New energy station intelligent operation system, control method and device, and medium

Abstract

The present disclosure provides a new energy station digital operation system and control method, device and medium, and relates to the technical field of new energy. The system comprises: outputting market electricity price prediction results and new energy output prediction results through an electricity price prediction module and a new energy output prediction module respectively, and realizing operation strategy optimization and capacity configuration decision of the new energy station by the collaborative work of an energy storage optimization scheduling module and a planning layout decision module in combination with the market electricity price prediction results and the new energy output prediction results, and solving and outputting a capacity configuration scheme corresponding to the new energy device and the energy storage device. The technical scheme realizes full-link closed-loop optimization from prediction to scheduling to planning by constructing a multi-module collaborative new energy station digital operation system, can significantly enhance the adaptability of the system to power market fluctuations, and ensures the operation income of the new energy station.

Description

Technical Field

[0001] This disclosure relates to the field of new energy technology, and more specifically, to a digital and intelligent operation system and control method, equipment, and medium for new energy power stations. Background Technology

[0002] With the continued advancement of the "dual carbon" goals, the proportion of renewable energy power plants in the power system is constantly increasing, becoming an important supporting force for achieving a green and low-carbon transformation. Especially against the backdrop of large-scale grid integration of renewable energy sources such as wind and solar power, the operation and management of renewable energy power plants are facing a profound transformation from policy-driven to market-driven. Guided by relevant policies, the fixed feed-in tariff mechanism for renewable energy has been gradually phased out, replaced by a market-based pricing mechanism, promoting the full participation of renewable energy in multiple trading segments, including the electricity spot market, ancillary services market, and capacity market. This transformation signifies that renewable energy power generation projects will no longer rely on subsidies but will need to actively participate in market transactions and respond to electricity price fluctuations to achieve economic benefits.

[0003] However, as electricity price liberalization deepens, a mismatch remains between the level of digital and intelligent operation of renewable energy power plants and the complexity of the electricity market mechanism. On the one hand, renewable energy power is highly volatile and uncertain, particularly affected by factors such as weather conditions and geographical location, making it difficult to accurately predict its output characteristics. On the other hand, electricity market prices are influenced by a complex interplay of various disturbances, with both sharp short-term fluctuations and long-term trend evolution, resulting in high uncertainty risks for renewable energy power plants when formulating trading strategies and making operational decisions.

[0004] Furthermore, traditional operation and scheduling methods typically employ fixed rules or linear models for energy storage charging and discharging decisions, neglecting the deep nonlinear coupling between the dynamics of electricity market supply and demand and changes in renewable energy output. This results in insufficient flexibility in scheduling strategies, making it difficult to balance economic efficiency and system stability in operational outcomes. Simultaneously, during the planning phase of renewable energy power plants, there is often an over-reliance on resource endowment as the basis for site selection, lacking systematic consideration of future market electricity price trends, load center distribution, and grid constraints. Consequently, some projects, despite possessing favorable resource conditions, face low returns or even difficulty in achieving profitability in actual operation.

[0005] In summary, current operations and management of renewable energy power plants in the context of a market-oriented electricity market generally suffer from insufficient output forecasting accuracy, inadequate market responsiveness, lagging energy storage dispatch strategies, and a single dimension in planning and layout decisions, making it difficult to achieve stable, efficient, and profit-oriented operational goals. Therefore, there is an urgent need to construct a new type of intelligent digital operation system that can adapt to market changes, integrate multi-source information, and possess intelligent analysis and strategy generation capabilities to enhance the survivability and profitability of renewable energy power plants in the competitive electricity market.

[0006] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0007] The purpose of this disclosure is to provide a digital and intelligent operation system and control method, equipment, and medium for new energy power plants, which can significantly enhance the system's adaptability to fluctuations in the electricity market and ensure the operational benefits of new energy power plants.

[0008] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0009] According to a first aspect of the present disclosure, a digital and intelligent operation system for new energy power stations is provided, comprising:

[0010] The electricity price forecasting module is used to input the acquired electricity price disturbance feature data into the electricity price forecasting model based on the fusion of time series model and attention mechanism, so as to predict the market-based electricity price in the future period and output the market-based electricity price forecast results at multiple time scales.

[0011] The new energy output prediction module is used to input the acquired spatiotemporal data of the power plant output into the new energy output prediction module based on the fusion of time-series spatial features, so as to predict the power generation of the new energy devices in the new energy power plant and obtain the new energy output prediction result.

[0012] An energy storage optimization scheduling module is connected to the electricity price prediction module and the new energy output prediction module. It is used to construct a diversified target model based on the market-based electricity price prediction results and the new energy output prediction results, and generate a charging and discharging strategy for the energy storage device by solving the diversified target model.

[0013] The planning and layout decision module is coupled to the electricity price prediction module, the new energy output prediction module, and the energy storage optimization scheduling module. It is used to combine the site selection conditions of the new energy power plant, the market-based electricity price prediction results, the new energy output prediction results, and the charging and discharging strategy of the energy storage device to solve and output the capacity configuration scheme corresponding to the new energy device and the energy storage device.

[0014] In some example embodiments of this disclosure, based on the foregoing scheme, the electricity price prediction model includes an electricity price time-series feature extraction network based on a time-series model structure and a feature enhancement representation network based on an attention mechanism;

[0015] The electricity price forecasting module includes:

[0016] The first data fusion unit is used to vectorize the various multi-source heterogeneous data in the electricity price disturbance feature data to obtain the electricity price disturbance vector;

[0017] The first model scheduling unit is used to schedule the trained electricity price prediction model to perform time series modeling on the electricity price disturbance vector through the electricity price time series feature extraction network, extract the electricity price time series features, and construct a weight matrix based on the electricity price time series features through the feature enhancement representation network to achieve focused modeling of important disturbance factors and output the market-based electricity price prediction result.

[0018] In some example embodiments of this disclosure, based on the foregoing scheme, the new energy output prediction module includes a spatial feature extraction network based on a convolutional neural network structure, an output temporal feature extraction network based on a temporal model structure, and a feature fusion network:

[0019] The new energy output prediction module includes:

[0020] The second data fusion unit is used to vectorize various multi-source heterogeneous data in the spatiotemporal data of the power station output to obtain meteorological spatial vector and new energy output time series vector.

[0021] The second model scheduling unit is used to schedule the trained new energy output prediction module to extract spatial features from the meteorological spatial vector through the spatial feature extraction network, obtain spatial features by performing time series modeling on the new energy output time series vector through the output time series feature extraction network, obtain time series features, and fuse the spatial features and the time series features through the feature fusion network to output the new energy output prediction result.

[0022] In some example embodiments of this disclosure, based on the foregoing scheme, the energy storage optimization scheduling module includes:

[0023] The optimization model construction unit is used to take the market-based electricity price forecast results and the new energy output forecast results as boundary condition inputs, and combine them with physical constraints, grid constraints and operational constraints as constraints to construct a multi-objective optimization model with economic, technical and social objectives; wherein, the physical constraints, grid constraints and operational constraints include any one or more combinations of energy storage device type, initial capacity, battery cycle life, charge and discharge efficiency, equipment cost, grid load and frequency regulation reserve requirements;

[0024] The optimization solution unit is used to call the multi-objective optimization model, perform iterative calculations on the multi-objective optimization model based on a non-dominated sorting genetic algorithm or a multi-agent optimization algorithm, and output a charging and discharging strategy for the energy storage device that satisfies multiple constraints.

[0025] In some example embodiments of this disclosure, based on the foregoing scheme, the planning layout decision module includes:

[0026] The strategy input unit is used to acquire the site selection condition information corresponding to the new energy power station, and to receive resource attribute decision and market attribute decision input. The site selection condition information includes at least land availability, grid access capacity, policy incentive information and load center distance.

[0027] The coupled modeling unit is used to construct a capacity configuration optimization model for new energy devices and energy storage devices based on the site selection information, resource attribute decisions, market attribute decisions, market-based electricity price prediction results, new energy output prediction results, and energy storage device charging and discharging strategies.

[0028] The model solving unit is used to solve the capacity configuration optimization model through competitive game analysis or Nash equilibrium solution method, and output the optimal capacity configuration scheme of the new energy device and the energy storage device.

