation simulation, can adapt to new energy fluctuation and multi-time scale coupling requirements, and improves the simulation efficiency. And thus, medium-and-long-term planning requirements are met.

The invention discloses an intelligent power grid dynamic planning method and system based on multi-dimensional space-time coupling, and belongs to the technical field of power grid planning, and the method comprises the following steps: carrying out original data collection, carrying out multi-dimensional modeling, and carrying out dynamic planning; according to the method, short-term scheduling and long-term planning can be dynamically coordinated through multi-dimensional modeling, cross-regional resource complementation can also be achieved, insufficient or waste of local resources is reduced, and the dynamic characteristics of the power grid are accurately captured through high-resolution spatio-temporal data. According to the method, the uncertainty of wind and light output prediction errors, load fluctuation and the like can be effectively handled, the model can be dynamically planned, flexible resources can be reserved, extreme weather or equipment faults can be handled, time and space separation is broken through, resource utilization efficiency maximization is achieved, and overall economical efficiency, reliability and low-carbon performance are cooperatively improved.

The application discloses a kind of carbon constraints under regional power system planning collaborative optimization method and system, method includes: the unit product cost of each department technical path of calculation terminal, the technical path occupancy rate is predicted using Logit selection model and inventory replacement model, and terminal energy consumption and carbon emissions are summarized and calculated;Based on terminal energy consumption, power load curve is constructed, and system operation simulation data is obtained by solving power production model;Multi-year power supply and demand side evolution path optimization model with minimum total cost in the whole cycle as the target is constructed, which is decomposed into long-term planning main problem and short-term operation sub-problem using Benders decomposition, under the condition of introducing total carbon, carbon intensity and department carbon emission constraint, the optimal evolution path meeting carbon constraint is output by iteratively solving through investment scheme transmission and feedback optimality cut or feasibility cut between main problem and sub-problem.The application realizes the collaborative optimization of supply and demand sides under carbon constraint.

The invention relates to a reverse deduction power system planning method, which comprises the following steps of: obtaining a long-term annual total installed capacity target in a long-term planning layer; in the middle-term coordination layer, an adjusted long-term annual total installed capacity target is obtained; in the short-term verification layer, outputting a final long-term annual total installed capacity target; the long-term planning layer, the middle-term coordination layer and the short-term verification layer jointly form a long-term-middle-term-short-term three-layer coupling deduction framework, and iterative optimization circulation of verification is operated from bottom to top. According to the method, a long-term-middle-term-short-term three-layer coupling deduction framework is constructed, reverse solution is carried out with the carbon peak reaching target year as rigid constraint, the problem that long-term strategy and short-term operation are disjointed frequently occurring in traditional electric power planning is effectively solved, the planning result has perspectiveness, and the method is suitable for large-scale popularization and application. The scientificity and the performability of the planning scheme are obviously improved; the total economic cost of low-carbon transformation of the whole power industry is effectively reduced, and collaborative improvement of economy and reliability is achieved.

The invention discloses a method for determining a chemical flooding block popularization benefit oil price limit, and solves the problems that a chemical flooding scheme is long in economic evaluation time consumption and cannot meet medium and long term planning in tertiary oil recovery. The method comprises the following steps: acquiring a chemical flooding potential block well pattern adjustment mode and investment allocation; chemical flooding economic evaluation and development parameters are obtained; establishing a chemical flooding enhanced recovery efficiency economic limit model, and calculating enhanced recovery efficiency economic limits under different development modes, different oil prices and different single well controlled reserves to obtain an economic limit chart; based on the development parameters of the chemical flooding potential block, when the recovery efficiency improving technical level of the chemical flooding potential block is equal to the recovery efficiency improving economic limit, according to the economic limit chart, interpolation is carried out to obtain the popularization benefit oil price of the chemical flooding potential block; the benefit oil prices are sorted from small to large, and the development and popularization sequence is optimized. According to the method, the popularization economic benefits and the popularization sequence of different blocks can be determined, so that a scientific and reasonable decision basis is provided for medium-and-long-term planning of tertiary oil recovery.

