Power transaction auxiliary decision-making management method, device and equipment and storage medium

Abstract

The invention is applicable to the technical field of power transaction and energy management, and provides a power transaction aid decision management method, which comprises the following steps of: analyzing and predicting a power market environment through an energy large model according to power transaction environment information to obtain an energy prediction result, and performing decision management on the power market environment on the basis of the energy prediction result. The energy scheduling strategy is generated for the electricity market environment through the multi-target optimization model, and the electricity transaction in the electricity market environment is scheduled according to the energy scheduling strategy, so that the decision-making balance and comprehensiveness are improved, the method can better adapt to the complex scenes such as large-scale access of new energy and frequent change of electricity market rules, and the user experience is improved. And the market risk is reduced, so that the method has better adaptability and application prospects.

Description

Technical Field

[0001] This invention belongs to the field of power trading and energy management technology, and particularly relates to a power trading auxiliary decision management method, device, equipment and storage medium. Background Technology

[0002] With the continuous development of the power system, electricity trading faces increasing challenges: First, the uncertainty of new energy sources is a major problem. New energy power generation exhibits significant instability, posing a significant obstacle to electricity trading. For example, solar power generation depends on sunlight intensity and duration, while wind power generation depends on wind speed and direction. The uncontrollability of these natural factors makes it difficult to accurately predict the output of new energy power generation, leading to numerous uncertainties in electricity trading regarding power balance and price setting. Second, the increasing complexity of the electricity market cannot be ignored. The participants in the current electricity market are becoming increasingly diversified, encompassing power generation companies, grid companies, electricity sales companies, electricity users, and various emerging market players. Simultaneously, trading rules are constantly being updated to adapt to market development needs. This situation greatly increases the complexity of trading decisions, making it difficult for market participants to quickly and accurately grasp market dynamics and make reasonable decisions. Third, electricity trading demands extremely high real-time performance. The operating characteristics of the power system dictate that electricity trading needs to respond quickly to market changes. Whether it's instantaneous changes in electricity supply and demand or real-time fluctuations in electricity prices, the trading decision-making system must react promptly, placing unprecedented demands on the real-time performance of the trading system.

[0003] Traditional power trading decision-making methods mainly rely on expert experience, historical data analysis, and simple statistical models. However, these methods have obvious limitations. They are poorly adaptable and struggle to keep up with the rapid changes in the power market. Faced with the large-scale integration of new energy sources and frequent adjustments to power market rules, traditional models are unable to effectively respond and make accurate decisions. Moreover, they have low information utilization rates, typically using only partial historical data and failing to fully tap the hidden value within massive amounts of data. This results in a lack of comprehensiveness and foresight in decision-making. Furthermore, the problem of decision lag is prominent. Traditional decision-making processes often involve long time delays, making it impossible to capture and respond to the ever-changing market in a timely manner, leaving market participants in a passive position during transactions. While existing patented technologies (such as CN118333429A, CN118552058A, and CN118367555A) have incorporated technologies like machine learning and blockchain, they still have some shortcomings. First, the models are too simplistic: relying on a single prediction or optimization model makes it difficult to capture the complexity of the power system. Second, the optimization objectives are too singular: they typically only focus on maximizing economic benefits, ignoring objectives such as system stability and renewable energy utilization, which has significant limitations in the context of sustainable development and ensuring the reliable operation of the power system. Third, data utilization is insufficient: they do not fully integrate multi-source heterogeneous data (such as meteorological data, equipment status data, and market rules), fail to fully explore the enormous value of massive data in improving the accuracy and scientific nature of trading decisions, and fail to transform rich data resources into effective decision support. Summary of the Invention

[0004] The purpose of this invention is to provide a method, apparatus, equipment and storage medium for power trading auxiliary decision management, which aims to solve the problems of single power trading decision, poor balance and difficulty in adapting to complex power trading markets caused by existing technology.

[0005] On one hand, the present invention provides a power trading auxiliary decision management method, the method comprising the following steps: Based on electricity trading environment information, the electricity market environment is analyzed and predicted using a large energy model to obtain energy forecast results; Based on the energy forecast results, an energy dispatch strategy is generated for the electricity market environment using a multi-objective optimization model. The power transactions in the power market environment are scheduled according to the energy dispatch strategy.

