Cost prediction and decomposition method and device for renewable energy power optimal scheduling and storage medium

Abstract

The present disclosure relates to the field of power system optimization scheduling, and particularly relates to a renewable energy power optimization scheduling cost prediction and decomposition method and device and storage medium. The method comprises: obtaining power system operation data, the power system operation data comprising operation data and cost data of multiple renewable energy devices in a power system; determining power optimization scheduling data and cost analysis results according to the power system operation data through a pre-trained target model, the power optimization scheduling data being used to indicate a predicted operation combination scheme of the multiple renewable energy devices with the minimum total system cost, and the cost analysis results comprising a total system cost corresponding to the power optimization scheduling data and / or a cost decomposition result of the total system cost. The present disclosure uses a pre-trained target model to realize the optimization scheduling of a renewable energy power system, accurately predicts and decomposes the cost, and improves the accuracy of power optimization scheduling and cost analysis.

Description

Technical Field

[0001] This disclosure relates to the field of power system optimization dispatch, and in particular to a method, apparatus and storage medium for cost prediction and decomposition of renewable energy power optimization dispatch. Background Technology

[0002] With the intensification of global climate change and the advancement of renewable energy technologies, the proportion of renewable energy in the power systems of various countries is gradually increasing. The integration of a high proportion of renewable energy not only brings volatility to power supply but also increases the complexity of power system dispatch, posing a significant challenge to traditional power system dispatching models.

[0003] When dealing with the dispatch of power systems with a high proportion of renewable energy, related technologies often suffer from challenges such as high dispatch difficulty and low accuracy in cost analysis. These problems become even more pronounced under complex meteorological conditions, such as extreme weather events, and the influence of fluctuations in energy supply and demand. Therefore, how to achieve optimized dispatch of power systems with a high proportion of renewable energy and accurately predict and decompose system costs has become an urgent problem to be solved in the current technological field. Summary of the Invention

[0004] In view of this, this disclosure proposes a method, apparatus and storage medium for cost prediction and decomposition of renewable energy power optimization dispatch.

[0005] According to one aspect of this disclosure, a method for cost prediction and decomposition of optimized dispatch of renewable energy power is provided, the method comprising:

[0006] Acquire power system operation data, which includes operation data and cost data of various renewable energy devices in the power system;

[0007] Based on the power system operation data, power optimization scheduling data and cost analysis results are determined by a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization scheduling data, and the cost analysis results.

[0008] The power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy devices that minimizes the predicted total system cost, and the cost analysis results include the total system cost corresponding to the power optimization dispatch data and / or the cost decomposition results of the total system cost.

[0009] In one possible implementation, the target model includes a scheduling model and an analysis model. The step of determining power optimization scheduling data and cost analysis results based on the power system operation data using a pre-trained target model includes:

[0010] The power system operation data is input into the scheduling model, and the power optimization scheduling data is output. The scheduling model is used to indicate the correspondence between the power system operation data and the power optimization scheduling data.

[0011] The power optimization scheduling data is input into the analysis model, and the cost analysis result is output. The scheduling model is used to indicate the correspondence between the power optimization scheduling data and the cost analysis result.

[0012] In another possible implementation, the scheduling model includes an objective function and preset constraints. The objective function is used to determine the operating combination scheme of various renewable energy devices that minimizes the total cost of the system under the preset constraints. The preset constraints are used to indicate preset operating limitations of various renewable energy devices.

[0013] In another possible implementation, the cost decomposition result includes:

[0014] The result is obtained by decomposing the total system cost according to the target dimensions. The target dimensions include one or more of the following: different geographical locations, different types of renewable energy, different time periods, and different system operating states. The different system operating states include extreme states and normal states. The extreme state is the period within a preset time range that exceeds a preset percentage of the total system cost. The normal state is the period within the preset time range other than the extreme state.

[0015] In another possible implementation, the operational data in the power system operation data includes:

[0016] The renewable energy equipment includes one or more of the following: power capacity factor, power demand data, power generation ratio data, carbon emission factor, and technical constraint indicators. The power capacity factor indicates the operating efficiency of the renewable energy equipment, the power demand data indicates the power consumption of the renewable energy equipment, the power generation ratio data indicates the proportion of the power generation of the renewable energy equipment in the total power generation of the power system, the carbon emission factor indicates the carbon dioxide emissions generated per unit of energy consumption of the renewable energy equipment, and the technical constraint indicators indicate the configuration ratio of at least two types of renewable energy equipment.

[0017] In another possible implementation, the cost data in the power system operation data includes:

[0018] The investment cost and / or operation and maintenance cost of each of the various renewable energy devices, wherein the investment cost indicates the cost of the renewable energy device during construction and installation, and the operation and maintenance cost indicates the cost of the renewable energy device during operation.

[0019] In another possible implementation, the various renewable energy devices in the power system include power generation devices and energy storage devices, wherein the power generation devices include one or more of wind power generation devices, solar power generation devices, hydropower generation devices, nuclear power generation devices, coal power generation devices, and gas power generation devices.

[0020] According to another aspect of this disclosure, a cost prediction and decomposition apparatus for optimized dispatch of renewable energy power is provided, the apparatus comprising:

[0021] The acquisition module is used to acquire power system operation data, which includes operation data and cost data of various renewable energy equipment in the power system;

[0022] The determination module is used to determine power optimization scheduling data and cost analysis results based on the power system operation data and a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization scheduling data and the cost analysis results.

[0023] The power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy devices that minimizes the predicted total system cost, and the cost analysis results include the total system cost corresponding to the power optimization dispatch data and / or the cost decomposition results of the total system cost.

[0024] In one possible implementation, the target model includes a scheduling model and an analysis model, and the determining module is further configured to:

[0025] The power system operation data is input into the scheduling model, and the power optimization scheduling data is output. The scheduling model is used to indicate the correspondence between the power system operation data and the power optimization scheduling data.

[0026] The power optimization scheduling data is input into the analysis model, and the cost analysis result is output. The scheduling model is used to indicate the correspondence between the power optimization scheduling data and the cost analysis result.

[0027] In another possible implementation, the scheduling model includes an objective function and preset constraints. The objective function is used to determine the operating combination scheme of various renewable energy devices that minimizes the total cost of the system under the preset constraints. The preset constraints are used to indicate preset operating limitations of various renewable energy devices.

[0028] In another possible implementation, the cost decomposition result includes:

[0029] The result is obtained by decomposing the total system cost according to the target dimensions. The target dimensions include one or more of the following: different geographical locations, different types of renewable energy, different time periods, and different system operating states. The different system operating states include extreme states and normal states. The extreme state is the period within a preset time range that exceeds a preset percentage of the total system cost. The normal state is the period within the preset time range other than the extreme state.

[0030] In another possible implementation, the operational data in the power system operation data includes:

[0031] The renewable energy equipment includes one or more of the following: power capacity factor, power demand data, power generation ratio data, carbon emission factor, and technical constraint indicators. The power capacity factor indicates the operating efficiency of the renewable energy equipment, the power demand data indicates the power consumption of the renewable energy equipment, the power generation ratio data indicates the proportion of the power generation of the renewable energy equipment in the total power generation of the power system, the carbon emission factor indicates the carbon dioxide emissions generated per unit of energy consumption of the renewable energy equipment, and the technical constraint indicators indicate the configuration ratio of at least two types of renewable energy equipment.

[0032] In another possible implementation, the cost data in the power system operation data includes:

[0033] The investment cost and / or operation and maintenance cost of each of the various renewable energy devices, wherein the investment cost indicates the cost of the renewable energy device during construction and installation, and the operation and maintenance cost indicates the cost of the renewable energy device during operation.