[0029] In some example embodiments of this disclosure, based on the foregoing scheme, the intelligent digital operation system for new energy power stations further includes a data acquisition and preprocessing module, which includes:

[0030] The multi-source data interface unit is used to connect to the data interfaces corresponding to the meteorological monitoring system, the power market data platform, the power station monitoring system, and the policy information database, and to collect the electricity price disturbance characteristic data and the power station output spatiotemporal data. The electricity price disturbance characteristic data includes any one or more combinations of historical electricity price data, seasonal climate data, geographical location information, fuel cost data, power generation technology data, power line data, and supply and demand balance data. The power station output spatiotemporal data includes any one or more combinations of historical output data, local meteorological data, atmospheric boundary layer data, irradiance data, and wind speed data.

[0031] The data cleaning unit is used to perform data preprocessing on the electricity price disturbance feature data and the power station output spatiotemporal data to obtain preprocessed electricity price disturbance feature data and power station output spatiotemporal data. The data preprocessing includes at least outlier removal, missing value imputation and time alignment.

[0032] The data normalization unit is used to standardize the preprocessed electricity price disturbance characteristic data and power plant output spatiotemporal data to obtain normalized electricity price disturbance characteristic data and power plant output spatiotemporal data, which are then transmitted to the electricity price prediction module and the new energy output prediction module, respectively.

[0033] In some example embodiments of this disclosure, based on the foregoing scheme, the intelligent operation system for new energy power stations further includes a market adaptation and dynamic update module, which includes:

[0034] The data scheduling and control unit is used to dynamically determine the data acquisition frequency and data acquisition priority based on the update rate, data importance, and model call requirements of different types of electricity price disturbance characteristic data and power station output spatiotemporal data, and distribute them to the multi-source data interface unit and the data cache and backtracking unit.

[0035] The data caching and backtracking unit is used to perform batch caching and time indexing management of the collected electricity price disturbance characteristic data and the spatiotemporal data of the power station output according to the received data acquisition frequency and the data acquisition priority, so as to support the historical data backtracking requirements of different models.

[0036] The data output management unit is used to extract the latest data that belongs to the target priority from the data cache and backtracking unit according to the data acquisition priority, and output it synchronously to the electricity price prediction module and the new energy output prediction module in the order of model call.

[0037] According to a second aspect of the present disclosure, a control method for the intelligent digital operation system of a new energy power station in the first aspect is provided, comprising:

[0038] The electricity price prediction module inputs the acquired electricity price disturbance feature data into the electricity price prediction model based on the fusion of time series model and attention mechanism to predict the market-based electricity price in the future period and output the market-based electricity price prediction results at multiple time scales.

[0039] The acquired spatiotemporal data of power plant output is input into the new energy output prediction module based on temporal spatial feature fusion through the new energy power plant output prediction module to predict the power generation of the new energy equipment in the new energy power plant and obtain the new energy output prediction result.

[0040] The energy storage optimization scheduling module constructs a diversified target model based on the market-based electricity price prediction results and the new energy output prediction results, and generates the energy storage device charging and discharging strategy by solving the diversified target model.

[0041] By combining the site selection conditions of the new energy power station, the market-based electricity price forecast, the new energy output forecast, and the energy storage device charging and discharging strategy of the planning and layout decision module, the corresponding capacity configuration schemes for the new energy device and the energy storage device are solved and output.

[0042] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions, wherein the computer-readable instructions, when executed by the processor, implement the intelligent digital operation system for new energy power stations in the first aspect.

[0043] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the intelligent operation system for new energy power stations in the first aspect.

[0044] The technical solutions provided in this disclosure may have the following beneficial effects:

[0045] The intelligent operation system for new energy power plants in the example embodiments of this disclosure, on the one hand, uses the outputs of the electricity price prediction module and the new energy output prediction module as inputs to jointly drive the energy storage optimization scheduling module, and further uses the energy storage device charging and discharging strategy as input to feed back to the planning and layout decision-making module, forming a market-oriented decision-making cascade mechanism. This vertical information transmission and coupling between modules enables each operational link to achieve coordinated and consistent strategy selection based on the same prediction. The system exhibits high consistency and goal unity at the overall level, which can significantly reduce the risk of resource mismatch caused by strategy conflicts. On the other hand, by dynamically inputting the prediction results into the energy storage optimization scheduling module, the energy storage strategy... It can flexibly match market fluctuations at different time scales, and the dynamic adjustment results of the dispatch strategy in turn affect the capacity configuration scheme, enabling newly built renewable energy power plants to have structural resistance to power market disturbances. It also enables the system to have the dual capabilities of feedforward prediction and feedback correction when facing real-time market changes, thereby improving the dispatch flexibility of the energy storage system. On the other hand, the generation of capacity configuration schemes relies on the coupled modeling of electricity price forecasts, output forecasts and energy storage dispatch results, which enables the planning process to "simulate" future operating scenarios. This achieves a full-link feedback mechanism that optimizes the early planning in reverse with operational efficiency, which can effectively improve the consistency of goals and resource optimization from renewable energy power plant planning to real-time execution.

[0046] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0048] Figure 1 The schematic diagram illustrates the structure of a digital and intelligent operation system for new energy power stations according to some embodiments of the present disclosure.

[0049] Figure 2 The schematic diagram illustrates the structure of an electricity price prediction module according to some embodiments of the present disclosure.

[0050] Figure 3 The schematic diagram illustrates the structure of a new energy output prediction module according to some embodiments of the present disclosure.

[0051] Figure 4 The schematic diagram illustrates the structure of an energy storage optimization scheduling module according to some embodiments of the present disclosure.

[0052] Figure 5 The schematic diagram illustrates the structure of a planning layout decision module according to some embodiments of the present disclosure.

[0053] Figure 6 The schematic diagram illustrates the structure of a data acquisition and preprocessing module according to some embodiments of the present disclosure.

[0054] Figure 7 The schematic diagram illustrates the structure of a market adaptation and dynamic update module according to some embodiments of the present disclosure.

[0055] Figure 8 The schematic diagram illustrates a flow chart of a control method for a digital and intelligent operation system for new energy power plants according to some embodiments of the present disclosure.

[0056] Figure 9 The schematic diagram illustrates the structural schematic of a computer system of an electronic device according to some embodiments of the present disclosure.

[0057] Figure 10 A schematic diagram of a computer-readable storage medium according to some embodiments of the present disclosure is shown.

[0058] In the accompanying drawings, the same or corresponding reference numerals indicate the same or corresponding parts. Detailed Implementation

[0059] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0060] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0061] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0062] Furthermore, the accompanying drawings are for illustrative purposes only and are not necessarily drawn to scale. The block diagrams shown in the drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0063] In this example embodiment, a digital and intelligent operation system for new energy power stations is first provided, referring to... Figure 1 As shown, the intelligent operation system 100 for new energy power plants may include an electricity price prediction module 110, a new energy output prediction module 120, an energy storage optimization scheduling module 130, and a planning and layout decision module 140. Wherein:

[0064] The electricity price forecasting module 110 can be used to input the acquired electricity price disturbance characteristic data into an electricity price forecasting model based on the fusion of time series models and attention mechanisms, so as to predict the market-based electricity price for future periods and output the market-based electricity price forecast results at multiple time scales. The electricity price disturbance characteristic data refers to the set of key factors affecting changes in market-based electricity prices, which specifically includes, but is not limited to, historical electricity price data, seasonal climate data, geographical location information, fuel cost data, power generation technology type, power line structure data, and electricity supply and demand balance data.

[0065] Electricity price prediction models refer to deep learning network architectures built upon the fusion of time series modeling and attention mechanisms. Their core structure includes a time series model component for modeling the time-series characteristics of electricity prices and an attention mechanism component for enhancing the representation of key perturbation factors. The time series model can employ structures such as Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, or Gated Recurrent Units (GRUs) to learn the trends and periodic patterns of electricity price evolution over time. Among these, LSTM networks, through their gating mechanisms of input, forget, and output gates, dynamically adjust the contribution of historical states to the current output, effectively modeling the characteristics of electricity price sequences over longer time spans.

[0066] The attention mechanism refers to the introduction of self-attention to learn the correlation between different time segments and the current prediction point. By calculating the attention weights among the query, key, and value, it automatically focuses on key perturbation time periods, thereby enhancing the model's ability to model nonlinear perturbations such as price mutations and boundary effects. In this embodiment, the attention mechanism can adopt a multi-head attention structure, combined with positional encoding to achieve non-recursive information capture, which can significantly reduce computational complexity while improving the model's expressive power.