The invention provides an urban power system toughness improvement method and device based on vehicle network interaction, and the method constructs a two-stage stochastic optimization model with the minimum total cost of the system as a target, and covers the long-term planning and operation scheduling of the urban power system in a disaster scene. The method can improve the toughness of an urban power system in an extreme weather long-term scene, achieves the collaborative optimization of multi-dimensional costs such as power generation capacity expansion, line reinforcement, operation maintenance and load reduction, effectively reduces the comprehensive cost, and enhances the dynamic response capability of the system. A fusion channel of vehicle-network interaction and urban power grid toughness planning is opened, and a technical path capable of being popularized is provided for safe, flexible and economical operation of a power system under future climate uncertainty.

The invention discloses a collaborative operation method for a data center cluster and shared energy storage, and aims to solve the problems of disjunction of long-term planning and short-term operation, difficulty in multi-agent collaboration, conservative uncertainty response, insufficient service quality guarantee and the like of a green power direct connection data center cluster in energy management. The invention provides a two-stage double-layer collaborative management framework. In the first stage, a robust optimization model driven by data is constructed, and the capacity of the shared energy storage and the capacity of the gas turbine are optimally configured. And in the second stage, an asymmetric Nash bargaining game model is constructed, and distributed solution is carried out by using an alternating direction multiplier method so as to realize multi-agent cooperative operation and fair income distribution. According to the method, the cross-time-scale coupling decision problem is effectively solved, synergistic interaction among multiple subjects is realized, and the overall economy and the renewable energy consumption rate of the system are improved.

The present invention relates to a source-grid-load coordinated expansion planning method considering the optimization of combined hydropower, wind-solar and direct current transmission, belonging to the technical field of integrated energy system planning and operation. The method carries out detailed modeling of cascade hydropower stations and demand response, and takes into account the operational constraints of direct current transmission. The method utilizes demand response resources to alleviate the intermittent output of wind and solar power stations on the power supply side, proposes a load-side demand response service planning model to reduce the system's long-term planning costs, and establishes a source-grid-load coordinated planning model. The method establishes an opportunity constraint model to ensure the system's operational safety and the effective absorption of wind and solar power output, and utilizes the strong extension formula of the sample average approximation method to transform the opportunity constraint model into a mixed integer linear programming problem for solution.

A distributed photovoltaic accommodation capacity quantitative evaluation method, system and device considering uncertainty, the method comprising: generating a source and load uncertainty scenario suitable for long-term planning of a power distribution network, comprehensively considering the occurrence probability of various typical scenarios within a period based on an uncertainty method, aggregating clusters through improved K-Means mean clustering, and reducing scenarios of clusters through an SBR algorithm based on Kantorovich distance to obtain various typical scenarios and their probabilities; constructing a future simultaneous period load and distributed photovoltaic joint scenario set, and solving the voltage out-of-limit probability and comprehensive line loss rate of each load node by using a joint scenario probability power flow calculation method; establishing a distributed photovoltaic accommodation capacity quantitative evaluation model considering uncertainty, relaxing the voltage constraint, taking the maximum access amount of distributed photovoltaic as the target, and carrying out optimization solution of the maximum accommodation capacity of distributed photovoltaic based on the source and load uncertainty scenario.

A capacity configuration method and system for microgrid system planning based on double-layer optimization adopts a deep Q-network reinforcement learning method to determine the capacity configuration scheme for each decision cycle according to the state space and action space; the capacity configuration scheme for the long-term planning cycle is composed of the capacity configuration schemes of all decision cycles in the long-term planning cycle; a mathematical programming method is adopted to determine the capacity configuration scheme for each short-term planning cycle in the current decision cycle according to the constraint conditions of the target model and the upper limit of the configuration capacity of each short-term planning cycle in the current decision cycle; the economic index of the capacity configuration scheme for the long-term planning cycle is updated using the updated decision cycle reward function; when the updated economic index is less than the economic index before the update, the updated reward function of the implemented decision cycle is fed back to update the capacity configuration scheme for the long-term planning cycle, thereby solving the capacity configuration problem of microgrid system planning under multi-time scale uncertainty.