[0034] In another possible implementation, the various renewable energy devices in the power system include power generation devices and energy storage devices, wherein the power generation devices include one or more of wind power generation devices, solar power generation devices, hydropower generation devices, nuclear power generation devices, coal power generation devices, and gas power generation devices.

[0035] According to another aspect of this disclosure, a computing device is provided, the device comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the method described above when executing instructions stored in the memory.

[0036] According to another aspect of this disclosure, a non-volatile computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the method described above.

[0037] According to another aspect of this disclosure, a computer program product is provided, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of a computing device, the processor in the computing device performs the above-described method.

[0038] This disclosure provides a method for cost prediction and decomposition of optimized dispatching of renewable energy power. It involves acquiring power system operation data, including operational and cost data of various renewable energy devices within the power system. Based on this data, a pre-trained target model is used to determine optimized dispatching data and cost analysis results. The target model indicates the correspondence between the power system operation data, optimized dispatching data, and cost analysis results. The optimized dispatching data indicates the operational combination scheme of various renewable energy devices that minimizes the predicted total system cost. The cost analysis results include the total system cost corresponding to the optimized dispatching data and / or the cost decomposition results of the total system cost. In other words, by using a pre-trained target model, this method can more accurately predict the operational combination scheme of various renewable energy devices that minimizes the total system cost and the cost analysis results, thereby achieving optimized dispatching of renewable energy power systems and accurately predicting and decomposing the total system cost. This solves the problems of high dispatching difficulty and low cost analysis accuracy in high-proportion renewable energy power systems in related technologies, thus improving the accuracy of optimized dispatching and cost analysis.

[0039] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0040] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0041] Figure 1 A flowchart illustrating a cost prediction and decomposition method for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure is shown.

[0042] Figure 2 This illustration shows a schematic diagram of the model framework for a cost prediction and decomposition method for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure.

[0043] Figure 3 A flowchart is shown for a cost prediction and decomposition method for optimized scheduling of renewable energy power provided by another exemplary embodiment of this disclosure.

[0044] Figure 4 A schematic diagram illustrating simulation results of the installed capacity of different energy types provided in an exemplary embodiment of this disclosure is shown.

[0045] Figure 5 A schematic diagram illustrating simulation results of power generation from different energy types provided in an exemplary embodiment of this disclosure is shown.

[0046] Figure 6 A schematic diagram of hourly power generation and power demand provided by an exemplary embodiment of this disclosure is shown.

[0047] Figure 7 This illustration shows a schematic diagram of the hourly power system cost decomposition under extreme and normal conditions provided by an exemplary embodiment of this disclosure.

[0048] Figure 8 This illustration shows a schematic diagram of the cost variation contribution analysis of power systems with different energy types provided in an exemplary embodiment of this disclosure.

[0049] Figure 9 A schematic diagram of the structure of a cost prediction and decomposition apparatus for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure is shown.

[0050] Figure 10 This is a block diagram illustrating an apparatus according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0051] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0052] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0053] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0054] While some power dispatch models in related technologies can account for the volatility of renewable energy sources such as wind and solar power, the dispatch efficiency and cost analysis accuracy of the system still need improvement when dealing with a high proportion of renewable energy integration. Furthermore, these technologies do not yet provide comprehensive solutions for cost decomposition of different renewable energy types or for cost comparison analysis under extreme and normal conditions.

[0055] This disclosure provides a cost prediction and decomposition system for optimized dispatching of high-proportion renewable energy power, which solves the problems of high dispatching difficulty and low cost analysis accuracy of high-proportion renewable energy power systems in related technologies. In particular, it addresses complex meteorological conditions and energy supply and demand fluctuations, ensuring the system's operational stability and economy under extreme and normal conditions.

[0056] To address the peak-shaving demands of high-proportion renewable energy power systems under complex and variable weather conditions, this disclosure proposes a cost-optimal hourly power dispatch simulation system. This system integrates different power generation and energy storage technologies to construct a multi-technology collaborative target model, covering various renewable energy types such as wind, solar, thermal, nuclear, hydro, long-term energy storage, and short-term energy storage. It enables multi-period dispatch optimization from hourly to annual levels. First, by collecting and organizing hourly wind and solar capacity factor data, cost information for each renewable energy type, and power generation ratio data, and combining this with a series of power system operation constraints, the system uses cost minimization as the objective function to solve for the annual installed capacity demand of different renewable energy types and their hourly output. This method also has dynamic response capabilities, allowing for flexible adjustments based on real-time weather conditions and power demand, thereby improving the adaptability and accuracy of the dispatch scheme.

[0057] This disclosure also addresses the impact of extreme weather conditions on power dispatch. By integrating meteorological reanalysis data and simulating the volatility and peak-shaving demands of renewable energy sources such as wind and solar power, the system can respond to weather changes in real time, ensuring the stable operation of the power system. Under extreme weather conditions, the system can not only adjust the operating strategies of traditional power generation and energy storage systems according to the supply fluctuations of renewable energy, but also ensure the security and reliability of power supply under extreme circumstances through pre-set reserve capacity and redundancy mechanisms. Furthermore, by simulating the interaction of different technology combinations, the system analyzes the power generation contribution of various technologies under extreme weather and normal conditions, thereby providing decision-makers with a scientific basis for selecting the optimal technology combination during the energy system transition.

[0058] The following describes the cost prediction and decomposition method for optimized scheduling of renewable energy power provided in the embodiments of this disclosure using several exemplary models.

[0059] Please refer to Figure 1 This document illustrates a flowchart of a cost prediction and decomposition method for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure. This embodiment uses the method in a computing device as an example for illustration. The method includes the following steps.

[0060] Step 101: Obtain power system operation data, which includes operation data and cost data of various renewable energy devices in the power system.

[0061] A power system is an electrical energy production and consumption system composed of power generation, transformation, transmission, distribution, and consumption. The power system includes various renewable energy devices, which are those capable of converting energy from renewable resources such as wind, solar, hydro, and biomass. These devices include power generation equipment and energy storage equipment. Power generation equipment includes one or more of the following: wind power generation equipment, solar power generation equipment, hydropower generation equipment, nuclear power generation equipment, coal-fired power generation equipment, and gas-fired power generation equipment. Energy storage equipment includes one or more of the following: long-duration energy storage equipment, short-duration energy storage equipment, and spinning reserve capacity equipment. Long-duration energy storage equipment refers to energy storage equipment capable of storing energy and continuously releasing energy at full power for a period exceeding a first preset duration (e.g., 4 hours or 10 hours). Short-time energy storage devices refer to energy storage devices capable of storing energy and continuously releasing energy at full power for less than a second preset duration (e.g., 1 hour). These devices can quickly respond to control signals, frequently switch between charging and discharging, and exchange active or reactive power with the power system. The first and second preset durations can be the same or different values; this disclosure does not limit this. Spinning standby capacity devices refer to power generation resources that can quickly respond to changes in grid demand. They are typically kept in a standby state to rapidly provide power in the event of a sudden increase in power demand or an unexpected power outage, such as fast-start units in hydropower generation.

[0062] The power system can be a high-proportion renewable energy power system. In a high-proportion renewable energy power system, "high proportion" usually refers to the proportion of renewable energy equipment in the installed capacity, power generation, or energy consumption of the power system being higher than a preset threshold, or the proportion of one or more specific renewable energy devices in the installed capacity, power generation, or energy consumption of the power system being higher than a preset threshold. For example, one or more specific renewable energy devices are wind power generation equipment and solar power generation equipment, and the preset threshold is 90%. This disclosure does not limit this aspect.