[0006] Preferably, after the step of scheduling electricity transactions in the electricity market environment according to the energy dispatch strategy, the method further includes: The operating curves of each power trading node in the power market environment under the energy dispatch strategy are generated, and the operating curves are submitted to the power trading center.

[0007] Preferably, the multi-objective optimization model includes an encoding module and a decoding module. The step of generating an energy dispatch strategy for the electricity market environment based on the energy forecast results using the multi-objective optimization model includes: The encoding module extracts multi-dimensional correlation features between the energy prediction results and the pre-acquired multi-source data. The energy scheduling strategy is generated by the decoding module based on the multi-dimensional correlation features.

[0008] Preferably, before the step of generating an energy dispatch strategy for the electricity market environment based on the energy forecast results using a multi-objective optimization model, the method further includes: A multi-objective optimization model is constructed using a Transformer-like architecture, with the objectives of maximizing economic benefits, maximizing system stability, and maximizing renewable energy utilization. The multi-objective optimization model is iteratively trained using a pre-defined multi-stage training strategy.

[0009] Preferably, the step of iteratively training the multi-objective optimization model using a preset multi-stage training strategy includes: The multi-objective optimization model is pre-trained using pre-acquired training data to capture deep features related to electricity trading. The pre-trained multi-objective optimization model is fine-tuned using supervised learning with labeled data from specific scenarios to optimize the model's prediction accuracy for the target electricity market.

[0010] On the other hand, the present invention provides a power trading auxiliary decision management device, the device comprising: The transaction forecasting unit is used to analyze and forecast the power market environment based on power trading environment information and through a large energy model to obtain energy forecasting results. The strategy generation unit is used to generate an energy dispatch strategy for the electricity market environment based on the energy forecast results and through a multi-objective optimization model. An energy dispatching unit is used to dispatch electricity transactions in the electricity market environment according to the energy dispatching strategy.

[0011] Preferably, the device further includes: The information reporting unit is used to generate the operating curves of each power trading node in the power market environment under the energy dispatch strategy, and to submit the operating curves to the power trading center.

[0012] Preferably, the multi-objective optimization model includes an encoding module and a decoding module, and the policy generation unit includes: The feature extraction unit is used to extract multi-dimensional correlation features between the energy prediction results and the pre-acquired multi-source data through the encoding module; The strategy generation subunit is used to generate the energy scheduling strategy based on the multi-dimensional correlation features through the decoding module.

[0013] On the other hand, the present invention also provides an electricity trading management device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the steps described in the above-described electricity trading auxiliary decision management method.

[0014] On the other hand, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps described in the above-described power trading auxiliary decision management method.

[0015] This invention analyzes and predicts the power market environment based on power trading environment information using a large energy model, obtaining energy forecast results. Based on these results, an energy dispatch strategy is generated for the power market environment through a multi-objective optimization model. Power transactions in the power market environment are then dispatched according to this energy dispatch strategy, thereby improving the balance and comprehensiveness of decision-making. This approach also better adapts to complex scenarios such as the large-scale integration of new energy sources and frequent changes in power market rules, reducing market risks and thus demonstrating better adaptability and application prospects. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the implementation of the power trading auxiliary decision management method provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of the power trading auxiliary decision management device provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a preferred structure of the power trading auxiliary decision management device provided in Embodiment 2 of the present invention; Figure 4 This is a schematic diagram of the power trading management equipment provided in Embodiment 3 of the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0018] The specific implementation of the present invention will be described in detail below with reference to specific embodiments: Example 1: Figure 1 The implementation flow of the power trading auxiliary decision management method provided in Embodiment 1 of the present invention is illustrated. For ease of explanation, only the parts related to the embodiments of the present invention are shown, and are described in detail below: In step S101, based on the electricity trading environment information, the electricity market environment is analyzed and predicted using a large energy model to obtain energy prediction results.