[0067] In its implementation, the electricity price prediction module 110 can be built using deep learning frameworks such as TensorFlow and PyTorch. During the training phase, it can use mean squared error (MSE) or weighted mean absolute error (WMAE) as the loss function, combined with supervised learning using historical labeled datasets. Optionally, it can also use graph neural networks (GNNs) to enhance the modeling of structural correlations between perturbation factors, or integrate external knowledge graphs to improve the model's generalization ability.

[0068] The output processed by the electricity price forecasting module 110 is the market-based electricity price forecast results at multiple time scales, which can include intraday forecasts (15-minute or 1-hour granularity), day-ahead forecasts (24-hour granularity), and monthly forecasts. The forecast results will serve as an important input source for subsequent module scheduling and optimization decisions, thereby improving the system's ability to predict electricity price market fluctuations and its forward-looking regulation.

[0069] The new energy output prediction module 120 is used to input the acquired spatiotemporal data of the power plant output into the new energy output prediction model based on the fusion of time-series spatial features, so as to predict the power generation of the new energy devices in the new energy power plant and obtain the new energy output prediction result. For example, the new energy device can be a photovoltaic power generation device or a wind power generation device, and this embodiment is not limited to this.

[0070] Spatiotemporal data on power generation at a renewable energy plant refers to a set of data characterizing the interaction between the operating status of the renewable energy plant and its surrounding environment. This data can include historical power generation data, local meteorological data, atmospheric boundary layer data, irradiance data, and wind speed data. Historical power generation data refers to the power generation records of various types of renewable energy plants (such as photovoltaic arrays and wind turbines) at a specific time scale. Local meteorological data can include indicators such as temperature, humidity, wind speed, wind direction, and air pressure. Atmospheric boundary layer data can reflect the impact of wind shear and thermal stability on the availability of wind resources. Irradiance data can describe the intensity of solar radiation received per unit area of ​​the Earth's surface. Wind speed data can be collected data on wind speed variations.

[0071] New energy output prediction models can include spatial feature extraction networks, output temporal feature extraction networks, and feature fusion networks. Spatial feature extraction networks can employ convolutional neural networks (CNNs) to extract spatial distribution patterns inherent in meteorological fields and geographical features. In specific implementations, network structures of different depths can be designed based on 2D or 3D convolutional kernels to encode features from multivariate, multi-level spatial data, outputting high-dimensional dense vector representations.

[0072] Output time series feature extraction networks can be used to model the dynamic characteristics of historical power changes in new energy devices. They often adopt long short-term memory (LSTM) or gated recurrent unit (GRU) structures. These network structures can effectively identify time-dependent features such as periodic trends, short-term fluctuations and operating inertia in the output of new energy, and enhance the model's ability to predict the future state of the power sequence.

[0073] Feature fusion networks can be used to integrate spatial and temporal features to achieve deep fusion of cross-modal information. Fusion methods can include feature concatenation, attention-weighted fusion, or cross-network structures, ensuring effective alignment of different information channels in a shared representation space, thereby improving the final prediction accuracy. This embodiment does not impose any special limitations on the fusion method.

[0074] The new energy output prediction module 120 can be implemented by constructing a multi-input multi-output neural network structure based on a deep learning framework, and training samples are generated by stepwise prediction or sliding window method during the training process.

[0075] The output of new energy power generation prediction results can cover power generation forecast data at different time scales, providing dynamic boundary input for subsequent energy storage optimization and scheduling modules, which helps to improve the dispatchability and operational safety margin of the energy system.

[0076] The energy storage optimization scheduling module 130 is connected to the electricity price prediction module 110 and the renewable energy output prediction module 120. It is used to construct diversified objective models based on market-based electricity price prediction results and renewable energy output prediction results, and to generate charging and discharging strategies for the energy storage device by solving these diversified objective models. The connection means that the energy storage optimization scheduling module can receive multi-timescale electricity price prediction results from the electricity price prediction module and the power generation prediction values ​​from the renewable energy output prediction module in real time, and use these as inputs to establish an optimization decision-making model under operational constraints.

[0077] A diversified objective model refers to an optimization model that considers multiple optimization objectives simultaneously. These can be categorized into three types: economic objectives, technical objectives, and social objectives. Economic objectives may include maximizing the return on investment, minimizing operating costs, or maximizing revenue throughout the entire lifecycle of the energy storage system. Technical objectives may include extending battery lifespan, balancing charge-discharge cycles, and enhancing grid frequency regulation response capabilities. Social objectives may include minimizing carbon emissions, reducing wind and solar curtailment rates, and improving system stability.

[0078] When constructing diverse target models, electricity price forecasts and renewable energy output forecasts can be used as boundary condition inputs, combined with various constraints. These constraints may include, but are not limited to: electrochemical characteristics of the energy storage device type (such as lithium iron phosphate, flow batteries, sodium-sulfur batteries, etc.), initial capacity settings, battery cycle life limits, charge / discharge efficiency parameters, equipment construction and maintenance costs, grid load fluctuation range, grid connection voltage and frequency constraints, and frequency regulation reserve scheduling requirements. Physical constraints reflect the operational boundaries of the energy storage system, grid constraints reflect grid connection conditions and scheduling feasibility, and operational constraints ensure the feasibility of the scheme over time.

[0079] The diverse objective models constructed by the energy storage optimization scheduling module 130 can be solved using either the Non-dominated Sorting Genetic Algorithm II (NSGA-II) or the Multi-Agent Optimization Algorithm. The NSGA-II is applicable to nonlinear optimization problems with multiple conflicting objectives and complex solution spaces; its core components include fast non-dominated sorting, crowding comparison operators, and elite strategies. The Multi-Agent Optimization Algorithm can simulate the coordinated evolution of multiple agents under certain rules, making it suitable for scenarios involving strategic game theory or shared resource allocation between energy storage systems and the electricity market.

[0080] The solution process for diverse objective models can be modeled and simulated using platforms such as Python and MATLAB, with heuristic search and parallel computing combined to accelerate solution convergence. Alternatively, mixed-integer linear programming (MILP) can be used to implement deterministic scheduling, or deep reinforcement learning algorithms can be employed to achieve adaptive policy evolution; this embodiment does not impose any specific limitations on these methods.

[0081] Energy storage device charging and discharging strategies can include combinations of parameters such as energy input, energy release, and standby state switching timing at different time points. These strategies have clear feasibility and market responsiveness, providing dynamic adjustment capabilities for new energy power plants. This enables a balance between operational economy and system stability in the context of fluctuating electricity prices and uncertain power output.

[0082] The planning and layout decision module 140 is coupled with the electricity price prediction module 110, the new energy output prediction module 120, and the energy storage optimization scheduling module 130. This module combines the site selection conditions of new energy power plants, market-based electricity price prediction results, new energy output prediction results, and energy storage device charging and discharging strategies to solve for and output the corresponding capacity configuration schemes for new energy devices and energy storage devices. Coupling means that the planning and layout decision module can simultaneously access the output results of the aforementioned three modules and use them as input parameters to participate in the entire process of subsequent capacity configuration modeling and optimization analysis, thereby achieving full-process data-driven planning and design.

[0083] The site selection criteria for renewable energy power plants refer to the set of external information related to the proposed construction area, including environment, resources, policies, and infrastructure. This can include factors such as land availability, grid connection capacity, policy incentives, and distance to load centers. Land availability limits the area and form of the installed capacity; grid connection capacity reflects grid connection capability and grid adaptability; policy incentives involve institutional support at the local level, such as subsidies, electricity pricing mechanisms, and green certificate quotas; and distance to load centers affects transmission losses, construction costs, and market proximity.

[0084] Under the aforementioned multiple input conditions, the planning and layout decision module 140 can achieve capacity allocation decisions by constructing a capacity configuration optimization model for new energy devices and energy storage devices. The capacity configuration optimization model is a combined decision-making model under multiple objectives and constraints. Its objective function can cover the minimization of investment costs, the maximization of average annual profits, the minimization of curtailment rates, and the maximization of system flexibility. The constraints can include land area restrictions, grid access capacity, battery maximum power and energy limits, and operation and maintenance budget constraints.

[0085] Once the capacity allocation optimization model is constructed, it can be solved using either competitive game analysis or Nash equilibrium methods. Competitive game analysis is suitable for scenarios involving multiple stakeholders (such as renewable energy developers, grid companies, and user-side load response units) in resource or market competition, and modeling can be based on non-cooperative game theory, Stackelberg game, or other strategy models. Nash equilibrium methods, on the other hand, can derive the optimal response combinations for multiple stakeholders in situations where their decisions are interdependent, leading to a stable equilibrium state. The construction methods of the capacity allocation optimization model and the use of competitive game analysis or Nash equilibrium methods are common analytical techniques in this field and will not be elaborated upon here.