[0063] Operational data for renewable energy equipment refers to the data generated by renewable energy equipment during actual operation, including but not limited to power generation, equipment status, efficiency, and energy consumption. Operational data can be obtained by monitoring and recording the operating parameters of renewable energy equipment. Cost data for renewable energy equipment includes the entire lifecycle cost from construction to operation, including investment costs, operation and maintenance costs, and fuel costs (if applicable). Obtaining cost data allows for analysis of the project's financial records, including expenses at each stage of equipment acquisition, installation, maintenance, and decommissioning.

[0064] In some embodiments, the operational data in the power system operation data includes one or more of the following: power capacity factors, power demand data, power generation share data, carbon emission factors, and technical constraints for each of the various renewable energy devices. The cost data in the power system operation data includes the investment costs and / or operation and maintenance costs for each of the various renewable energy devices. The following sections provide a glossary of these data.

[0065] 1. Power Capacity Factor: The power capacity factor is the ratio of actual power generation to the maximum theoretical power generation within a certain period. It is used to indicate the operating efficiency of renewable energy equipment and is particularly important for renewable energy equipment such as wind and solar power generation, as the power generation of these energy sources is greatly affected by weather and seasons.

[0066] 2. Electricity Demand Data: Electricity demand data indicates the electricity demand of renewable energy devices. It reflects changes in electricity demand across different time periods and is typically presented as grid load curve data. This data is crucial for power system dispatching and planning because it helps predict and meet peak and off-peak demand.

[0067] 3. Power Generation Share Data: Power generation share data indicates the proportion of power generation from renewable energy devices in the total power generation of the power system. Data on the power generation share of various renewable energy devices helps to understand the diversity of the power structure and the penetration rate of renewable energy, which is of great significance for formulating energy policies and emission reduction targets.

[0068] 4. Carbon Emission Factor: The carbon emission factor indicates the amount of carbon dioxide emissions generated per unit of energy consumption by renewable energy equipment. For the power system, the carbon emission factor is a key indicator for assessing the environmental impact of electricity production, especially in the context of addressing climate change and promoting a low-carbon transition.

[0069] 5. Technical Constraints: Technical constraints involve the technical parameters and operational limitations of equipment and systems in a power system, such as generation efficiency, transmission capacity, and equipment lifespan. These constraints are crucial for ensuring the safe, reliable, and efficient operation of the power system. Technical constraints can be used to indicate the configuration ratio of at least two renewable energy devices.

[0070] 6. Investment Costs: This indicates the costs incurred during the construction and installation of renewable energy equipment. Investment costs may include equipment purchase, land acquisition, infrastructure construction, and operating expenses. This cost represents the fixed capital invested at the beginning of the project, used for the purchase of major equipment, etc.

[0071] 7. Operation and Maintenance Costs: This refers to the costs incurred during the operation of renewable energy equipment. Operation and maintenance costs are the funds dynamically invested to ensure the normal operation of renewable energy equipment throughout its lifespan, typically including expenses for equipment testing, installation, wear and tear, downtime, labor, inspection, and repair.

[0072] These technical terms cover multiple aspects of power system operation data, including operating and cost data for renewable energy equipment, which are crucial for the planning, operation, and optimization of power systems.

[0073] Step 102: Based on the power system operation data, determine the power optimization dispatch data and cost analysis results through a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization dispatch data, and the cost analysis results. The power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy equipment with the lowest predicted total system cost. The cost analysis results include the total system cost and / or the cost decomposition results of the total system cost corresponding to the power optimization dispatch data.

[0074] This disclosure aims to optimize power system dispatching and provide accurate cost analysis results through advanced data analysis and machine learning technologies. The computing device, using a pre-trained target model, can process power system operation data and output optimized power dispatching data and cost analysis results to support the efficient and economical operation of the power system.

[0075] In one possible implementation, the aforementioned process of determining power system optimization dispatch data and cost analysis results based on a pre-trained target model using power system operation data includes: inputting power system operation data into the target model and outputting power system optimization dispatch data and cost analysis results. That is, the target model is responsible for processing the input power system operation data and outputting power system optimization dispatch data and cost analysis results. This target model can identify the correspondences between power system operation data, power system optimization dispatch data, and cost analysis results, providing the optimal dispatch scheme and cost analysis for the power system.

[0076] In another possible implementation, the aforementioned method of determining optimal power dispatch data and cost analysis results based on power system operation data through a pre-trained target model includes: inputting power system operation data into a dispatch model and outputting optimal power dispatch data, whereby the dispatch model indicates the correspondence between the power system operation data and the optimal power dispatch data; and inputting the optimal power dispatch data into an analysis model and outputting cost analysis results, whereby the dispatch model also indicates the correspondence between the optimal power dispatch data and the cost analysis results. That is, the target model includes a dispatch model and an analysis model, which work together to achieve optimal power system dispatch and cost analysis. The dispatch model is responsible for processing the input power system operation data, determining the optimal power dispatch data according to a pre-trained algorithm, and outputting the optimal power dispatch data for subsequent cost analysis. This model can identify the correspondence between power system operation data and optimal power dispatch data, providing the best dispatch scheme for the power system. The analysis model receives the optimal power dispatch data from the dispatch model, performs cost analysis based on the optimal power dispatch data, and outputs the cost analysis results to support economic decision-making for the power system. This model can indicate the correspondence between power optimization dispatch data and cost analysis results, providing a basis for the economic evaluation of power systems.

[0077] Power dispatch optimization data aims to guide the selection of the lowest-cost operating combination of multiple renewable energy devices. Cost analysis yields the total system cost and its detailed breakdown. In some cases, this data also provides the lowest-cost renewable energy device operating schemes expected within various preset time periods over a specific timeframe. Furthermore, the cost analysis results include not only the total system cost of the target combination schemes within each preset time period but also a detailed cost breakdown. Such analysis helps to more accurately understand and control the cost-effectiveness of renewable energy systems. In some embodiments, power dispatch optimization data is used to indicate target combination schemes for multiple preset time periods within a specific timeframe, where the target combination scheme is the operating combination of multiple renewable energy devices with the predicted lowest total system cost; the cost analysis results include the total system cost and the cost breakdown of the total system cost for each target combination scheme for the multiple preset time periods.

[0078] In some embodiments, the cost decomposition results include: the results of decomposing the total system cost according to target dimensions, which include one or more of different geographical locations, different types of renewable energy, different time periods, and different system operating states. That is, the cost decomposition results provide in-depth cost analysis by breaking down the total system cost into various key dimensions. These dimensions cover geographical locations, renewable energy types, different time periods, and different system operating states. Furthermore, the cost decomposition considers the following aspects:

[0079] 1. Geographical Location Areas: The total system cost is broken down into different geographical locations to reflect the contribution of different regions to the total system cost.

[0080] 2. Renewable Energy Types: The cost analysis is further subdivided into different types of renewable energy, such as wind power and solar power, to identify the impact of each type on costs. In this embodiment, each renewable energy device includes multiple devices of that renewable energy type, which may also be simply referred to as energy type.

[0081] 3. Different time periods: The total system cost is broken down into different time periods in order to analyze the impact of different times on the total system cost.

[0082] 4. System Operating Status: Cost decomposition also includes the operating costs of the power system under extreme and normal conditions. This means different system operating states include extreme and normal conditions. An extreme state is defined as the period within a preset time frame where the cost exceeds a preset percentage of the total system cost. A normal state is the period within the preset time frame excluding extreme states. For example, an extreme state is defined as the period within a preset time frame where the cost exceeds the 90th percentile of the total system cost.