[0019] In this embodiment of the invention, the power market environment needs to be analyzed and predicted using a large energy model based on power trading environment information, thereby deriving energy prediction results. The power trading environment information includes multi-source data such as power market data, meteorological data, and policy and regulatory information. Specifically, firstly, power trading environment information is collected: real-time power market data (e.g., power prices), historical power market data within a preset time period (e.g., the past month), and the latest policy and regulatory information related to the power market are collected. Simultaneously, meteorological data for the same period (e.g., temperature, humidity, wind speed) is acquired to analyze its impact on the generation and consumption sides. Then, the power trading environment... Information processing includes, but is not limited to, data cleaning to remove outliers, filling in missing values, and data format conversion (such as standardizing the text format of policy and regulatory information). Finally, the processed electricity trading environment information is input into a trained energy big data model, which is then used to predict the supply and demand of the electricity market within a preset timeframe (such as electricity prices and trends in the next 24 hours). This yields energy forecast results, which provide a basis for subsequent energy dispatch strategies. For example, the energy dispatch strategy will determine how much electricity to purchase from the electricity market based on the predicted electricity price and adjust the remaining load to ensure that specific energy needs are met.

[0020] In one feasible implementation, the energy big data model employs a machine learning or deep learning architecture to achieve accurate predictions of energy trends (such as electricity prices) by learning from massive amounts of multi-source data, such as electricity market data and meteorological data.

[0021] In another feasible embodiment, the large energy model uses a sliding window recursive approach to output energy prediction results for a future preset time period.

[0022] In step S102, based on the energy forecast results, an energy dispatch strategy is generated for the electricity market environment through a multi-objective optimization model.

[0023] In this embodiment of the invention, based on energy forecast results and combined with real-time status data of end-side equipment, an energy dispatch strategy is generated for the power market environment through a multi-objective optimization model, wherein the multi-objective optimization model includes an encoding module and a decoding module.

[0024] In a feasible embodiment, the multi-objective optimization model is trained through the following steps before it generates energy dispatch strategies for the electricity market environment: (1) A multi-objective optimization model with the objectives of maximizing economic benefits, maximizing system stability, and maximizing renewable energy utilization is constructed using a Transformer-like architecture; In this embodiment of the invention, a multi-objective optimization model is constructed using an encoder-decoder structure similar to the Transformer architecture. The objective function of this multi-objective optimization model simultaneously covers maximizing economic benefits, maximizing system stability, and maximizing renewable energy utilization. Compared with traditional single-objective optimization methods, this achieves more comprehensive and balanced decision-making, significantly improves the quality of decision-making, and ensures the sustainable development of the power system.

[0025] (2) The multi-objective optimization model is iteratively trained using a pre-set multi-stage training strategy.

[0026] In this embodiment of the invention, the PyTorch framework is used, combined with distributed training technology, and a multi-stage training strategy combining self-supervised learning and supervised learning is used to iteratively train the multi-objective optimization model to achieve dynamic balance and policy generation of the energy system.

[0027] When iteratively training a multi-objective optimization model using a pre-defined multi-stage training strategy, preferably, the multi-objective optimization model is first pre-trained using self-supervised learning with pre-acquired training data to capture deep features related to electricity trading, and then the pre-trained multi-objective optimization model is fine-tuned using supervised learning with labeled data for specific scenarios to optimize the model's prediction accuracy for the target electricity market.

[0028] In this embodiment of the invention, a large amount of previously labeled energy data (including pre-balancing energy data (such as energy consumption, new energy generation, electricity trading, etc.) and post-balancing energy data corrected by the electricity trading team) is used as training data for the model. Using this training data, a self-supervised learning method is employed to pre-train the multi-objective optimization model to capture deep features related to electricity trading. Then, labeled data for specific scenarios is used to fine-tune the pre-trained multi-objective optimization model through supervised learning to optimize the model's prediction accuracy for the target electricity market, enabling it to adapt to the special needs of energy system balance in specific scenarios.

