Energy storage transaction data processing method and model based on electric power spot market environment

Abstract

The invention belongs to the technical field of data processing, and particularly relates to an energy storage transaction data processing method and model based on an electric power spot market environment, and the method comprises the steps: analyzing the historical energy storage state of an electric power spot market platform to obtain a historical energy storage state feature value, and analyzing the historical transaction state of the electric power spot market platform to obtain a historical energy storage state feature value; obtaining a historical transaction state characteristic value, combining a real-time meteorological state data set, performing comparison to obtain a predicted daily charging frequency of an energy storage battery, a predicted power transmission line power factor and a predicted power grid load capacity, and performing comparison based on a scheduling optimization characteristic value to obtain an electric power spot market platform scheduling optimization scheme; the system comprises an energy storage state characteristic value analysis module, a transaction state characteristic value analysis module, a meteorological state data set acquisition module, a prediction data analysis module and a scheduling optimization scheme comparison module. The method can improve the capability of judging the future power demand and supply condition, helps to balance the power grid load, and enhances the flexibility and stability of the power system.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and specifically relates to a method and model for processing energy storage transaction data based on an electricity spot market environment. Background Art

[0002] With the rapid development of renewable energy such as wind power and solar power, the proportion of renewable energy in the power system has gradually increased. The intermittent and unstable nature of these energy sources has brought challenges to the balance of supply and demand in the power market. Energy storage technology can help alleviate this problem by storing excess electricity and releasing it when demand peaks.

[0003] However, the existing forecasting models and algorithms cannot fully consider the complexity of the electricity spot market and the dynamic characteristics of the energy storage system. Specifically, the existing forecasting models and algorithms mainly focus on single-dimensional data and fail to comprehensively consider multiple factors. Single-dimensional data analysis and forecasting models may not be able to accurately reflect the complex dynamics of the electricity spot market, which may lead to inaccurate forecasting results. The electricity spot market is often affected by multiple factors, and a single-dimensional forecasting model may not be able to adapt to the rapid changes in the market. If the forecasting model fails to consider the dynamic characteristics of the energy storage system and the complexity of the market, it may underestimate potential risks and affect the flexibility and adaptability of the system. Summary of the invention

[0004] In view of the shortcomings of the existing technology, the present invention provides a method and model for processing energy storage transaction data based on the electricity spot market environment, which can provide a more comprehensive understanding of the operating rules of the electricity spot market, thereby improving the ability to judge future electricity demand and supply conditions.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for processing energy storage transaction data in a power spot market environment, comprising the following steps: Analyze the historical energy storage status of the power spot market platform and obtain the historical energy storage status characteristic value; Analyze the historical transaction status of the power spot market platform and obtain the characteristic value of the historical transaction status; Get real-time weather status data set; Based on the historical energy storage state characteristic values ​​and historical transaction state characteristic values, combined with the real-time meteorological state data set, the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load are obtained by comparison; Based on the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load, an optimization plan for the dispatching of the electricity spot market platform is obtained through comparison.

[0006] Preferably, the process of analyzing the historical energy storage status of the power spot market platform is: Obtain historical energy storage status data sets, including maximum battery capacity, battery efficiency, average battery usage temperature, and traditional energy usage ratio; Based on the acquired historical energy storage status data set, a comprehensive analysis is performed to obtain the historical energy storage status characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load.

[0007] Preferably, the formula for obtaining the historical energy storage state characteristic value is: ; In the formula, is the historical energy storage state characteristic value, rl is the maximum capacity of the battery, xl is the battery efficiency, wd is the average temperature of the battery, ct is the proportion of traditional energy use, is the compensation factor of the set rl, is the compensation factor of the set xl, is the compensation factor of the set wd, is the compensation factor of the set ct.

[0008] Preferably, the process of analyzing the historical transaction status of the power spot market platform is: Obtain a historical transaction status data set, which includes the average transaction duration, the frequency of historical transaction orders, and the matching rate of historical transaction orders; Based on the acquired historical transaction status data set, a comprehensive analysis is performed to obtain the historical transaction status characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted power grid load.