[0083] This multi-dimensional cost breakdown allows for more accurate identification of cost drivers, optimization of resource allocation, and the development of more effective cost control strategies.

[0084] In summary, the embodiments of this disclosure provide a method for cost prediction and decomposition of optimized dispatching of renewable energy power. This method acquires power system operation data, including operational and cost data of various renewable energy devices within the power system. Based on this data, a pre-trained target model is used to determine optimized dispatching data and cost analysis results. The target model indicates the correspondence between the power system operation data, optimized dispatching data, and cost analysis results. The optimized dispatching data indicates the operational combination scheme of various renewable energy devices that minimizes the predicted total system cost. The cost analysis results include the total system cost corresponding to the optimized dispatching data and / or the cost decomposition results of the total system cost. In other words, by using a pre-trained target model, this method can more accurately predict the operational combination scheme of various renewable energy devices that minimizes the total system cost and the cost analysis results, thereby achieving optimized dispatching of renewable energy power systems and accurately predicting and decomposing the total system cost. This solves the problems of high dispatching difficulty and low cost analysis accuracy in high-proportion renewable energy power systems in related technologies, thus improving the accuracy of optimized dispatching and cost analysis.

[0085] The software in this disclosure has been engineered, eliminating the need for cumbersome installation and compilation steps for users. In the Linux operating system, users only need to configure the necessary dependencies, and then personalize the configuration through basic and policy settings. Subsequently, simply submitting the job script will automatically achieve parallel computing for power dispatch simulation across multiple regions, time periods, and energy types. The system development environment can be built on Windows 11.0 and Linux CentOS 7.9 systems, using the Python programming language and project management through the PyCharm integrated development environment. For the hardware environment, a CPU P3 800MHz or higher processor with a clock speed of at least 2.60GHz is recommended, along with 16GB or more of memory to support large-scale data processing and complex calculations.

[0086] The operating system can be a Linux system, and the runtime environment can be Python 3.9.12. The main dependencies include PyCharm 2022.2.4, Matplotlib 3.7.2, Pandas 2.0.3, NumPy 1.24.3, CVXPY 1.4.2, SciPy 1.11.1, Joblib 1.2.0, and GurobiPy 11.0.1. The execution flow of this embodiment is highly flexible and portable; users can directly copy and run the system by configuring the same runtime environment. Users can manage dependencies through virtual environments, such as using virtualenv or conda to create isolated Python environments and installing the aforementioned dependency libraries via pip or conda.

[0087] During operation, users can submit jobs through the Slurm job management system. First, a `sbatch` job submission script needs to be created, and then the `sbatch` command is used to submit tasks, thus achieving parallel simulation of power dispatch. After successful system execution, simulation results and runtime information will be output to the specified path. Based on the results, the system can simulate power dispatch across multiple regions and energy types, including the generation and storage of renewable energy sources such as wind, solar, nuclear, hydro, and thermal power.

[0088] Furthermore, this disclosure also features automatic data visualization capabilities, enabling the display and analysis of the aforementioned data. It can showcase determined power system optimization dispatch data and cost analysis results, including predictions for key parameters such as system cost, emissions, and energy storage status. These visualizations are output in the form of charts or reports, providing crucial information for optimizing power system dispatch strategies and decision-making.

[0089] In an illustrative example, such as Figure 2The diagram illustrates a model framework for a cost prediction and decomposition method for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure, showing the main modules involved and their interrelationships. The model framework is divided into three main parts: an input section, a processing section, and an output section. The input section includes: power curves, hourly meteorological data, geographical constraints, capacity factor algorithm, hourly wind and solar power output, sectoral power generation ratio, and power load curves. The processing section includes: system operating constraints, such as minimum output, energy storage balance, and supply-demand balance. Cost and emission information includes investment costs, operating costs, and emission factors. Based on the cost-optimal objective function, power supply is considered, including solar, wind, coal, energy storage, hydro, nuclear, gas, and oil power. The output section includes: sectoral installed capacity structure, sectoral power generation, carbon emissions, hourly output curves, annual total system cost, hourly system cost, and hourly sectoral cost. The overall model framework describes how to optimize power dispatch by considering various input data and constraints, using an objective function to achieve cost minimization, and ultimately outputs relevant power dispatch optimization data and cost analysis results. The definitions of some technical terms used in the diagram are as follows:

[0090] 1. Power curve: A curve describing the relationship between the output power of a wind turbine or photovoltaic panel under different wind speeds or light intensities and these conditions.

[0091] 2. Hourly meteorological data: refers to meteorological condition data recorded every hour, such as wind speed, temperature, humidity, solar radiation, etc., which are used to predict the power generation of renewable energy.

[0092] 3. Geographical constraints: These refer to the limitations imposed by geographical location on the layout and operation of the power system, such as topography, land use restrictions, and environmental regulations.

[0093] 4. Capacity factor algorithm: An algorithm used to calculate the ratio of the actual power generation of a power generation device to its theoretical maximum power generation within a certain period of time.

[0094] 5. Wind and solar power output per hour: refers to the amount of electricity generated by wind and solar power generation equipment per hour.

[0095] 6. Power generation by sector: This refers to the proportion of power generation by different sectors (i.e., different power generation equipment) in the total power generation.

[0096] 7. Electricity load curve: A curve that describes how electricity demand changes over time, typically used for forecasting and planning electricity supply.

[0097] 8. System operation constraints: These refer to the restrictions that a power system must comply with during operation, such as the maximum and minimum output of equipment and grid stability requirements.

[0098] 9. Cost and Emissions Information: This includes data on power generation costs (such as investment costs and operating costs) and environmental emissions (such as carbon dioxide emissions).

[0099] 10. Cost-optimal objective function: A mathematical function used in power dispatch to minimize total cost (including generation cost and environmental cost).

[0100] 11. Power supply: refers to the electricity provided by various power generation methods in the power system, including solar energy, wind energy, coal power, energy storage, hydropower, nuclear energy, gas power, oil power, etc.

[0101] 12. Installed capacity structure by sector: refers to the distribution of installed capacity in different power generation sectors.

[0102] 13. Power generation by sector: refers to the power generation of different power generation sectors within a certain period of time.

[0103] 14. Carbon emissions: refers to the total amount of carbon dioxide emitted during the power generation process.

[0104] 15. Hourly power output curve: A curve that describes the change in the total power generation of the power system or the power generation of a specific power generation sector every hour.

[0105] 16. Annual total system cost: refers to the total cost of the power system in one year, including the cost of all power generation sectors.

[0106] 17. Hourly system cost: refers to the total cost of the power system in each hour.

[0107] 18. Hourly departmental cost: refers to the cost of different power generation departments in each hour.

[0108] Please refer to Figure 3 This illustration shows a flowchart of a cost prediction and decomposition method for optimized scheduling of renewable energy power provided in another exemplary embodiment of this disclosure. This embodiment illustrates the method in a computing device. The method includes the following steps.

[0109] Step 301: Organize and import power system operation data.

[0110] The processing and import of power system operation data is a crucial step in ensuring the consistency and accuracy of all data before it is incorporated into the model. Hourly data on power capacity factors, power demand, generation share, investment costs, operation and maintenance costs, carbon emission factors, and technical constraints are processed using defined custom functions and then imported into the computing equipment to ensure the accuracy and consistency of subsequent analyses. The main steps of this process are as follows:

[0111] 1. Obtain hourly electricity capacity factor and electricity demand data. For example, the function "get_supply" can be used to obtain hourly wind energy capacity factor (CF_wind), solar energy capacity factor (CF_solar), and hourly electricity demand data for different countries or regions. This data will be used in the supply and demand balance calculation in the model to ensure that the electricity supply can meet the demand each hour.