[0029] In another feasible embodiment, the energy scheduling strategy is generated through the following steps: ① Extract multi-dimensional correlation features between energy forecast results and pre-acquired multi-source data through the coding module; In this embodiment of the invention, the pre-acquired multi-source data includes, but is not limited to, real-time status data from the end side (such as the SOC of the energy storage system, adjustable load demand, and new energy power generation), meteorological data (temperature, wind speed, and light intensity), historical transaction data, and market rule information. Specifically, the input and output load of the power system is tracked in real time through devices such as smart gate meters and secondary anti-reverse flow meters to ensure the real-time nature and accuracy of the data. Real-time data of distributed energy facilities is collected, such as the output power of photovoltaic panels, the speed and power output of wind turbine generators, and the charging status and capacity of energy storage batteries. Sensors and monitoring systems are used to monitor the health status and efficiency of the equipment in real time to ensure the accuracy and reliability of the data. Third-party meteorological services are accessed to obtain key meteorological parameters such as light intensity, wind speed, and temperature in real time. Here, the energy pre- The measurement results (such as the electricity price and new energy power generation forecast for the next 24 hours) and multi-source data are preprocessed: different types of data are standardized and normalized to eliminate differences in dimensions and fill missing values. The preprocessed energy forecast results and multi-source data are then input into the encoding module. After that, the long-term dependency relationship of electricity price fluctuations and load cycle changes is captured through the temporal encoding layer of the encoding module. The topological relationship between distributed energy devices (such as photovoltaic, energy storage, and load) is modeled through the graph neural network (GNN) of the encoding module to analyze the impact of energy flow between devices. The correlation between meteorological data on the power generation side (such as the influence of sunlight on photovoltaic output) and the power consumption side (such as the influence of temperature on air conditioning load) is dynamically weighted through the attention mechanism of the encoding module to generate multi-dimensional correlation features after fusion.

[0030] ② An energy scheduling strategy is generated based on multi-dimensional correlation features through the decoding module.

[0031] In this embodiment of the invention, multi-dimensional related features are input into the decoding module. Through the fully connected layer of the decoding module, these features are mapped into a potential strategy space (such as charging and discharging plans, trading volume ranges, and load adjustment ranges). A reinforcement learning framework is adopted, with economic benefits, system stability, and renewable energy utilization rate as reward functions, to guide the model to generate multiple sets of candidate strategies that meet multi-objective optimization (such as energy storage charging and discharging schemes for different time periods and electricity trading volume allocation). Candidate strategies that achieve a balance between economic benefits, stability, and environmental protection are selected. Here, the selected candidate strategies can be input into the simulation environment to simulate the system state after execution (such as grid frequency, energy storage capacity, and market revenue) to verify their feasibility. Strategies that violate constraints (such as exceeding the limit of energy storage charging and discharging rate) are corrected. Finally, executable candidate energy dispatch strategies are output. Finally, the executable candidate energy dispatch strategies are presented to the power trading decision-maker. The decision-maker selects the optimal energy dispatch strategy as the final energy dispatch strategy for power trading based on the actual market situation and experience.

[0032] The above steps ① and ② achieve the fusion of multi-source heterogeneous data through the encoding module, capture the complex dynamic correlation of the power system, and avoid the strategy bias caused by the traditional model ignoring cross-dimensional relationships. In the decoding module, generative AI and multi-objective optimization are combined to achieve the diversity and balance of strategies, and significantly improve the adaptability of the virtual power plant in the volatile market.

[0033] In step S103, power transactions in the power market environment are scheduled according to the energy dispatch strategy.

[0034] In this embodiment of the invention, the energy dispatch strategy is converted into corresponding power trading instructions, energy storage charging and discharging instructions, and load adjustment instructions, which are respectively issued to the power trading side, the energy storage system side, and the adjustable load side. This enables the power trading side to conduct power trading according to the optimal power trading quantity and market trading rules in the power trading instructions, and enables the energy storage system side to execute corresponding charging and discharging operations according to the charging and discharging scheme in the energy storage charging and discharging instructions, such as charging when the power price is low and discharging when the load is high, in order to adjust the power supply and demand balance. This enables the adjustable load side to execute the adjustment amount based on the load adjustment instructions and perform load regulation according to various control algorithms in the end-side control system, such as adjusting the power consumption time of industrial users' production equipment, and feeding back the adjustment results to the system for the next round of balance optimization.

[0035] In one feasible embodiment, after scheduling power transactions in the power market environment according to the energy dispatch strategy, the operating curves of each power transaction node in the power market environment under the energy dispatch strategy are generated, and the operating curves are submitted to the power trading center.