[0086] In practical implementation, a distributed simulation platform can be built, encapsulating prediction results, scenario parameters, economic models, and market mechanisms into solution modules. Evolutionary game theory or iterative optimization methods can then be used to find stable capacity ratios in the multi-round solution space. Alternatively, system dynamics methods can be employed to dynamically simulate the configuration strategies of large-scale facility clusters, or machine learning methods can be introduced for empirical regression and strategy reinforcement.

[0087] The capacity configuration scheme for new energy devices and energy storage devices can include key design parameters such as the optimal installed capacity of different types of equipment, the capacity distribution of energy storage systems, the deployment sequence, and regional division. This provides a structured support scheme for the investment and construction of new energy projects based on market feasibility and system benefits, ensuring that the site design scheme has good economic efficiency, system adaptability, and long-term profitability.

[0088] The following will provide a further explanation of the intelligent operation system for new energy power stations in this example embodiment.

[0089] In one example embodiment of this disclosure, the electricity price prediction model may include an electricity price time-series feature extraction network based on a time-series model structure and a feature enhancement representation network based on an attention mechanism. The electricity price time-series feature extraction network is used to learn the time-series evolution patterns from the electricity price disturbance vector, while the feature enhancement representation network is used to dynamically weight key disturbance factors, enhancing the model's ability to express important features. This combination of model structures allows the system to simultaneously consider both trend and abrupt changes in the electricity price sequence, thereby improving the stability and accuracy of multi-timescale electricity price prediction results.

[0090] refer to Figure 2 As shown, the electricity price forecasting module 110 may include a first data fusion unit 111 and a first model scheduling unit 112, wherein:

[0091] The first data fusion unit 111 is used to vectorize various multi-source heterogeneous data in the electricity price disturbance feature data to obtain the electricity price disturbance vector. The electricity price disturbance feature data can be a collection of data from different data platforms with different formats, sampling granularity and update cycles. For example, the electricity price disturbance feature data can include historical electricity price records (such as day-ahead average price, spot transaction price), meteorological factors (such as temperature, wind speed, air pressure, etc.), geographical location parameters (such as station latitude and longitude, altitude), fuel prices (such as coal, gas and oil unit prices), power generation technology structure (such as wind and thermal complementarity), power transmission capacity parameters (such as node voltage, current fluctuation), and load-supply curves in the region.

[0092] In the first data fusion unit 111, the original electricity price disturbance feature data can first undergo type identification and standardization preprocessing. For numerical data, normalization methods (such as Z-score standardization, Min-Max scaling, etc.) are used, while for categorical data, one-hot encoding or embedding vectors are used for discretization. Subsequently, different data sources are uniformly mapped to a common feature space to construct a unified data representation structure. The fusion method can employ simple concatenation, weighted fusion, or fusion compression strategies based on dimensionality reduction algorithms (such as principal component analysis PCA, t-SNE, Autoencoder, etc.) to ensure that the data input dimension is controllable and the information is fully expressed.

[0093] The first model scheduling unit 112 can be used to schedule the trained electricity price prediction model. Scheduling refers to dynamically loading model parameters and computation paths according to the system task plan and call priority, completing model instantiation and inference tasks in edge computing nodes or central processing units. The electricity price prediction model consists of two sub-networks working together. First, the electricity price time-series feature extraction network models the electricity price disturbance vector in a time series, extracting electricity price time-series features. The modeling method of the electricity price time-series feature extraction network can be implemented using a gated recurrent structure (such as a Long Short-Term Memory network LSTM), recursively updating the state in multiple recurrent units to extract the implicit time dependency patterns in the sequence.

[0094] Next, the first model scheduling unit 112 can construct a weight matrix based on the aforementioned electricity price time-series features through a feature enhancement representation network, thereby achieving focused modeling of important disturbance factors. The feature enhancement representation network is a weighted focusing module built on an attention mechanism. It generates an attention distribution matrix through matching calculations and Softmax normalization operations. The attention distribution matrix can represent the model's estimate of the importance of the disturbance factor at each time step. The feature enhancement representation network can be constructed using single-head or multi-head attention mechanisms, or positional encoding can be introduced to enhance the time-series order awareness capability; this embodiment does not impose any special limitations on this.

[0095] In some alternative implementations, a Transformer encoder structure can be used to replace LSTM as the main body for temporal feature extraction, thereby improving modeling parallelism; or a gated convolutional neural network can be used to extract trend features of local time windows to reduce gradient vanishing problems caused by long-term dependence; in addition, the feature enhancement representation network can also use an adaptive gating mechanism (such as SE module, Dynamic Routing) to replace the traditional attention mechanism for dynamic feature regulation. This embodiment does not impose any special restrictions on the network structure in the electricity price prediction model.

[0096] By vectorizing the characteristic data of electricity price disturbances and inputting them into an electricity price prediction model that integrates time series modeling and attention mechanisms, the model can effectively improve the trend capture and change response capabilities of the electricity price prediction model across multiple time scales, thereby enhancing the accuracy, stability, and interpretability of the electricity price prediction results.

[0097] In one example embodiment of this disclosure, the new energy output prediction model may include a spatial feature extraction network based on a convolutional neural network structure, an output temporal feature extraction network based on a temporal model structure, and a feature fusion network.

[0098] refer to Figure 3As shown, the new energy output prediction module 120 may include a second data fusion unit 121 and a second model scheduling unit 122, wherein:

[0099] The second data fusion unit 121 is used to vectorize various multi-source heterogeneous data in the spatiotemporal data of power station output to obtain meteorological spatial vector and new energy output time series vector.

[0100] Spatiotemporal data on wind farm output refers to a dataset reflecting the environmental status and operational behavior of new energy wind farms. This data can include historical output data, local meteorological data, atmospheric boundary layer data, irradiance data, and wind speed data. Historical output data consists of power records from the equipment's operational history, acquired at minute or hourly granularity. Local meteorological data includes indicators such as temperature, humidity, wind speed, air pressure, and wind direction, exhibiting significant spatial variability. Atmospheric boundary layer data reflects the vertical structural characteristics of wind resources. Irradiance data represents the intensity of solar radiation received per unit area. Wind speed data reflects the driving factors of wind farm operation.

[0101] In its implementation, the second data fusion unit performs time synchronization processing and missing value imputation on various types of raw data, ensuring alignment consistency across different data sources on the time axis. Subsequently, the data is decoupled and categorized according to spatial and temporal characteristics, constructing meteorological spatial vectors and renewable energy output temporal vectors respectively. The meteorological spatial vectors are based on regional meteorological maps or raster data, constructed as two-dimensional or three-dimensional matrices using pixel interpolation or regional grouping methods; the renewable energy output temporal vectors are constructed as fixed-length sliding time series using a sampling window mechanism. During vectorization, normalization, standardization, and embedding mapping can be employed to ensure data dimensionality consistency and representation stability.

[0102] The second model scheduling unit 122 can be used to schedule the trained new energy output prediction model, extract spatial features from meteorological spatial vectors through a spatial feature extraction network to obtain spatial features, perform time series modeling on new energy output time series vectors through an output time series feature extraction network to obtain time series features, and fuse spatial features and time series features through a feature fusion network to output new energy output prediction results.

[0103] Spatial feature extraction networks can be built on the Convolutional Neural Network (CNN) structure, and can include input layers, convolutional layers, activation layers, pooling layers, and fully connected layers. Convolutional layers perform local perception operations on the input data through multiple convolutional kernels, extracting the spatial correlation and pattern features of regional meteorological variables. Activation layers often use Rectified Linear Units (ReLU) to introduce nonlinear expressive power. Pooling layers (such as max pooling and average pooling) can be used to reduce feature dimensionality and enhance feature abstraction capabilities. Finally, the fully connected layers output spatial feature vectors, which serve as one of the inputs to subsequent fusion networks.

[0104] Temporal feature extraction networks can be constructed based on recurrent neural network structures, preferably long short-term memory networks or gated recurrent units. By performing time series analysis on historical power generation data of new energy sources, dynamic features such as periodic changes, short-term inertial fluctuations, and responses to sudden disturbances in power output can be identified. The temporal feature extraction network structure models long-term dependency issues through its hidden states and gating mechanisms, thereby improving the extraction effect of nonlinear output features of new energy sources.