[0112] 2. Obtain power generation percentage data. For example, the function "supply_pro" can be used to obtain power generation percentage data for each sector. These sectors cover different renewable energy types such as nuclear power, hydropower, and thermal power. The thermal power portion also includes the percentages of coal, oil, and natural gas. This step provides basic data for the optimized allocation of each renewable energy type.

[0113] 3. Calculate cost data and carbon emission factors. To calculate the unit investment cost, fixed operating costs, and variable operating costs for each department, the "get_costGHG" function can be used, where the unit investment cost is calculated based on the Capital Recovery Factor (CRF). The formula is:

[0114] C fix,i =C fix_cap,i ×CRF i +C fix_OM,i

[0115]

[0116] Among them, C fix,i Let C represent the annual fixed cost of the i-th type of renewable energy equipment. fix_cap,i Let C represent the overnight capital cost of the i-th type of renewable energy equipment. fix_OM,i This represents the fixed operation and maintenance cost of the i-th type of renewable energy equipment. (CRF) i It is the capital recovery factor of the i-th type of renewable energy equipment, which depends on the discount rate R of the i-th type of renewable energy equipment. i and lifespan L i .

[0117] 4. Obtain technical constraint indicators. For example, the function "get_ratio" can be used to obtain the constraint indicators for various renewable energy devices. These indicators are used to determine the configuration ratio of at least two renewable energy devices (such as wind power generation equipment and solar power generation equipment) to ensure the rational use of each technology during dispatching.

[0118] These steps ensure that the processing and import of power system operation data are both accurate and efficient, laying a solid foundation for subsequent power dispatch simulation and analysis.

[0119] Step 302: Based on the power system operation data, determine the power optimization dispatch data through the target model.

[0120] The power system utilizes various renewable energy devices, including power generation equipment and energy storage equipment. Power generation equipment includes one or more of wind power, solar power, hydropower, nuclear power, coal power, and gas power. Energy storage equipment includes one or more of long-duration energy storage, short-duration energy storage, and spinning reserve capacity. During the scheduling process, based on the power generation characteristics and cost curves of each renewable energy device, model optimization can automatically select the optimal combination of power generation and energy storage to meet power demand in different time periods. In some embodiments, the target model defines multiple power generation modules and energy storage modules, each initialized according to its characteristics and constraints. Supply and demand balance constraints ensure that hourly power demand can be met through power generation and energy storage. Power generation ratio constraints, capacity limits, and ramp rate constraints ensure stable system operation. Energy storage modules achieve supply and demand balance through charging and discharging regulation. Ultimately, the total system cost is minimized through an objective function, and an optimized objective solver (such as the GUROBI solver) is used to solve for the optimal scheduling scheme. The modules coordinate with each other through defined interfaces to ensure the overall stability and optimization effect of the system. The main steps of this process are as follows:

[0121] 1. Module Definition and Initialization. The target model defines multiple power generation and energy storage modules to simulate wind, solar, hydro, nuclear, coal, oil, natural gas, thermal power, and CCUS (Carbon Capture, Utilization, and Storage) technologies. Each module is defined based on its specific power generation characteristics and corresponding constraints are set. For example, the wind power module uses variables `capwind` and `genwind` to represent the installed capacity and hourly power generation of the wind power generation equipment, respectively, and considers the wind capacity factor (CF_wind) and power supply constraints; the solar power module uses variables `capsolar` and `gensolar` to define the installed capacity and hourly power generation of the solar power generation equipment, considering the solar capacity factor (CF_solar) and power generation ratio constraints; the energy storage module uses variables `Storcha` and `Stordis` to represent the charging and discharging status of the energy storage equipment. The capacity of the energy storage module is limited by physical constraints; the long-term energy storage capacity can be 16 times the energy storage power, and the short-term energy storage capacity can be 4 times the energy storage power.

[0122] 2. Definition of Supply-Demand Balance Constraint. The supply-demand balance constraint of the model ensures that the power output of all renewable energy generation and storage devices can meet the demand in each hour, i.e., the power load in hour t. t It should be equal to the power generation of all energy types of power generation equipment (supply) t) and the discharge capacity of energy storage devices (battary) dis,t The sum of ( ) minus the charging amount of the energy storage device (battary) cha,t The formula is as follows:

[0123] demand t =supply t +battary dis,t -battary cha,t

[0124]

[0125] Where typen represents the total number of energy types of power generation equipment, Gen i,t Let be the power generation of the i-th type of renewable energy device in hour t. These represent the discharge amounts from short-term and long-term energy storage devices, respectively. These represent the charging power from short-term and long-term energy storage devices, respectively.

[0126] 3. Definition of Generation Ratio Constraints. Generation ratio constraints ensure that the proportion of each energy type's power generation in the entire power system meets a pre-set target. Through these constraints, the model can reflect the requirements of policy objectives or market rules regarding the generation ratio of different energy types, thereby achieving a specific energy structure during dispatching. Generation ratio constraints are achieved by ensuring that the total generation share of each energy type meets a specific target. The formula is as follows:

[0127]

[0128] Where Hrs is the total number of hours within the scheduling period, the scheduling period is a preset time range, and Gen i,t Share represents the power generation of the i-th renewable energy device in hour t. i This represents the target power generation ratio of the i-th type of renewable energy equipment, that is, the proportion of power generation of this type of energy to the total power generation during the entire dispatch period.

[0129] 4. Definition of Capacity Limitation. The model limits the capacity of various energy types and energy storage devices. The charging and discharging power and capacity of energy storage devices are physically limited to ensure that they do not exceed their design capacity during operation. The system is required to maintain a certain spinning reserve capacity to cope with sudden load changes or generator failures. Various power supply types (Gen) are also considered. i,t It should be within the preset lower limit value and upper limit value The formula is as follows:

[0130]

[0131] Among them, Cap i It is the installed capacity of the i-th type of renewable energy equipment.

[0132] The power generation of wind and solar energy is limited by the wind and solar capacity factors and the installed capacity, as shown in the following formula:

[0133] 0≤Gen w,t ≤Cap w ×CF w,t

[0134] 0≤Gen s,t ≤Cap s ×CF s,t

[0135] Among them, Gen w,t Gen s,t Cap represents the power generation of wind and solar energy in hour t, respectively. w Cap s These represent the installed capacity of wind power and solar power, respectively, CF w,t CF s,t Let represent the capacity factors of wind energy and solar energy in hour t, respectively.

[0136] 5. Definition of Energy Storage Module Constraints. In the target model, the energy storage module plays a crucial regulatory role, achieving a balance in power supply through charging and discharging operations at different time periods. The constraints on the energy storage module mainly include charging and discharging operation limitations, state limitations, the impact of degradation rate, and its interaction with the overall system.

[0137] The charging and discharging operations of energy storage modules are limited by the power capacity of the energy storage device. During each time period, the charging and discharging power of the energy storage system must meet the following conditions, as shown in the formula below:

[0138]

[0139] in, This represents the charging power of the s-th type of energy storage device in hour t. Let represent the discharge power of the s-th type of energy storage device in hour t. It is the power capacity of the s-th type of energy storage device, ensuring the safe operation of the energy storage device within physical constraints.