[0036] In this embodiment of the invention, operating curves are generated and optimized according to energy dispatch strategies to ensure compliance with system constraints and market rules. The optimized operating curves are then converted into a format specified by the power trading center and submitted. Specifically, firstly, all relevant node data of each power trading node in the power market environment under the dispatch of the energy dispatch strategy are collected, including energy storage status, load demand, and generation capacity. Based on the collected node data, preliminary operating curves for the corresponding power trading nodes are generated. Next, the preliminary operating curves are smoothed to remove noise and abnormal fluctuations. Simultaneously, it is checked whether the smoothed curves meet the system's technical constraints such as voltage and frequency, as well as market rules and trading requirements. If not, the curves are adjusted to comply with market rules and trading requirements during the trading period. Additionally, users can check the provided human-computer interaction interface... The process involves reviewing the operating curve and adjusting it based on load, energy storage system requirements, or other actual business needs. For example, the load curve might be modified to accommodate temporary adjustments to the production plan. Once the user confirms the adjusted curve, the process begins with submitting the operating curve for approval. This involves first identifying the curve format required by the power trading center, such as specific data structures and file formats. The optimized operating curve is then converted to conform to the power trading center's requirements, ensuring data accuracy and completeness. Next, the converted curve is checked against the power trading center's trading rules to ensure compliance (e.g., checking if the electricity volume, price, and other data in the curve conform to the trading rules). If any non-compliance is found, necessary corrections are made. Finally, the approved operating curve is submitted to the power trading center, completing the power trading application process.

[0037] In this embodiment of the invention, based on the electricity trading environment information, the electricity market environment is analyzed and predicted through an energy big data model to obtain energy prediction results. Based on the energy prediction results, an energy dispatch strategy is generated for the electricity market environment through a multi-objective optimization model. The electricity trading in the electricity market environment is dispatched according to the energy dispatch strategy, thereby improving the balance and comprehensiveness of decision-making and better adapting to complex scenarios such as the large-scale access of new energy sources and frequent changes in electricity market rules, reducing market risks, and thus having better adaptability and application prospects.

[0038] Example 2: Figure 2 The structure of the power trading auxiliary decision management device provided in Embodiment 2 of the present invention is shown. For ease of explanation, only the parts related to the embodiments of the present invention are shown, including: The transaction forecasting unit 21 is used to analyze and forecast the power market environment based on power trading environment information and through an energy big data model to obtain energy forecasting results. The strategy generation unit 22 is used to generate energy dispatch strategies for the electricity market environment based on energy forecast results and through a multi-objective optimization model. Energy dispatch unit 23 is used to dispatch electricity transactions in the electricity market environment according to energy dispatch strategy.

[0039] Preferably, such as Figure 3 As shown, the power trading auxiliary decision management device of this embodiment of the invention further includes: Information reporting unit 24 is used to generate the operating curves of each power trading node in the power market environment under the energy dispatch strategy, and to report the operating curves to the power trading center.

[0040] Preferably, the multi-objective optimization model includes an encoding module and a decoding module.

[0041] Preferably, the strategy generation unit 22 includes: Feature extraction unit 221 is used to extract multi-dimensional correlation features between energy prediction results and pre-acquired multi-source data through the encoding module; The strategy generation subunit 222 is used to generate energy scheduling strategies based on multi-dimensional correlation features through the decoding module.

[0042] In this embodiment of the invention, each unit of the power trading auxiliary decision management device can be implemented by a corresponding hardware or software unit. Each unit can be an independent hardware or software unit, or it can be integrated into a single hardware or software unit, which is not intended to limit the invention. Specifically, the implementation methods of each unit can be referred to the description of the aforementioned Embodiment 1, and will not be repeated here.

[0043] Example 3: Figure 4 The structure of the power trading management device provided in Embodiment 3 of the present invention is shown. For ease of explanation, only the parts related to the embodiments of the present invention are shown.

[0044] The power trading management device 4 of this embodiment includes a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, it implements the steps described in the above embodiment of a power trading auxiliary decision management method, for example... Figure 1 The steps S101 to S103 are shown. Alternatively, when the processor 40 executes the computer program 42, it implements the functions of each unit in the above-described device embodiments, for example... Figure 2 The function of the unit shown.

[0045] In this embodiment of the invention, based on the electricity trading environment information, the electricity market environment is analyzed and predicted through an energy big data model to obtain energy prediction results. Based on the energy prediction results, an energy dispatch strategy is generated for the electricity market environment through a multi-objective optimization model. The electricity trading in the electricity market environment is dispatched according to the energy dispatch strategy, thereby improving the balance and comprehensiveness of decision-making and better adapting to complex scenarios such as the large-scale access of new energy sources and frequent changes in electricity market rules, reducing market risks, and thus having better adaptability and application prospects.