[0009] Preferably, the historical transaction status characteristic value is obtained in the following manner: ; In the formula, is the historical transaction status characteristic value, sc is the average transaction time of historical transactions, pl is the order frequency of historical transactions, pp is the order matching rate of historical transactions, is the compensation factor of the set sc, is the compensation factor of the set pl, is the compensation factor of the set pp, and e is a natural constant.

[0010] Preferably, the real-time meteorological status data set includes real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation.

[0011] Preferably, the process of comparing and obtaining the predicted number of daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted load of the power grid is: Based on the historical energy storage state characteristic values ​​and historical transaction state characteristic values, a comprehensive analysis is performed to obtain the predicted characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted load of power grids; The predicted characteristic value, real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation are stored as designated tags, and the designated tags are compared with the predicted daily charging times of the energy storage battery, the predicted transmission line power factor, and the predicted grid load corresponding to each designated tag stored in the database to obtain the predicted daily charging times of the energy storage battery, the predicted transmission line power factor, and the predicted grid load corresponding to the designated tags.

[0012] Preferably, the process of obtaining the optimization plan for dispatching the power spot market platform by comparison is: Based on the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted load of power grids, a comprehensive analysis is conducted to obtain the dispatch optimization characteristic value, which is used as the analysis basis for comparing the dispatch optimization plan of the power spot market platform; The dispatch optimization characteristic value is compared with the power spot market platform dispatch optimization plan corresponding to each dispatch optimization characteristic value stored in the database to obtain the power spot market platform dispatch optimization plan corresponding to the dispatch optimization characteristic value.

[0013] Preferably, the scheduling optimization characteristic value is obtained in the following manner: ; In the formula, is the scheduling optimization characteristic value, cn is the predicted daily charging times of the energy storage battery, ys is the predicted power factor of the transmission line, fh is the predicted power grid load, is the compensation factor of the set cn, is the compensation factor of the set ys, is the compensation factor of the set fh, and e is a natural constant.

[0014] Based on the energy storage transaction data processing model under the power spot market environment, it is used to implement the above-mentioned energy storage transaction data processing method under the power spot market environment, including an energy storage state characteristic value analysis module, a transaction state characteristic value analysis module, a meteorological state data set acquisition module, a prediction data analysis module and a scheduling optimization scheme comparison module, wherein: The energy storage state characteristic value analysis module is used to analyze the historical energy storage state of the power spot market platform and obtain the historical energy storage state characteristic value; The transaction status characteristic value analysis module is used to analyze the historical transaction status of the power spot market platform and obtain the historical transaction status characteristic value; A meteorological status data set acquisition module is used to acquire a real-time meteorological status data set; The prediction data analysis module is used to compare the historical energy storage state characteristic values ​​and historical transaction state characteristic values ​​with the real-time meteorological state data set to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load; The scheduling optimization scheme comparison module is used to obtain the scheduling optimization scheme of the power spot market platform based on the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load.

[0015] The present invention has the following beneficial effects: By analyzing the historical energy storage state characteristic values ​​and the historical transaction state characteristic values, the present invention can more comprehensively understand the operation rules of the electricity spot market, thereby improving the ability to judge future electricity demand and supply conditions. Combined with real-time meteorological data, it can more accurately predict the daily charging times of energy storage batteries, the power factor of transmission lines and the load of the power grid. The intelligent scheduling of storage resources and the gradual optimization of market transaction status can achieve a more reasonable allocation of power resources, help improve the overall resource utilization efficiency, reduce the risk of over-investment, and help balance the power grid load and enhance the flexibility and stability of the power system.

[0016] The present invention can predict the number of daily charging times of energy storage batteries, the power factor of transmission lines, and the load on power grids based on historical energy storage state characteristic values ​​and historical transaction state characteristic values ​​in combination with real-time meteorological state data sets. The comprehensive analysis of historical data and real-time data can accurately identify trends and patterns, thereby providing data-driven decision support for power market participants, reducing reliance on experience and intuitive methods, and improving the scientificity and effectiveness of decision-making. The system can better match power demand and ensure sufficient power supply during high-demand periods.