[0140] State of Charge (SOC) of energy storage devices s,t The state of energy (SGE) represents the energy storage level of an energy storage system at a specific moment, and is affected by the system's charge / discharge efficiency and degradation rate. Changes in the state of energy storage can be described by the following formula:

[0141]

[0142] Among them, SOC s,t SOC represents the energy storage capacity of the s-th type of energy storage device in hour t. s,t-1 eff represents the energy storage capacity of the s-th type of energy storage device in the (t-1)-th hour. s,cha ,eff s,dis Let denot s_i represent the charging efficiency and discharging efficiency of the s-th type of energy storage device, respectively. s This represents the attenuation rate of the s-th type of energy storage device.

[0143] To ensure the safe operation of energy storage devices, SOC s,t The following conditions must also be met, as shown in the formula below:

[0144]

[0145] Among them, SOC s,min SOC s,max These represent the minimum energy limit and maximum energy limit of the s-th type of energy storage device, respectively. It is the upper limit of the energy capacity of the s-th type of energy storage device.

[0146] The spinning reserve capacity constraint ensures that the system has sufficient reserve capacity when faced with sudden load changes, as shown in the following formula:

[0147]

[0148] Among them, res_spin s,t This represents the spinning reserve capacity provided by the s-th type of energy storage device in hour t. SOC represents the installed capacity of the s-th type energy storage system. t Gen represents the energy storage capacity of the s-th type energy storage system at time t. w,t Gen s,t Spin represents the power generation of the wind power generation equipment and the solar power generation equipment in hour t, respectively. min It is the minimum share limit for the total power generation of wind power generation equipment and solar power generation equipment.

[0149] Energy storage devices not only influence system operation through their own charging and discharging behavior, but also interact with other power generation equipment to cope with supply and demand fluctuations and sudden load changes. When the system is short of power, energy storage devices fill the gap by releasing stored energy; while when there is a power surplus, energy storage devices absorb the excess power by charging, maintaining the system's supply and demand balance.

[0150] 6. Definition of the Objective Function. The objective function is the core of the scheduling model, defining the final goal the system aims to achieve during optimization. The scheduling model includes the objective function and preset constraints. The objective function determines the optimal combination of various renewable energy devices that minimizes the total system cost while satisfying the preset constraints. The preset constraints indicate the pre-defined operational limitations of these renewable energy devices. In this model, the primary objective of the objective function is to minimize the total system cost of the power system. This objective function comprehensively considers fixed investment costs, fixed operation and maintenance costs, and variable operating costs to optimize the power dispatch strategy while satisfying all constraints. The formula is as follows:

[0151] minC total =min(C fix +C var )

[0152]

[0153] C op_var =C gen +C stor

[0154]

[0155] Among them, C total C represents the total system cost of the power system. fix Cap represents the sum of fixed investment costs and fixed operation and maintenance costs of a power system. i This represents the installed capacity of the i-th type of power generation equipment. This represents the energy capacity of the s-th type of energy storage device. Let C represent the fixed operation and maintenance costs of the i-th type of power generation equipment and the s-th type of energy storage equipment, respectively. op_var C is the sum of the variable operating costs of power generation equipment and energy storage equipment. gen C stor Gen represents the variable operating costs of power generation equipment and energy storage equipment, respectively. i,t , Let represent the power generation and operating cost of the i-th type of power generation equipment in t hours, respectively. Let represent the charging power and discharging power of the s-th type of energy storage device in hour t, respectively. Let $\frac{s}{s}$ represent the charging cost and discharging cost of the $s$-th type of energy storage device, respectively.

[0156] 7. Optimization Solution. After defining the objective function and all constraints, the model's final task is to find the optimal solution using an optimization solver, i.e., the generation and energy storage dispatch scheme that minimizes the objective function under given constraints. In this model, an objective solver is used for optimization. During the solution process, a mathematical model is first constructed based on the input objective function and constraints, and then an iterative algorithm is used to gradually approach the optimal solution. In each iteration, the solver evaluates the feasibility of the current solution and the objective function value, and adjusts according to the constraints until the optimal solution is found or a preset stopping criterion is reached. After the solution is completed, the model outputs the optimal solution as power optimization dispatch data, including the predicted operating combination scheme of multiple renewable energy devices that minimizes the total system cost, i.e., it can include the dispatch status of each generation device and each energy storage device in different time periods. The simulation results can provide a reference for actual power system operation to achieve optimal economic benefits and carbon emission control.

[0157] Step 303: Based on the power optimization dispatch data, perform annual-scale installed capacity and system cost accounting.

[0158] Annual-scale installed capacity and system cost accounting is the process of evaluating the overall economic efficiency of a power system over a year. This process primarily calculates the installed capacity, power generation, and total system cost for the entire year, while simultaneously compiling hourly output data to ensure data completeness and accuracy, providing a foundation for annual analysis and optimization. Installed capacity refers to the total capacity of all generating equipment in the power system, i.e., the maximum power they can generate at full load. Power generation refers to the actual electrical energy generated by the power system within a certain period. Total system cost includes all costs related to power system operation, such as generation costs, maintenance costs, and fuel costs. Output data refers to the data records of the power generation or discharge status of various generating or energy storage devices in the power system at a specific point in time, usually recorded hourly, including wind and solar power curtailment and energy storage charging and discharging. Wind and solar power curtailment refers to the data on the amount of electricity generated by wind and solar power generation equipment that cannot be absorbed by the grid due to grid dispatching, technical limitations, or insufficient market demand, thus forcing a reduction or cessation of power generation. Energy storage charging and discharging is used to indicate the charging and discharging amounts of energy storage devices in the power system. The process of annual-scale installation and system cost accounting may include the following steps:

[0159] 1. Calculation and compilation of installed capacity. The installed capacity of various renewable energy devices in the power system is calculated, and the results are compiled into annual data. All data will be summarized and recorded on an annual basis; installed capacity data is the foundation for system cost accounting.

[0160] 2. Calculation and Compilation of Power Generation. Calculate the hourly power generation data for each of the various renewable energy devices in the power system, and compile the hourly power generation data into an annual total power generation. The hourly power generation data for each type of renewable energy device will be aggregated into annual data and recorded according to renewable energy type. In addition, the hourly wind and solar power curtailment will also be compiled; this data will support the assessment of system performance and optimization potential.

[0161] 3. System Cost Calculation. Calculate the total system cost on an annual scale. The calculation results include the total fixed cost of all power generation equipment and the total variable operating cost of all power generation equipment and energy storage equipment. The cost calculation method can refer to the relevant formulas in step 302.

[0162] 4. Hourly Output Data Processing. Hourly output data is a detailed record of system operation, covering the actual operating status of each type of power generation and energy storage equipment throughout the year. This step involves processing the hourly output data into detailed data frames, including hourly power generation (categorized by renewable energy type), hourly charging and discharging status of energy storage equipment, and hourly wind and solar power curtailment. The processed data will be saved and output to a designated file for subsequent analysis and visualization.

[0163] In some embodiments, such as Figure 4 As shown, this diagram illustrates simulation results of the installed capacity of different energy types provided in an exemplary embodiment of this disclosure, demonstrating the installed capacity demand of various renewable energy devices in the system. The bar chart displays the installed capacity of different energy types (unit: MW), and the pie chart displays the percentage of different energy types in the total capacity. These charts provide a visual comparison of the proportion and absolute value of different energy types in the total installed capacity.

[0164] In some embodiments, such as Figure 5 As shown, it illustrates a schematic diagram of the simulation results of power generation of different energy types provided by an exemplary embodiment of this disclosure, showing the simulation results (unit: MWh) of power generation of various renewable energy devices under different installed capacity conditions.

[0165] Step 304: Based on the power optimization dispatch data, perform hourly cost decomposition and analysis to obtain cost analysis results.