The invention relates to an intelligent soft switching planning method and device for a power distribution network, equipment, a medium and a product. The method comprises the steps of generating an intelligent soft switch planning strategy set according to power distribution network parameters, to-be-selected positions of intelligent soft switches in the power distribution network and unit capacity cost of each planning period by obtaining power distribution network parameters of each planning period of the power distribution network, and determining the intelligent soft switch according to the power distribution network parameters and the intelligent soft switch planning strategy set. According to the method, a first income model of an operator and a second income model of a power distribution network are constructed, and a target intelligent soft switch planning strategy of each planning period is determined according to the first income model and the second income model, so that different requirements of different interest subjects in intelligent soft switch planning can be considered; medium and long term planning can be carried out on the intelligent soft switch in different periods, and the characteristic that the source load increases year by year in the power distribution network is considered, so that the utilization efficiency of equipment resources is improved, and the return on investment of the intelligent soft switch is improved.

The invention relates to a rapid unit commitment model construction method based on scheduling and unit aggregation coupling. The method comprises the following steps: S1, constructing a traditional unit commitment model; s2, introducing line transmission capacity limitation and a direct current power flow model into a traditional unit combination model; s3, aggregating the large-scale units with the same type of operation characteristics, and carrying out output characteristic and climbing start-stop constraint modeling on an aggregation set; s4, introducing a relaxation hypothesis of an economic scheduling only model, and coupling constraint conditions of unit aggregation and scheduling only; and S5, completing construction of a rapid unit commitment model based on scheduling and unit aggregation coupling, and performing piecewise linearization solution on the model. According to the method, rapid operation simulation of a large number of thermal power generating units can be achieved, the method is suitable for a novel electric power system with high renewable energy permeability and a scene where long-term operation simulation of renewable energy volatility needs to be considered, and powerful support is provided for long-term planning and daily scheduling of the electric power system on the premise that calculation precision is guaranteed.

The present application relates to the technical field of elastic power system planning optimization, and particularly relates to a power supply structure optimization method and system for energy transformation and elasticity improvement, comprising: constructing and solving a short-term unit commitment model according to collected power system data to obtain unit output and line power flow information; inputting the unit output and line power flow information into a constructed two-stage long-term power system planning model considering extreme events to obtain unit capacity expansion demand and the most serious extreme event scenario of the power system, and inputting the same into the short-term unit commitment operation model to take the same as a standard thermal power unit to be upgraded for unit upgrading to obtain unit expansion results. The present application realizes a unit structure optimization scheme combined with long-term planning and short-term operation by taking into account long-term expansion planning and short-term operation, thereby laying a foundation for subsequent elastic power system planning optimization research.

The invention relates to the technical field of power grid carbon business planning, in particular to a dynamic prediction method, system and device for medium and long term planning of power grid enterprise carbon business and a storage medium. Collecting multi-source heterogeneous data, carrying out power grid service tagging processing, and constructing a carbon service exclusive database; based on a hierarchical policy analysis system, combining four-level evaluation index quantitative analysis to the cooperative influence of international rules, domestic policies and regional detailed rules on the power grid carbon business; establishing a scene suitability evaluation system, performing multi-dimensional evaluation scoring on carbon business cases outside the region, screening high-quality cases, and extracting reusable experience; performing basic trend fitting through a time sequence model, and combining a machine learning model with dynamic factors to construct a hybrid prediction model; and setting a fluctuation threshold value based on the dynamic factor library, triggering correction when the factor change exceeds the threshold value, and dynamically adjusting the prediction result. The problems of insufficient policy analysis, unscientific case reference, inaccurate prediction method and non-closed-loop landing execution are solved.

The invention provides a renewable energy supply-transmission-demand-storage system space-time collaborative configuration method, and relates to the technical field of smart energy, and the method comprises the steps: obtaining the data of a plurality of regions; calculating a time mismatch degree, a space mismatch degree and a space-time coupling mismatch degree of each region; decomposing the optimization problem into a long-term planning layer, a medium-term scheduling layer and a short-term real-time layer in a time dimension; constructing a multi-objective optimization function of each time layer; the optimization problem of each time layer is decomposed in the spatial dimension; alternately solving the local optimization sub-problem and the global coordination problem of each region by adopting a distributed iteration method; when the algorithm converges, outputting a configuration result of the current time layer; and executing the decision of the first time period by each time layer and taking the decision as a constraint condition of the next time layer to obtain the power generation installed capacity, the power transmission line capacity, the energy storage capacity and the operation strategy of each region. The renewable energy consumption rate can be improved, and the system operation cost can be reduced.