[0105] Feature fusion networks can be used to achieve unified encoding and joint modeling of two types of heterogeneous features. A feature fusion network can include structures such as a feature concatenation module, an attention weighting module, and a fusion perception module. The feature concatenation module can connect spatial and temporal features along the feature dimension to form a joint feature representation; the attention weighting module can enhance the expressive power of key features by calculating the importance weights of each channel; and the fusion perception module can further model cross-modal interaction relationships based on a multilayer perceptron (MLP) or Transformer structure to generate the final output prediction vector.

[0106] In some alternative implementations, residual networks (ResNet) or densely connected networks (DenseNet) can be used in the spatial feature extraction network to enhance the transfer capability of deep features; bidirectional LSTM can be used in the temporal feature extraction network to enhance the ability to model the correlation between consecutive time steps; and cross-modal attention mechanisms or graph convolutional networks can be introduced in the feature fusion stage to further explore the structural connections between spatial regions.

[0107] The new energy output prediction results are output in the form of hourly power prediction values ​​over a future period of time. They can be used to support subsequent energy storage optimization scheduling and system operation strategy formulation. The output of the new energy output prediction model with the above network structure can effectively improve the prediction accuracy, enhance the model's generalization ability, and has good adaptability to multi-source data.

[0108] By constructing a new energy power output prediction model that includes a spatial feature extraction network, a power output temporal feature extraction network, and a feature fusion network, it is possible to effectively model the temporal variation patterns of meteorological spatial features and new energy power output, respectively. Through the fusion mechanism, the two types of features are efficiently integrated, thereby improving the new energy power output prediction model's ability to fit complex meteorological disturbances and nonlinear power response relationships, significantly enhancing the accuracy and robustness of new energy power output prediction, and strengthening the predictability and controllability of new energy power plant operation scheduling.

[0109] In an example embodiment of this disclosure, reference is made to Figure 4 As shown, the energy storage optimization scheduling module 130 may include an optimization model construction unit 131 and an optimization solution unit 132, wherein:

[0110] The optimization model building unit 131 can be used to take the market-based electricity price forecast results and the new energy output forecast results as boundary condition inputs, and combine them with physical constraints, grid constraints and operation constraints as constraints to build a multi-objective optimization model with economic, technical and social objectives.

[0111] The boundary condition inputs can include predicted electricity price sequences and predicted power output sequences for several future time periods, exhibiting multi-timescale and dynamic characteristics. Their function is to limit the input domain of the multi-objective optimization model and constrain the operational context of the energy storage strategy. Economic objectives can include maximizing energy storage device revenue, maximizing peak-valley arbitrage income, and minimizing the investment payback period. Technical objectives involve extending the cycle life of energy storage batteries, maximizing load balance rate, and optimizing grid fluctuation suppression capabilities. Social objectives can encompass minimizing carbon emissions, minimizing curtailment rates, and increasing regional energy self-sufficiency.

[0112] Physical constraints refer to the operational limitations based on the energy storage device itself, including parameters such as the type of energy storage device (e.g., lithium battery, sodium-sulfur battery, flywheel energy storage, compressed air energy storage, etc.), initial capacity (expressed in terms of rated power and energy capacity), battery cycle life (expressed in terms of equivalent full charge-discharge cycles or total operating time), and charge-discharge efficiency (typically 80%-95%, considering energy conversion losses). These parameters collectively define the technical boundaries of the energy storage device, ensuring that optimization strategies are executable within the device's carrying capacity.

[0113] Grid constraints refer to the grid operation boundary conditions that energy storage devices must meet to operate in grid-connected mode. These include, but are not limited to, maximum / minimum injectable power limits at the grid connection point, node voltage amplitude limits, current limits, frequency deviation tolerance ranges, and response time requirements for frequency and voltage regulation. In some special scenarios, they may also include access protocol constraints imposed by the electricity market on the provision of ancillary services (such as peak shaving, frequency regulation, and backup) to energy storage systems. For example, these constraints may require energy storage devices to reserve a certain percentage of their capacity for grid dispatch during specific time periods.

[0114] Operational constraints are mainly used to limit the scheduling feasibility of the multi-objective optimization model in the time dimension. They include limits on the rate of change of the charging and discharging power of the energy storage system (to avoid sudden changes that could cause system shocks), minimum charging / discharging time limits, continuous charging and discharging time window limits, and interlocking control strategies (to prevent simultaneous charging and discharging). At the same time, they also include requirements on the coupling between predicted output and energy storage behavior to ensure that the energy storage system can effectively regulate new energy power generation within the output fluctuation range and avoid amplifying scheduling deviations due to prediction errors.

[0115] The construction of multi-objective optimization models can be expressed using mathematical modeling languages ​​(such as Pyomo, GAMS, and AMPL). The objective function and constraints can be nonlinear, non-convex, or mixed optimization problems with integer decision variables. They can also be simplified to a solvable form through linearization, piecewise linear approximation, etc. Of course, fuzzy logic can be introduced to express uncertainties, or robust optimization methods can be used to handle prediction errors, etc., to achieve the modeling of multi-objective optimization models. This embodiment is not limited to these methods.

[0116] The optimization solution unit 132 can be used to call a multi-objective optimization model, perform iterative calculations on the multi-objective optimization model based on a non-dominated sorting genetic algorithm or a multi-agent optimization algorithm, and output a charging and discharging strategy for the energy storage device that satisfies multiple constraints.

[0117] Among them, the non-dominated sorting genetic algorithm can be used as a swarm intelligence algorithm for multi-objective nonlinear optimization problems. It manages the solution set hierarchically through non-dominated sorting and maintains the diversity and distribution balance of solutions by combining crowding distance index. During the algorithm iteration process, selection, crossover, and mutation operations can be used to generate a new generation of population, and an elite retention mechanism ensures that the optimal solution is not lost. Using the non-dominated sorting genetic algorithm, multiple optimal solutions under different trade-offs can be obtained in a single run, forming a Pareto front, providing rich alternatives for strategy selection in different scenarios.

[0118] Multi-agent optimization algorithms can simulate the information interaction and strategy game process between multiple autonomous agents. In energy storage system scheduling, different strategies can be regarded as "agents," and their behavior can be continuously adjusted based on the payoff function in the simulated environment. For example, multi-agent optimization algorithms can be constructed through Actor-Critic structures under reinforcement learning frameworks, Q-learning algorithms, or evolutionary strategies based on game theory. This method is suitable for problem scenarios with complex coupling relationships and high uncertainty, and has the advantages of strong adaptability and outstanding online optimization capabilities.

[0119] The final generated energy storage device charging and discharging strategy can be a set of time-series control instructions, explicitly specifying the charging power, discharging power, and standby state of the energy storage system over several future time periods. This strategy aims to optimize the overall system efficiency while satisfying all constraints. The strategy can take the form of an hourly scheduling table, a strategy function, or a heuristic control rule. The energy storage device charging and discharging strategy can be directly used as input to the execution unit's scheduling instructions or as an optimization reference for the upper-level energy management system.

[0120] By using electricity price forecasts and renewable energy output forecasts as boundary conditions, and constructing a multi-objective optimization model under various constraints such as physics, power grid, and operation, and solving the model using a non-dominated sorting genetic algorithm or a multi-agent optimization algorithm, an effective trade-off can be achieved among multiple optimization objectives. This generates a charging and discharging strategy for energy storage devices that takes into account economic, technical, and social factors, thereby significantly improving the response efficiency and operational flexibility of renewable energy power plants to fluctuations in electricity market prices and uncertainties in resource output.

[0121] In an example embodiment of this disclosure, reference is made to Figure 5 As shown, the planning and layout decision module 140 may include a strategy input unit 141, a coupled modeling unit 142, and a model solving unit 143, wherein:

[0122] The strategy input unit 141 can be used to obtain the site selection condition information corresponding to the new energy power station, and receive resource attribute decision and market attribute decision input. The site selection condition information includes at least land availability, grid access capacity, policy incentive information and load center distance.

[0123] Among them, site selection information refers to the set of spatial constraints and feasibility indicators for the deployment of new energy power plants. Land availability is used to assess the land development attributes, physical constructability, and legal use rights of the proposed area. It can usually be identified and screened by combining topographic slope, land type, and ownership information through a GIS geographic information system. Grid access capacity refers to the grid connection capacity and remaining available capacity of the target access point. It can be obtained from the regional power grid dispatch platform and is limited by the capacity of the main line, voltage level, and power flow distribution. Policy incentive information includes new energy subsidy policies, electricity price floating mechanisms, and green certificate quota allocation schemes issued by the central and local governments. This part of the information can be obtained through government data interfaces or by trend extrapolation based on the historical policy effective cycle. Load center distance is used to measure the transmission path length between the power plant and the main power consumption area. It has a decisive impact on evaluating the construction cost of the transmission channel and the power consumption path loss.