[0166] The computing device can use cost decomposition algorithms to break down the total system cost hourly by renewable energy type and distinguish between extreme and normal conditions, providing a multi-faceted basis for cost analysis.

[0167] For example, an extreme state is defined as the period exceeding the 90th percentile of the total system cost within a preset time range. Cost analysis results include cost comparisons of various renewable energy types and cost analysis under extreme conditions. The final cost analysis results are presented in chart form to help users better understand and analyze the system's economics under different scenarios. The cost analysis process may include the following steps:

[0168] 1. Hourly Cost Decomposition. This step involves a thorough analysis and decomposition of the system cost hourly, specifically the hourly allocation of fixed and variable costs. This process begins by weighting the fixed costs for each hour based on power generation, then normalizing the weights and combining them with the unit fixed cost to calculate the hourly fixed cost. Next, the hourly variable cost is calculated based on the hourly power generation and the unit variable cost. Finally, the hourly fixed and variable costs are added together to obtain the total hourly system cost. The hourly fixed cost is allocated according to the power generation weight, using the following formula:

[0169]

[0170] in, This represents the fixed cost weight of the i-th type of renewable energy equipment in the first hour. Gen represents the fixed cost weight of the i-th type of renewable energy equipment in hour t. i,1 Gen represents the power generation of the i-th renewable energy device in the first hour. i,t Gen represents the power generation of the i-th renewable energy device in hour t. i,t-1 This represents the power generation of the i-th type of renewable energy device in the (t-1)-th hour.

[0171] Then, by combining the fixed cost weights with the total fixed cost of the technology, the hourly fixed cost is calculated as follows:

[0172]

[0173] in, Let C represent the total fixed cost of the i-th type of renewable energy device in hour t. fix,i This represents the total fixed cost of the i-th type of renewable energy equipment.

[0174] Variable costs are calculated based on hourly power generation and unit variable cost, using the following formula:

[0175]

[0176] in, Represents the unit variable cost of the i-th type of renewable energy equipment. Let represent the total system cost of the i-th type of renewable energy equipment in hour t.

[0177] Ultimately, the total system cost C per hour i,t For fixed costs and variable costs The sum is calculated using the following formula:

[0178]

[0179] 2. Distinguishing Between Extreme and Normal Costs and Cost Analysis. To analyze the system's cost performance under different conditions in more detail, hourly costs are distinguished between extreme and normal conditions. Within each hour, the extreme condition is defined as the period exceeding the 90th percentile of the total system cost for that hour; the remaining periods are considered normal. The formula for distinguishing between extreme and normal conditions is:

[0180] P90(C i,t ) = pencentile(C i,t ,90)

[0181] Among them, P90(C i,t Let $\frac{i}{t}$ represent the 90th percentile of the total system cost for the $i$-th renewable energy device in hour $t$. Periods exceeding this percentile are considered extreme periods. This formula allows us to identify extreme periods and calculate the average cost, peak cost, and cost performance of other renewable energy types under both extreme and normal conditions.

[0182] 3. Compilation and Output of Cost Analysis Results. The above analysis results will be compiled, and the cost data for each renewable energy type will be summarized into a comprehensive report and output to the specified file format. The output will include hourly cost breakdown results, a comparison analysis of extreme and normal state costs, and cost analysis results for each renewable energy type.

[0183] 4. Data Integrity Check and Output. After data processing, all data will be checked for completeness and accuracy to ensure that the data for each hour is accurate and without omissions or anomalies. The checked data will be output to a specified data format file (such as an Excel file) or other data format files as the basis for system analysis and reporting.

[0184] In some embodiments, such as Figure 6The diagram illustrates hourly power generation and demand, as provided in an exemplary embodiment of this disclosure, reflecting the supply and demand balance of the power system on an hourly scale. The horizontal axis represents time (hours), from 0 to 8000 hours. The vertical axis represents power generation (unit: MW), from -40000MW to 80000MW. The diagram shows the variations in various power supply and demand over different time periods, as well as the charging and discharging activities of energy storage devices.

[0185] In some embodiments, such as Figure 7 The diagram illustrates an exemplary embodiment of this disclosure, showing the hourly power system cost breakdown under extreme and normal conditions, demonstrating the variation of system costs under different weather conditions. These charts and maps illustrate the variation of global power system costs under different scenarios (SSP126 and SSP245), and the cost distribution under extreme and normal conditions. SSP126 and SSP245 are two scenarios within the Shared Socioeconomic Pathways (SSPs).

[0186] In some embodiments, such as Figure 8 As shown, this diagram illustrates the contribution analysis of power system cost changes for different energy types according to an exemplary embodiment of this disclosure, further analyzing the impact of various renewable energy devices on the total system cost. The diagram shows the changes in power system costs in different regions under two different scenarios (SSP126 and SSP245). The diagram is divided into two parts, a and b, corresponding to scenarios SSP126 and SSP245, respectively. Tables in each part list the power system cost changes in different regions, including changes in total cost, various energy costs, capacity factor, and electricity load. The numbers in the tables represent the percentage change in cost; positive numbers indicate cost increases, and negative numbers indicate cost decreases. The last column of the table, "Extreme," indicates the cost change under extreme conditions. Furthermore, each part of the table has a heading below it, indicating the top 10 regions with the largest increases in system costs under that scenario.

[0187] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the embodiments of this disclosure and are not intended to limit them. Those skilled in the art should understand that various modifications or equivalent substitutions can be made to the technical solutions in the foregoing embodiments without departing from the spirit and scope of the embodiments of this disclosure. For example, users can adjust scheduling strategies, optimize targets and operating parameters according to specific application requirements, or implement the embodiments of this disclosure in different hardware and software environments. The software system of the embodiments of this disclosure can be compatible with various job management systems through custom configuration and supports various types of energy scheduling simulations, ensuring the flexibility and adaptability of the system.

[0188] This disclosure primarily utilizes software implementation, employing Python code that runs on a general-purpose computer or server to simulate and optimize power data. Furthermore, this disclosure can also incorporate hardware acceleration devices (such as GPUs and TPUs) for more efficient computational processing. The computer program product can be stored in a computer-readable storage medium (such as a hard disk, optical disk, or flash memory), and executes the described functions via computer instructions. The implementation methods of this disclosure have been verified in Windows and Linux environments and can run stably under various hardware configurations, making it suitable for power system simulations of different scales and complexities.

[0189] In summary, through the above steps, the embodiments of this disclosure can achieve optimized scheduling of high-proportion renewable energy power systems, providing accurate cost prediction and decomposition results, and offering a scientific basis for the economic operation and policy formulation of power systems. Simultaneously, the system has good scalability, adapting to different regional meteorological conditions and application scenarios, providing a scientific reference for renewable energy power dispatch simulation.

[0190] The following are device embodiments of the present disclosure. For parts not described in detail in the device embodiments, please refer to the technical details disclosed in the above method embodiments.

[0191] Please refer to Figure 9 This illustration shows a schematic diagram of a cost prediction and decomposition apparatus for optimized scheduling of renewable energy power provided in an exemplary embodiment of this disclosure. The apparatus can be implemented, in whole or in part, through software, hardware, or a combination of both, as a computing device. The apparatus includes an acquisition module 92 and a determination module 94.

[0192] The acquisition module 92 is used to acquire power system operation data, which includes the operation data and cost data of various renewable energy equipment in the power system;

[0193] The determination module 94 is used to determine the power optimization dispatch data and cost analysis results based on the power system operation data and a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization dispatch data, and the cost analysis results.

[0194] Among them, the power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy equipment with the lowest predicted total system cost. The cost analysis results include the total system cost and / or the cost decomposition results of the total system cost corresponding to the power optimization dispatch data.