The invention relates to a power supply planning method considering boundary uncertainty. The method comprises the following steps: step 1, inputting power supply construction and load conditions of original partitions in long-term planning as basic parameters of a model; 2, sampling uncertainty according to a Monte Carlo simulation method to generate a scene tree of future electricity consumption and load, and generating a possible value set under different time nodes in the future; 3, establishing a rolling optimization power supply structure planning model based on a model prediction control thought; the method has the advantages that the power supply structure planning model is constructed, model prediction control is introduced, pre-planning is realized, and the influence is reduced through an online rolling strategy.

The present invention relates to the technical field of hydropower station optimization and scheduling, and specifically to a multi-objective planning method and system for a hydropower station based on multimodal data fusion. The method and system comprise the following steps: collecting multimodal data of the hydropower station, mining a first planning connection and a second planning connection between the multimodal data of the hydropower station, fusing the data according to the first planning connection and the second planning connection to obtain fused planning data; constructing multi-objective planning constraints of the hydropower station according to the fused planning data, including long-term planning constraints, medium-term planning constraints and short-term planning constraints; constructing a planning state space of a target object using the multimodal data of the hydropower station, including a long-term planning state space, a medium-term planning state space and a short-term planning state space; and sequentially planning the target objects of the long-term planning, medium-term planning and short-term planning using a reinforcement learning algorithm based on the multimodal data fusion to obtain corresponding planning strategies.

The embodiment of the invention discloses a power grid configuration operation cooperation method and device, electronic equipment and a storage medium. The method comprises the steps that a medium and long term planning model is established with minimization of optimization cost, maximization of fluctuation stabilization effect and minimization of carbon emission as targets and with a thermal power generating unit peak regulation plan and installed capacity of various energy storage units as optimization variables; establishing a day-ahead operation model by taking minimization of the daily operation cost of the thermal power generating unit and the long-time energy storage unit as a target and taking the daily power curves of the thermal power generating unit and the long-time energy storage unit as optimization variables; a real-time operation control model based on reinforcement learning is established based on the real-time power supply state and the short-time energy storage unit charging and discharging instruction; and the optimal peak regulation plan of the thermal power generating unit, the optimal installed capacity of various energy storage units, the optimal daily power curve of the thermal power generating unit and long-time energy storage, and the optimal short-time power curve of short-time energy storage are determined by combining the optimization model and based on the optimized model. The embodiment of the invention can improve the power supply reliability and economy of the power grid system.

The invention discloses a building load prediction method and device based on a GWO-SRU network, and the method comprises the specific steps: integrating historical load data and environment data of a target building, inputting the integrated data into a GWO-SRU building load prediction model, and obtaining a prediction value of the load of the target building; wherein the GWO-SRU building load prediction model comprises an SRU network, and an optimal hyper-parameter of the SRU network is obtained by using an improved GWO algorithm; according to the improved GWO algorithm, a good point set is adopted to perform population initialization, and Levy flight is introduced into a position updating mechanism to search a globally optimal solution. The method plays a key role in flexible load optimization scheduling, the accuracy and flexibility of load scheduling are improved, the energy cost is reduced, and the stability of a power grid is enhanced. In addition, effective utilization of renewable energy sources is promoted, and a basis is provided for long-term planning and demand response strategies of a power system.

The invention relates to the technical field related to energy storage operation management, in particular to an operation strategy optimization method and system for energy storage equipment, and the method comprises the steps: setting strategy issuing parameters, and carrying out the operation strategy layered optimization management of the energy storage equipment through an energy storage strategy issuing architecture of annual granularity layering, monthly granularity layering and daily granularity layering. The technical problem that the operation efficiency of the energy storage equipment in different time periods is difficult to maximize due to the fact that connection among long-term planning of an annual strategy, medium-term adjustment of a monthly strategy and short-term execution of a daily strategy is not smooth is solved. According to the method, a hierarchical and refined collaborative optimization mechanism for constructing an annual granularity, monthly granularity and daily granularity three-level energy storage strategy is realized, and the technical effect of seamless connection of long-term planning, middle-term adjustment and short-term customization is realized.