[0124] Resource attribute decision-making refers to site assessment based on natural resource endowments, such as wind energy density distribution, solar irradiance, and water availability, which are usually obtained through modeling using historical measured data or satellite remote sensing data. Market attribute decision-making, on the other hand, is a proactive assessment of the potential revenue environment, such as the volatility of electricity market prices in the target area, the activity of capacity trading, ancillary service pricing mechanisms, and the market access threshold for energy storage, reflecting the financial return potential of the project under the future revenue model.

[0125] The coupled modeling unit 142 can be used to construct a capacity configuration optimization model for new energy devices and energy storage devices based on site selection information, resource attribute decisions, market attribute decisions, market-based electricity price prediction results, new energy output prediction results, and energy storage device charging and discharging strategies.

[0126] The capacity allocation optimization model is a mathematical model for calculating capacity allocation under the synergistic drive of multiple heterogeneous input factors. Essentially, it is a mixed-integer optimization problem with multiple objectives and constraints. In this model, the installed capacity of new energy devices and energy storage devices are the main decision variables. Its objective functions typically include, but are not limited to: maximizing the average annual return on investment, maximizing the net present value (NPV), minimizing the curtailment rate, minimizing system carbon emissions, and maximizing peak-shaving capacity.

[0127] In the capacity configuration optimization model, the input factors can be modeled and integrated as follows: the electricity price forecast result serves as the boundary of the electricity sales price in the future revenue model; the renewable energy output forecast result serves as the time series boundary of the electricity that each device unit can provide; the energy storage device charging and discharging strategy constrains the energy limit that the device can release or absorb at each time point; resource attribute decisions determine the upper limit of the deployable capacity of candidate sites in a specific spatial grid; and market attribute decisions provide supplementary constraints or incentive functions in terms of pricing mechanisms and service models. The modeling method can use mixed-integer linear programming (MILP) or mixed-integer nonlinear programming (MINLP) to express the relationship between the above-mentioned multiple types of variables and the objective function. Alternatively, a data-driven regression model can be introduced to estimate the sensitivity and weight of each objective function. This embodiment does not impose special limitations on the modeling method of the capacity configuration optimization model, and it belongs to the common technical means in this field, so it will not be described in detail here.

[0128] The model solving unit 143 can be used to solve the capacity configuration optimization model through competitive game analysis or Nash equilibrium solution method, and output the optimal capacity configuration scheme of the new energy device and the energy storage device.

[0129] The competitive game theory analysis method, based on the non-cooperative game modeling concept in game theory, is applicable to strategy deduction when multiple entities, such as new energy developers, grid companies, electricity retailers, and energy storage service providers, have resource sharing or conflicting benefits. Within this modeling framework, the capacity of new energy installations and energy storage installations are respectively considered as the strategy spaces of the game participants. The payoff functions of each party are reflected by both electricity price prediction models and operational simulations, and their optimal responses constitute a dynamic strategy evolution path. This method typically obtains a stable capacity distribution pattern where none of the parties are willing to unilaterally change their strategies by iteratively solving for the Nash equilibrium.

[0130] Nash equilibrium solutions are primarily applied to scenarios where participants have cross-coupled benefits but overall cooperation is limited. Their core principle is to derive one's own optimal policy based on the assumption that the other party's policy is constant, ultimately solving for the set of intersections where all participants are simultaneously optimal under a multi-policy combination. In terms of implementation, policy search and optimal solution approximation algorithms such as evolutionary game algorithms, multi-agent reinforcement learning, or approximate dynamic programming can be employed.

[0131] The output results include the installed capacity of new energy devices and energy storage devices at the target site, time-sharing deployment priority, equipment type selection and investment cycle arrangement. It has the characteristics of strong execution, economic feasibility and high system compatibility, forming a complete capacity configuration optimization strategy, and providing quantifiable design basis for subsequent project implementation.

[0132] By unifying and modeling site selection information, resource attribute decisions, market attribute decisions, electricity price forecasts, power output forecasts, and energy storage dispatch strategies, and solving the capacity configuration optimization model using competitive game analysis or Nash equilibrium methods, a structural balance can be achieved between the rationality of resource layout and market return response. This results in a capacity configuration scheme with multi-dimensional constraint adaptability, thereby improving the scientific nature of investment decisions in the planning stage of new energy and energy storage systems and their market adaptability in later operation.

[0133] In an example embodiment of this disclosure, reference is made to Figure 6 As shown, the intelligent operation system for new energy power stations may also include a data acquisition and preprocessing module 150. The data acquisition and preprocessing module 150 may include a multi-source data interface unit 151, a data cleaning unit 152, and a data normalization unit 153, wherein:

[0134] The multi-source data interface unit 151 can be used to connect to the data interfaces corresponding to the meteorological monitoring system, the power market data platform, the power station monitoring system and the policy information database, and collect electricity price disturbance characteristic data and power station output spatiotemporal data.

[0135] The meteorological monitoring system refers to the meteorological bureau's data interface, satellite remote sensing system, ground observation network, boundary layer radar, and micro-meteorological sensor array, which can provide real-time and historical meteorological factor data. The electricity market data platform can include provincial electricity trading centers, regional spot trading platforms, and ancillary service market settlement systems, whose output data can include historical day-ahead electricity prices, real-time electricity prices, marginal electricity prices, load forecast data, and traded electricity volumes. The power station monitoring system can collect status and analog quantities of new energy equipment through industrial communication protocols (such as Modbus and IEC 61850), including wind speed, irradiance, temperature, current, voltage, power generation, and operating status codes. The policy information database refers to a database interface for government affairs, including policy announcements and incentive measures issued by various departments.

[0136] Electricity price disturbance characteristic data can include any one or a combination of historical electricity price data, seasonal climate data, geographic location information, fuel cost data, power generation technology, power line data, and supply and demand balance data. Specifically, historical electricity price data can be extracted from multiple market dimensions such as day-ahead, real-time, and spot markets at an hourly granularity; seasonal climate data can be mapped to meteorological seasonal indices or cold / warm zone classification labels through timestamps; geographic location information can identify the physical environment of the power station through latitude, longitude, elevation, and administrative divisions; fuel cost data can come from spot prices of fuels such as coal, natural gas, and heavy oil; power generation technology can represent the power station type structure (such as wind and solar ratio, centralized / distributed installed capacity type); power line data can cover transmission channel topology, voltage level, and power flow direction; and supply and demand balance data can be calculated through the dynamic difference between regional load forecasting and supply capacity.

[0137] The spatiotemporal data of the power plant output can include any one or a combination of historical output data, local meteorological data, atmospheric boundary layer data, irradiance data, and wind speed data. Historical output data can be recorded by the power plant monitoring system; local meteorological data can be obtained through the power plant's own sensors or nearby observation points; atmospheric boundary layer data can generally be generated through modeling using lidar or radiosonde systems; irradiance data can be collected from ground stations or remote sensing satellite products (such as MODIS, Himawari); and wind speed data can come from the unit's anemometer or a third-party wind resource assessment platform.

[0138] The data cleaning unit 152 can be used to preprocess the electricity price disturbance characteristic data and the spatiotemporal data of power plant output to obtain the preprocessed electricity price disturbance characteristic data and the spatiotemporal data of power plant output. The data preprocessing includes at least outlier removal, missing value imputation and time alignment.

[0139] Outlier removal refers to identifying and removing extreme values ​​that are inconsistent with the data distribution pattern based on statistical distribution or rule models. This can be achieved using IQR (interquartile range) rules, Z-score standardization, or dynamic interval judgment based on sliding windows. Missing value imputation addresses the reconstruction of data from partial time slices or interrupted variable sampling. Strategies include interpolation (linear interpolation, spline interpolation), forward imputation, mean imputation, regression imputation, or nearest neighbor imputation (k-Nearest Neighbors, k-NN) based on similar samples. Time alignment ensures that all data variables are aligned to a uniform time granularity (e.g., 10 minutes, 30 minutes, 1 hour), generating structured time-series data frames for input into the model structure.