[0195] In one possible implementation, the target model includes a scheduling model and an analysis model, and the determination module 94 is further used for:

[0196] Power system operation data is input into the scheduling model, and power optimization scheduling data is output. The scheduling model is used to indicate the correspondence between power system operation data and power optimization scheduling data.

[0197] Power optimization scheduling data is input into the analysis model, and cost analysis results are output. The scheduling model is used to indicate the correspondence between power optimization scheduling data and cost analysis results.

[0198] In another possible implementation, the scheduling model includes an objective function and preset constraints. The objective function is used to determine the operating combination scheme of multiple renewable energy devices that minimizes the total system cost under the preset constraints. The preset constraints are used to indicate the preset operating limitations of multiple renewable energy devices.

[0199] In another possible implementation, the cost decomposition results include:

[0200] The result is obtained by decomposing the total system cost according to the target dimensions. The target dimensions include one or more of the following: different geographical regions, different types of renewable energy, different time periods, and different system operating states. Different system operating states include extreme states and normal states. Extreme states are the periods within a preset time range that exceed a preset percentage of the total system cost, while normal states are the periods within a preset time range other than extreme states.

[0201] In another possible implementation, the operational data in the power system operation data includes:

[0202] The data includes one or more of the following: power capacity factor, power demand data, power generation share data, carbon emission factor, and technical constraint indicators for various renewable energy devices. The power capacity factor is used to indicate the operating efficiency of the renewable energy devices. The power demand data is used to indicate the power demand of the renewable energy devices. The power generation share data is used to indicate the proportion of the power generation of the renewable energy devices in the total power generation of the power system. The carbon emission factor is used to indicate the carbon dioxide emissions generated per unit of energy consumption of the renewable energy devices. The technical constraint indicators are used to indicate the configuration ratio of at least two types of renewable energy devices.

[0203] In another possible implementation, cost data in the power system operation data includes:

[0204] The investment cost and / or operation and maintenance cost of various renewable energy devices are as follows: investment cost indicates the cost of constructing and installing the renewable energy device, and operation and maintenance cost indicates the cost of operating the renewable energy device.

[0205] In another possible implementation, the power system includes a variety of renewable energy devices, including power generation devices and energy storage devices. The power generation devices include one or more of the following: wind power generation devices, solar power generation devices, hydropower generation devices, nuclear power generation devices, coal power generation devices, and gas power generation devices.

[0206] It should be noted that the above embodiments only illustrate the division of the above functional modules when implementing the device. In actual applications, the above functions can be assigned to different functional modules according to actual needs, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0207] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0208] This disclosure also provides a computing device, which includes: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described method when executing the instructions stored in the memory.

[0209] This disclosure also provides a non-volatile computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the method described above.

[0210] This disclosure also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code, wherein when the computer-readable code is run in a processor of a computing device, the processor in the computing device performs the above-described method.

[0211] Figure 10 This is a block diagram illustrating an apparatus 1900 according to an exemplary embodiment of the present disclosure. For example, apparatus 1900 may be provided as a server or terminal device for performing the above-described method. (Refer to...) Figure 10 The apparatus 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0212] Device 1900 may also include a power supply component 1926 configured to perform power management of device 1900, a wired or wireless network interface 1950 configured to connect device 1900 to a network, and an input / output interface 1958 (I / O interface). Device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM macOS X TM Unix TM Linux TM FreeBSD TM Or similar.

[0213] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of the device 1900 to perform the above-described method.

[0214] This disclosure can be a system, method, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for causing a processor to implement various aspects of this disclosure.

[0215] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0216] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0217] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0218] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0219] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0220] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0221] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0222] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A cost prediction and decomposition method for renewable energy power optimal scheduling, characterized in that, The method includes: Acquire power system operation data, which includes operation data and cost data of various renewable energy devices in the power system; Based on the power system operation data, power optimization scheduling data and cost analysis results are determined by a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization scheduling data, and the cost analysis results. The power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy devices that minimizes the predicted total system cost, and the cost analysis results include the total system cost corresponding to the power optimization dispatch data and / or the cost decomposition results of the total system cost.

2. The method of claim 1, wherein, The target model includes a scheduling model and an analysis model. The process of determining power optimization scheduling data and cost analysis results using the pre-trained target model based on the power system operation data includes: The power system operation data is input into the scheduling model, and the power optimization scheduling data is output. The scheduling model is used to indicate the correspondence between the power system operation data and the power optimization scheduling data. The power optimization scheduling data is input into the analysis model, and the cost analysis result is output. The scheduling model is used to indicate the correspondence between the power optimization scheduling data and the cost analysis result.

3. The method of claim 2, wherein, The scheduling model includes an objective function and preset constraints. The objective function is used to determine the operating combination scheme of various renewable energy devices that minimizes the total cost of the system under the preset constraints. The preset constraints are used to indicate the preset operating limitations of various renewable energy devices.

4. The method according to any one of claims 1 to 3, characterized in that, The cost breakdown results include: The result is obtained by decomposing the total system cost according to the target dimensions. The target dimensions include one or more of the following: different geographical locations, different types of renewable energy, different time periods, and different system operating states. The different system operating states include extreme states and normal states. The extreme state is the period within a preset time range that exceeds a preset percentage of the total system cost. The normal state is the period within the preset time range other than the extreme state.

5. The method according to any one of claims 1 to 3, characterized in that, The operational data in the power system operation data includes: The renewable energy equipment includes one or more of the following: power capacity factor, power demand data, power generation ratio data, carbon emission factor, and technical constraint indicators. The power capacity factor indicates the operating efficiency of the renewable energy equipment, the power demand data indicates the power consumption of the renewable energy equipment, the power generation ratio data indicates the proportion of the power generation of the renewable energy equipment in the total power generation of the power system, the carbon emission factor indicates the carbon dioxide emissions generated per unit of energy consumption of the renewable energy equipment, and the technical constraint indicators indicate the configuration ratio of at least two types of renewable energy equipment.

6. The method according to any one of claims 1 to 3, characterized in that, The cost data in the power system operation data includes: The investment cost and / or operation and maintenance cost of each of the various renewable energy devices, wherein the investment cost indicates the cost of the renewable energy device during construction and installation, and the operation and maintenance cost indicates the cost of the renewable energy device during operation.

7. The method according to any one of claims 1 to 3, characterized in that, The various renewable energy devices in the power system include power generation equipment and energy storage equipment. The power generation equipment includes one or more of the following: wind power generation equipment, solar power generation equipment, hydropower generation equipment, nuclear power generation equipment, coal power generation equipment, and gas power generation equipment.

8. A device for cost prediction and decomposition of renewable energy power optimal scheduling, characterized in that, The device includes: The acquisition module is used to acquire power system operation data, which includes operation data and cost data of various renewable energy equipment in the power system; The determination module is used to determine power optimization scheduling data and cost analysis results based on the power system operation data and a pre-trained target model. The target model is used to indicate the correspondence between the power system operation data, the power optimization scheduling data and the cost analysis results. The power optimization dispatch data is used to indicate the operating combination scheme of multiple renewable energy devices that minimizes the predicted total system cost, and the cost analysis results include the total system cost corresponding to the power optimization dispatch data and / or the cost decomposition results of the total system cost.

9. A computing device, comprising: The device includes: processor; Memory used to store processor-executable instructions; The processor is configured to implement the method of any one of claims 1 to 7 when executing instructions stored in the memory.

10. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein, When the computer program instructions are executed by the processor, they implement the method described in any one of claims 1 to 7.

Images