The invention relates to a multi-dimensional security constraint-oriented source network collaborative planning method, apparatus and device, and a storage medium. The method comprises the steps of constructing a typical scene set based on basic data, and obtaining an extreme scene set and an extreme scene probability distribution uncertainty set; establishing a three-stage source network collaborative planning model, and introducing a frequency safety constraint based on frequency change rate limitation, a short-circuit current constraint based on node self-admittance and a direct-current short-circuit ratio constraint based on a multi-infeed short-circuit ratio; and decomposing and solving the three-stage source network collaborative expansion planning model, performing iteration to obtain an optimal planning scheme, and enabling the optimal planning scheme to meet the short-circuit ratio and short-circuit current constraint by utilizing a topological post-verification and constraint generation process. Compared with the prior art, the problem that traditional robust planning is too conservative is avoided while multiple types of safety requirements are considered, coordinated balance of economy and safety in source network planning is achieved, and the method is suitable for medium-and-long-term planning of high-proportion renewable energy sources and an alternating-current and direct-current hybrid system.

The invention discloses a power system scheduling method, device and equipment and a storage medium, and belongs to the technical field of power system scheduling. The method comprises the following steps: constructing a system planning and operation model; constructing a medium and long term runoff uncertainty optimization model based on an information gap decision theory, and determining a runoff uncertainty robust radius bearable by the system through a risk avoidance strategy; the method comprises the following steps: constructing a short-term wind and light uncertainty robust optimization model based on adaptive distributed robust optimization, and constructing a wind and light uncertainty set by adopting a state-driven adaptive Wasserstein distance; carrying out cooperative solution on the system planning and operation model, the medium and long-term runoff uncertainty optimization model and the short-term wind and light uncertainty robust optimization model by adopting a hierarchical optimization framework comprising three hierarchies to obtain a solution result; and outputting a medium and long-term planning scheme and a short-term operation strategy. According to the embodiment of the invention, the operation safety of the power system can be effectively improved.

The invention discloses a unified optimization method for physical toughness and operation configuration of an electric power system. The method comprises the following steps: establishing a double-layer computing architecture comprising an upper-layer power grid physical system model and a lower-layer energy community model; generating a random scene set and a robust uncertainty set; executing a numerical optimization process under a two-stage random-robust hybrid optimization framework: in the process, determining a physical topology reinforcement parameter in a long-term planning stage, determining a physical repair scheduling parameter in a short-term operation stage, and carrying out mathematical coupling on the two stages through technical constraints; and carrying out convergence solution on the unified optimization process. According to the method, a power grid operator can consider the physical toughness constraint and economic cost of coupling short-term emergency repair scheduling under the attack of the worst case when carrying out planning decision-making of long-term physical topology reinforcement, so that an engineering decision-making scheme with the highest physical security level and the optimal economic benefit is output.

This invention discloses a method for coordinated and optimized configuration of energy storage power stations in the medium and long term, belonging to the field of energy storage power station planning technology. The method includes: comprehensively considering the economic benefits during the construction of the planned energy storage power station, as well as the grid status, environmental factors, rated power, and capacity configuration of the completed energy storage power station, to construct a two-layer multi-objective optimization model and corresponding constraints; under the constraints, using a preset multi-objective optimization model solving algorithm, solving the multi-objective optimization model to obtain a Pareto optimal solution set for the energy storage power station configuration scheme; screening the schemes in the Pareto optimal solution set to obtain the optimal scheme, and configuring the planned energy storage power station with the obtained optimal scheme to achieve the optimal planning and configuration of the energy storage power station capacity. Using the technical solution of this invention can provide rational suggestions for the investment and construction of energy storage power stations.

The invention discloses a large-scale wind-solar-thermal storage base scheduling decision-making and optimal configuration method and system based on hierarchical reinforcement learning. The method comprises the steps that historical data are collected and preprocessed; a probability prediction model based on Transform is constructed, and wind and light power quantile prediction is output; designing a multi-time scale state space including long-term planning, short-term scheduling and real-time control; a hierarchical deep reinforcement learning framework is established, a high layer adopts a TD3 algorithm to carry out capacity configuration, a middle layer adopts an MADDPG algorithm to carry out day-ahead scheduling, and a low layer adopts a PPO algorithm to carry out real-time control; key constraints such as system inertia and short-circuit ratio are embedded through a projection method and a penalty term; training the network by adopting a priority experience playback and course learning strategy; deploying an online rolling optimization and incremental learning mechanism; according to the method, the high-dimensional state space of a large-scale base can be effectively dealt with, collaborative optimization of investment and operation is realized, and the system supporting capacity under the high proportion of new energy is guaranteed.