[0017] The present invention can obtain a scheduling optimization plan for the electricity spot market platform based on the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted load of the power grid. Based on the predicted data, the intelligent scheduling of power resources can be realized, the overall operating efficiency of the power system can be maximized, and the energy storage and power generation resources can be reasonably scheduled to balance load fluctuations and reduce the volatility of power supply, thereby enhancing the stability of the power grid and helping to prevent power shortages or overloads. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the method steps of the present invention; Figure 2 It is a schematic diagram of the connection of the model modules of the present invention; Figure 3A three-dimensional image of the change of the historical transaction state characteristic value along with the historical transaction order matching rate and the set compensation factor of the historical transaction order matching rate; Figure 4 It is an image of the change of historical transaction status feature value along with the historical transaction order matching rate; Figure 5 This is an image of the predicted feature value changing with the historical transaction status feature value. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the accompanying drawings.

[0020] Example 1: Figure 1 As shown, a method for processing energy storage transaction data based on a power spot market environment includes: analyzing the historical energy storage status of the power spot market platform to obtain historical energy storage status characteristic values.

[0021] The specific analysis process is as follows: obtaining a historical energy storage status data set, which includes the maximum capacity of the battery, battery efficiency, average battery usage temperature, and the proportion of traditional energy use; based on the historical energy storage status data set obtained, a comprehensive analysis is performed to obtain the historical energy storage status characteristic values, which are used as a basis for comparison to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted grid load.

[0022] The maximum capacity of a battery refers to the maximum amount of electricity that a battery can store under optimal conditions, usually measured in kilowatt-hours (kWh), which helps to understand the battery's energy storage capacity; battery efficiency refers to the energy conversion efficiency of a battery during the charging and discharging process, usually expressed as a percentage. A high-efficiency battery can better utilize stored electrical energy and reduce losses; the average temperature of a battery during use refers to the average temperature at which the battery is exposed to during use. Temperature has an important impact on the performance and life of the battery. Too high or too low a temperature may lead to reduced battery efficiency; the proportion of traditional energy use refers to the proportion of traditional energy (such as coal, natural gas, etc.) in the power supply, which can reflect the proportional relationship between renewable energy and traditional energy in the power supply, and has an important impact on the sustainability of the overall power system.

[0023] The maximum capacity of the battery is obtained through the battery management system, the battery efficiency is obtained through the battery testing equipment, the average temperature of the battery is obtained through the temperature sensor, and the proportion of traditional energy use is monitored by the power monitoring system. The maximum capacity of the battery affects the effectiveness of its use. When the battery is close to the maximum capacity, its charging efficiency may decrease. When the battery capacity is not enough to meet the system requirements, it may be necessary to rely on traditional energy. The battery efficiency is directly affected by the operating temperature. High or low temperatures will affect the chemical reaction of the battery, resulting in energy loss and reduced efficiency. If the battery works under high or low temperature conditions, its performance (including charging and discharging efficiency and maximum capacity) may decrease, forcing the system to use more traditional energy to meet power needs. If the maximum capacity of the battery is high, energy storage can be used first to meet load requirements and reduce the use of traditional energy.

[0024] By deeply analyzing historical energy storage status data, the accuracy of predictions for the number of daily charging times of energy storage batteries, power factor of transmission lines and grid load can be improved. By analyzing the historical energy storage status characteristic values, we can better understand the changing patterns of grid load and perform corresponding scheduling and energy storage management based on the prediction results, thereby enhancing the stability of the grid and reducing frequent power fluctuations. The power system can quickly adapt to changes in market demand and external conditions, and improve the flexibility and responsiveness of the system.

[0025] The formula for obtaining the historical energy storage state characteristic value is: ; In the formula, is the historical energy storage state characteristic value, rl is the maximum capacity of the battery, xl is the battery efficiency, wd is the average temperature of the battery, ct is the proportion of traditional energy use, is the compensation factor of the set rl, is the compensation factor of the set xl, is the compensation factor of the set wd, is the compensation factor of the set ct. In the present embodiment, each formula performs normalization processing on the relevant parameters as required during calculation.

[0026] Understanding the historical energy storage status characteristic values ​​can enable the battery management system to dynamically adjust the charging and discharging plan to maximize the economic benefits and performance of the energy storage system. By optimizing utilization efficiency and improving battery performance, higher economic returns can be achieved and the overall investment value of energy storage assets can be increased. Monitoring the maximum capacity and usage status of the battery can prevent overcharging and over-discharging, thereby extending the battery life. Using the energy storage system to balance the grid load can improve the stability of the power supply and reduce the risk of power outages caused by load fluctuations.