[0046] The power trading management device in this embodiment of the invention can be a personal computer or a server. The steps implemented by the processor 40 in the power trading management device 4 when executing the computer program 42 to achieve a power trading auxiliary decision management method can be referred to the description of the foregoing method embodiments, and will not be repeated here.

[0047] Example 4: In this embodiment of the invention, a computer-readable storage medium is provided, which stores a computer program. When executed by a processor, the computer program implements the steps described in the embodiment of the power trading auxiliary decision management method. For example... Figure 1 The steps S101 to S103 are shown. Alternatively, when the computer program is executed by the processor, it implements the functions of each unit in the above-described device embodiments, for example... Figure 2 The function of the unit shown.

[0048] In this embodiment of the invention, based on the electricity trading environment information, the electricity market environment is analyzed and predicted through an energy big data model to obtain energy prediction results. Based on the energy prediction results, an energy dispatch strategy is generated for the electricity market environment through a multi-objective optimization model. The electricity trading in the electricity market environment is dispatched according to the energy dispatch strategy, thereby improving the balance and comprehensiveness of decision-making and better adapting to complex scenarios such as the large-scale access of new energy sources and frequent changes in electricity market rules, reducing market risks, and thus having better adaptability and application prospects.

[0049] The computer-readable storage medium in embodiments of the present invention may include any entity or device capable of carrying computer program code, a recording medium, such as ROM / RAM, disk, optical disk, flash memory, etc.

[0050] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for power transaction aided decision management, characterized by, The method comprises the following steps: According to the power transaction environment information, the energy big model is used to analyze and predict the power market environment, and energy prediction results are obtained; Based on the energy prediction results, a multi-objective optimization model is used to generate an energy scheduling strategy for the power market environment; According to the energy scheduling strategy, the power transactions in the power market environment are scheduled.

2. The method of claim 1, wherein, After the step of scheduling the power transactions in the power market environment according to the energy scheduling strategy, the method further comprises: Generating the operation curve of each power transaction node in the power market environment under the energy scheduling strategy, and reporting the operation curve to the power transaction center.

3. The method of claim 1, wherein, The multi-objective optimization model comprises an encoding module and a decoding module. Based on the energy prediction results, the multi-objective optimization model is used to generate an energy scheduling strategy for the power market environment. The step comprises: Extracting multi-dimensional correlation features between the energy prediction results and pre-acquired multi-source data through the encoding module; Generating the energy scheduling strategy based on the multi-dimensional correlation features through the decoding module.

4. The method of claim 3, wherein, Before the step of generating an energy scheduling strategy for the power market environment based on the energy prediction results through a multi-objective optimization model, the method further comprises: Using a Transformer-like architecture to build the multi-objective optimization model with the goals of maximizing economic benefits, maximizing system stability, and maximizing renewable energy utilization rate; Using a pre-set multi-stage training strategy to iteratively train the multi-objective optimization model.

5. The method of claim 4, wherein, The step of using a pre-set multi-stage training strategy to iteratively train the multi-objective optimization model comprises: Using pre-acquired training data to pre-train the multi-objective optimization model for self-supervised learning to capture deep features related to power transactions; Using specific scenario labeled data to fine-tune the pre-trained multi-objective optimization model for supervised learning to optimize the prediction accuracy of the model for target power markets.

6. An electric power transaction aid decision management apparatus characterized by comprising: The device comprises: A transaction prediction unit configured to analyze and predict the power market environment based on power transaction environment information through an energy big model, and obtain energy prediction results; A strategy generation unit configured to generate an energy scheduling strategy for the power market environment based on the energy prediction results through a multi-objective optimization model; An energy scheduling unit configured to schedule power transactions in the power market environment according to the energy scheduling strategy.

7. The apparatus of claim 6, wherein, The device further comprises: An information reporting unit configured to generate the operation curve of each power transaction node in the power market environment under the energy scheduling strategy, and report the operation curve to the power transaction center.

8. The apparatus of claim 6, wherein, The multi-objective optimization model comprises an encoding module and a decoding module, and the strategy generation unit comprises: A feature extraction unit configured to extract multi-dimensional correlation features between the energy prediction results and pre-acquired multi-source data through the encoding module; A strategy generation subunit configured to generate the energy scheduling strategy based on the multi-dimensional correlation features through the decoding module.

9. A power transaction management device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the method according to any one of claims 1 to 5.

Images