[0140] The data normalization unit 153 can be used to standardize the preprocessed electricity price disturbance characteristic data and power plant output spatiotemporal data to obtain normalized electricity price disturbance characteristic data and power plant output spatiotemporal data, which are then transmitted to the electricity price prediction module and the new energy output prediction module, respectively.

[0141] The purpose of normalization is to unify the scale of variables with different physical dimensions, so that they have equivalent weights in model calculations. Commonly used normalization methods include Min-Max scaling to the [0, 1] interval, Z-score standardization to a distribution with a mean of 0 and a standard deviation of 1, or logarithmic transformation for power-law distributed data variables. For discrete or categorical variables, label encoding, one-hot encoding, or embedded vector mapping can be used. The normalized data will be encapsulated into tensor structures according to the module interface definition format, so that they can be used as input for batch inference and feature extraction operations in the electricity price prediction module and the new energy output prediction module.

[0142] By constructing a preprocessing workflow that integrates multi-source data acquisition, cleaning, processing, and normalization, the integrity, consistency, and model input compatibility of electricity price disturbance characteristic data and power plant output spatiotemporal data can be ensured. This effectively reduces the impact of data anomalies and errors on the performance of the prediction model, thereby improving the overall system's data processing efficiency and the input quality of prediction results. Consequently, it enhances the credibility and accuracy of the output results of subsequent prediction and optimization modules.

[0143] In an example embodiment of this disclosure, reference is made to Figure 7As shown, the intelligent operation system for new energy power stations may also include a market adaptation and dynamic update module 160. The market adaptation and dynamic update module 160 may include a data scheduling and control unit 161, a data caching and backtracking unit 162, and a data output management unit 163, wherein:

[0144] The data scheduling and control unit 161 can be used to dynamically determine the data acquisition frequency and data acquisition priority based on the update rate, data importance and model call requirements of different types of electricity price disturbance characteristic data and power station output spatiotemporal data, and distribute them to the multi-source data interface unit and the data cache and backtracking unit.

[0145] Here, update rate refers to the data refresh cycle of different data sources. For example, electricity spot market prices may be updated every 15 minutes, while meteorological model outputs may be hourly or daily, and generator unit operation data can be sampled at a second-level sampling frequency. Data importance refers to the degree of influence of each data variable on the prediction accuracy of the electricity price prediction model and the new energy output prediction model. It can usually be obtained through sensitivity analysis, feature importance assessment (such as SHAP value, information gain), or training error inversion. Model call requirements are determined by the type of prediction the system performs in the current time period (such as intraday prediction, day-ahead prediction, short-term dispatch optimization).

[0146] In its implementation, the data scheduling and control unit can establish a priority-based scheduling strategy matrix, categorizing data sources into multiple levels such as high-frequency critical data (e.g., real-time electricity price fluctuations, wind speed data), mid-frequency environmental data (e.g., boundary layer temperature, atmospheric pressure), and low-frequency structural data (e.g., geographic information, fuel prices), and setting corresponding sampling periods and synchronization frequencies. The control logic can be implemented through preset rule tables, empirical parameter adjustments, or adaptive data scheduling strategies based on reinforcement learning. The data scheduling and control unit can also dynamically adjust data acquisition tasks based on current task load and computing resource status, such as throttling, merging, and delaying, to prevent system resource overload.

[0147] The data caching and backtracking unit 162 can be used to perform batch caching and time indexing management of the collected electricity price disturbance characteristic data and power station output spatiotemporal data according to the received data acquisition frequency and data acquisition priority, so as to support the historical data backtracking needs of different models.

[0148] The cache structure can be designed based on a multi-layer partitioning mechanism, including a raw data layer, a cleaned data layer, and a normalized feature layer. Each layer is organized with time windows (e.g., the most recent 1 hour, 6 hours, 24 hours, 7 days) and spatial partitions (e.g., by station ID, electricity price node number) to support fast retrieval and differentiated storage strategies. To improve storage efficiency, cache units can use circular buffers, log-structured merged storage (LSM-tree), or key-value databases (e.g., RocksDB) to achieve efficient write and time-range-based read functions.

[0149] Time index management can construct a multi-level index structure using timestamps and variable names, allowing different models to directly access historical data segments as input or validation data when performing tasks such as sliding window prediction, rolling optimization, and error evaluation. For example, in day-ahead forecasting, the electricity price forecasting model may need the historical disturbance factor sequence of the last 30 days, while the renewable energy output forecasting model needs to match historical power generation output data under similar weather conditions. The system can directly extract the corresponding segments based on the time index. To support model training and strategy evaluation, a label database can also be established in the cache to store historical true values ​​and model output results, enabling training sample generation and error backtracking analysis.

[0150] The data output management unit 163 can be used to extract the latest data that belongs to the target priority from the data cache and backtracking unit according to the data acquisition priority, and output it synchronously to the electricity price prediction module and the new energy output prediction module according to the model call order.

[0151] The data output management unit is responsible for decoupling and controlling the flow of data from the cache to the model. Its core functions include data filtering, format adaptation, batch processing scheduling, and anomaly detection. Data filtering logic can extract valid data entries from the cache that conform to the current time window, time granularity, and spatial range based on a sampling priority table and model input template definition. Format adaptation can ensure that data meets the neural network input format requirements through tensor reconstruction, dimensional expansion, and missing value imputation. Batch processing scheduling can use sliding window or time wheel scheduling strategies to uniformly allocate multiple model requests, avoiding redundant computation caused by repeated readings.

[0152] In some alternative implementations, the data output management unit can also achieve dynamic distribution of streaming data based on stream processing frameworks (such as Apache Flink and Apache Kafka Streams), or deploy microservice components on edge computing nodes to achieve local caching and push functions. The data output management unit can ensure that the system can continuously provide timely, prioritized, and formatted input data to the model module even in scenarios with dynamic data updates, significantly improving prediction accuracy, response speed, and computing resource utilization.

[0153] By establishing a dynamic data scheduling mechanism based on update rate and priority, and combining it with cache management and index control strategies, hierarchical caching, historical backtracking, and on-demand distribution control of multi-source data can be achieved. This can continuously ensure the timeliness and stability of model input in the high-frequency fluctuation environment of the power market, significantly improve the system's adaptability to dynamic changes in data flow, and thus enhance the response speed and real-time decision-making capabilities of the intelligent digital operation system in the prediction, optimization, and execution stages.

[0154] It should be noted that although several modules or units of the intelligent operation system for new energy power stations have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units for embodiment.

[0155] Furthermore, this example embodiment also provides a control method for a digital and intelligent operation system of a new energy power station. (Refer to...) Figure 8 As shown, the control method for the intelligent operation system of new energy power stations may include:

[0156] Step S810: The acquired electricity price disturbance feature data is input into the electricity price prediction model based on the fusion of time series model and attention mechanism through the electricity price prediction module, so as to predict the market-based electricity price in the future period and output the market-based electricity price prediction results under multiple time scales.

[0157] Step S820: The acquired spatiotemporal power output data of the power plant is input into the new energy power output prediction module based on the fusion of time-series spatial features through the new energy power output prediction module, so as to predict the power generation of the new energy device of the new energy power plant and obtain the new energy power output prediction result.

[0158] Step S830: The energy storage optimization scheduling module constructs a diversified target model based on the market-based electricity price prediction results and the new energy output prediction results, and generates a charging and discharging strategy for the energy storage device by solving the diversified target model.

[0159] Step S840: By combining the site selection conditions of the new energy power station, the market-based electricity price prediction results, the new energy output prediction results, and the energy storage device charging and discharging strategy of the planning and layout decision module, the corresponding capacity configuration scheme of the new energy device and the energy storage device is solved and output.

[0160] The specific details of each step in the control method for the digital and intelligent operation system of new energy power stations mentioned above have been described in detail in the corresponding digital and intelligent operation system of new energy power stations, so they will not be repeated here.

[0161] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0162] Furthermore, in an exemplary embodiment of this disclosure, an electronic device capable of implementing a control method for a digital and intelligent operation system of a new energy power station is also provided.

[0163] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be embodied in the following forms: a completely hardware embodiment, a completely software embodiment (including firmware, microcode, etc.), or an embodiment combining hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0164] The following reference Figure 9 To describe an electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0165] like Figure 9 As shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, a bus 930 connecting different system components (including storage unit 920 and processing unit 910), and a display unit 940.

[0166] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure.

[0167] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 921 and / or cache memory 922, and may further include read-only memory (ROM) 923.

[0168] Storage unit 920 may also include a program / utility 924 having a set (at least one) program module 925, such program module 925 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0169] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0170] Electronic device 900 can also communicate with one or more external devices 970 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0171] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0172] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0173] refer to Figure 10 As shown, a program product 1000 for implementing a control method for a digital and intelligent operation system for new energy power plants, according to an embodiment of the present disclosure, is described. It may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0174] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0175] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0176] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0177] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0178] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0179] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0180] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0181] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A new energy station digital operation system, characterized in that, The method comprises the following steps: An electricity price prediction module is configured to input the obtained electricity price disturbance feature data into an electricity price prediction model based on the fusion of a time sequence model and an attention mechanism, to predict the market-oriented electricity price of a future period, and output a market-oriented electricity price prediction result in multiple time scales; A new energy output prediction module is configured to input the obtained field station output spatio-temporal data into a new energy output prediction model based on the fusion of time sequence spatial features, to predict the power generation of a new energy device of the new energy field station, and obtain a new energy output prediction result; An energy storage optimization scheduling module is connected to the electricity price prediction module and the new energy output prediction module, and comprises: An optimization model construction unit is configured to input the market-oriented electricity price prediction result and the new energy output prediction result as boundary conditions, and combine physical constraints, grid constraints and operation constraints as constraint conditions, to construct a multi-objective optimization model with economy, technology and society as targets; wherein the physical constraints, grid constraints and operation constraints include any one or a combination of multiple of the following: energy storage device type, initial capacity, battery cycle life, charging and discharging efficiency, equipment cost, grid load and frequency modulation reserve requirement; An optimization solving unit is configured to call the multi-objective optimization model, perform iterative calculation on the multi-objective optimization model based on a non-dominated sorting genetic algorithm or a multi-agent optimization algorithm, and output an energy storage device charging and discharging strategy that meets multiple constraint conditions; A planning layout decision module is coupled to the electricity price prediction module, the new energy output prediction module and the energy storage optimization scheduling module, and comprises: A strategy input unit is configured to obtain site selection condition information corresponding to the new energy field station, and receive resource attribute decision and market attribute decision input; the site selection condition information at least includes land availability, access grid capacity, policy incentive information and load center distance; A coupling modeling unit is configured to construct a capacity configuration optimization model of new energy devices and energy storage devices based on the site selection condition information, the resource attribute decision, the market attribute decision, the market-oriented electricity price prediction result, the new energy output prediction result and the energy storage device charging and discharging strategy; A model solving unit is configured to solve the capacity configuration optimization model by a competitive game analysis method or a Nash equilibrium solving method, and output an optimal capacity configuration scheme of the new energy devices and the energy storage devices.

2. The system of claim 1, wherein, The electricity price prediction model comprises an electricity price time sequence feature extraction network based on a time sequence model structure and a feature enhancement representation network based on an attention mechanism; The electricity price prediction module comprises: A first data fusion unit is configured to perform vectorization representation on each item of multi-source heterogeneous data in the electricity price disturbance feature data, to obtain an electricity price disturbance vector; The first model scheduling unit is configured to schedule the trained electricity price prediction model to perform time series modeling on the electricity price disturbance vector through the electricity price time sequence feature extraction network, extract electricity price time sequence features, and construct a weight matrix based on the electricity price time sequence features through the feature enhancement representation network, so as to realize focused modeling of important disturbance factors and output the market-oriented electricity price prediction result.

3. The system of claim 1, wherein, The new energy output prediction module includes a spatial feature extraction network based on a convolutional neural network structure, an output time sequence feature extraction network based on a time sequence model structure, and a feature fusion network: The new energy output prediction model includes: The second data fusion unit is configured to perform vectorization representation on each item of multi-source heterogeneous data in the station output spatio-temporal data to obtain a meteorological spatial vector and a new energy output time sequence vector. The second model scheduling unit is configured to schedule the trained new energy output prediction model to perform spatial feature extraction on the meteorological spatial vector through the spatial feature extraction network to obtain spatial features, perform time sequence modeling on the new energy output time sequence vector through the output time sequence feature extraction network to obtain time sequence features, and fuse the spatial features and the time sequence features through the feature fusion network to output a new energy output prediction result.

4. The system of claim 1, wherein, The new energy station intelligent operation system further includes a data acquisition and preprocessing module, and the data acquisition and preprocessing module includes: A multi-source data interface unit is configured to connect data interfaces corresponding to a meteorological monitoring system, a power market data platform, a station monitoring system, and a policy information base, acquire the electricity price disturbance feature data and the station output spatio-temporal data, wherein the electricity price disturbance feature data includes any one or a combination of multiple of historical electricity price data, seasonal climate data, geographic location information, fuel cost data, power generation technology, power line data, and supply and demand balance data, and the station output spatio-temporal data includes any one or a combination of multiple of historical output data, local meteorological data, atmospheric boundary layer data, irradiance data, and wind speed data. A data cleaning unit is configured to perform data preprocessing on the electricity price disturbance feature data and the station output spatio-temporal data to obtain preprocessed electricity price disturbance feature data and station output spatio-temporal data, wherein the data preprocessing at least includes outlier removal, missing value filling, and time alignment processing. A data normalization unit is configured to perform standardization processing on the preprocessed electricity price disturbance feature data and the station output spatio-temporal data to obtain normalized electricity price disturbance feature data and station output spatio-temporal data, and transmit the normalized electricity price disturbance feature data and the station output spatio-temporal data to the electricity price prediction module and the new energy output prediction module, respectively.

5. The system of claim 4, wherein, The new energy station intelligent operation system further includes a market adaptation and dynamic updating module, and the market adaptation and dynamic updating module includes: A data scheduling control unit is configured to dynamically determine data acquisition frequency and data acquisition priority according to update rates, data importance, and model calling demands of different types of electricity price disturbance feature data and station output spatio-temporal data, and distribute the data acquisition frequency and the data acquisition priority to the multi-source data interface unit and the data caching and backtracking unit. a data caching and backtracking unit, configured to batch cache and time index manage the collected power price disturbance feature data and the station output spatiotemporal data according to the received data collection frequency and the data collection priority, to support the historical data backtracking demand of different models; a data output management unit, configured to extract the latest data belonging to a target priority from the data caching and backtracking unit according to the data collection priority, and synchronously output the data to the price prediction module and the new energy output prediction module in sequence according to model calling.

6. A control method for the intelligent operation system of a new energy station according to any one of claims 1 to 5, characterized in that, comprising: inputting the acquired power price disturbance feature data into a price prediction model based on fusion of a time sequence model and an attention mechanism through the price prediction module, to predict the marketized power price in a future period, and output marketized power price prediction results in multiple time scales; inputting the acquired station output spatiotemporal data into a new energy output prediction module based on fusion of time sequence spatial features through the new energy output prediction module, to predict the power generation of a new energy device of the new energy station, and obtain new energy output prediction results; inputting the marketized power price prediction results and the new energy output prediction results as boundary conditions through the energy storage optimization scheduling module, and combining physical constraints, grid constraints and operation constraints as constraint conditions, to construct a multi-objective optimization model taking economy, technology and society as targets; wherein the physical constraints, the grid constraints and the operation constraints include any one or a combination of multiple of the following: energy storage device types, initial capacity, battery cycle life, charging and discharging efficiency, equipment cost, grid load and frequency modulation reserve requirements; and calling the multi-objective optimization model, and iteratively calculating the multi-objective optimization model based on a non-dominated sorting genetic algorithm or a multi-agent optimization algorithm, to output an energy storage device charging and discharging strategy meeting multiple constraint conditions; acquiring site selection condition information corresponding to the new energy station through the planning layout decision module, and receiving resource attribute decision and market attribute decision inputs; the site selection condition information at least includes land availability, access grid capacity, policy incentive information and load center distance; and based on the site selection condition information, the resource attribute decision, the market attribute decision, the marketized power price prediction results, the new energy output prediction results and the energy storage device charging and discharging strategy, constructing a capacity configuration optimization model of new energy devices and energy storage devices; and solving the capacity configuration optimization model through a competitive game analysis method or a Nash equilibrium solving method, to output an optimal capacity configuration scheme of the new energy devices and the energy storage devices.

7. An electronic device, comprising: comprising: a processor; and a memory having computer readable instructions stored thereon, the computer readable instructions, when executed by the processor, implement the method of claim 6.

8. A computer-readable storage medium, characterized in that, a computer program stored thereon, the computer program, when executed by a processor, implements the method of claim 6.

Images