[0027] The compensation factors of rl, xl, wd, and ct are obtained from the database. A mapping set of the historically measured maximum battery capacity, battery efficiency, average battery temperature, and traditional energy usage ratio and the compensation factors of rl, xl, wd, and ct is established based on historical data to obtain the compensation factors corresponding to the current rl, xl, wd, and ct. The same is true for other compensation factors in this embodiment.

[0028] The historical transaction status of the electricity spot market platform is analyzed to obtain the characteristic values ​​of the historical transaction status.

[0029] The specific analysis process is as follows: obtaining a historical transaction status data set, including the average duration of historical transaction transactions, the frequency of historical transaction orders, and the matching rate of historical transaction orders; based on the obtained historical transaction status data set, a comprehensive analysis is performed to obtain the historical transaction status characteristic values, and the historical transaction status characteristic values ​​are used as a comparison to obtain the analysis basis for predicting the number of daily charging times of energy storage batteries, predicting the power factor of transmission lines, and predicting the load on the power grid.

[0030] The average duration of historical transaction transactions refers to the average time taken for all transactions to be completed within a certain time range. The real-time trading platform or transaction management system can record the start and end time of each transaction and calculate the average duration through data processing; the frequency of historical transaction orders refers to the number of orders completed within a certain period of time, which is obtained based on data analysis tools; the historical transaction order matching rate refers to the ratio of the number of orders successfully matched and completed within a certain period of time to the total number of orders, usually expressed as a percentage, reflecting the efficiency and liquidity of the market. A high matching rate means that most orders can be successfully executed. The trading platform can monitor the order matching situation in real time, record successful and unsuccessful orders, and calculate the matching rate by analyzing these data.

[0031] A shorter average transaction time corresponds to a higher order frequency. If the average transaction time is long, it may mean that there are trading bottlenecks in the market and participants are unwilling to trade at high or low prices, resulting in a decrease in transaction frequency. If market liquidity is good and the order frequency increases, the average transaction time will be shortened. A higher transaction order frequency usually leads to a higher order matching rate. In an active market, it is easier for buyers and sellers to find matching trading partners, thereby improving the transaction efficiency of orders. There is also a correlation between the average transaction time and the order matching rate. A shorter transaction time usually corresponds to a higher order matching rate. Fast transactions indicate that the market can process orders quickly and meet the needs of buyers and sellers.

[0032] The characteristic values ​​of historical transaction status provide an important basis for predictive data, which can improve the prediction accuracy of the daily charging times of energy storage batteries, the power factor of transmission lines and the load of power grids. The characteristic values ​​can reflect the market activity and transaction efficiency. The analysis of historical transaction status can better understand the fluctuations in market demand, thereby improving the power system's ability to respond to changes in demand and ensuring the flexibility of power supply. By analyzing the matching rate of historical transaction orders, the resource allocation efficiency of the market can be evaluated, which helps power suppliers and dispatchers to rationally allocate power generation resources and improve the efficiency of the overall system.

[0033] The method for obtaining the historical transaction status characteristic value is as follows: ; In the formula, is the historical transaction status characteristic value, sc is the average transaction time of historical transactions, pl is the order frequency of historical transactions, pp is the order matching rate of historical transactions, is the compensation factor of the set sc, is the compensation factor of the set pl, is the compensation factor of the set pp, and e is a natural constant.

[0034] like Figure 3 , Figure 4 As shown in the figure, the historical transaction status characteristic value increases with the increase of the historical transaction order matching rate and the set compensation factor of the historical transaction order matching rate. The larger the historical transaction status characteristic value, the better the historical transaction status. By analyzing the average transaction time of historical transactions, the best trading opportunities and strategies can be identified, and trading behaviors can be optimized, thereby improving overall trading efficiency. Based on historical characteristic values, more scientific and reasonable investment and trading decisions can be made to reduce risks and uncertainties. By analyzing the historical transaction status characteristic values, problems in market operations can be identified, and more scientific and reasonable market access and trading policies can be formulated. The analysis of historical transaction status characteristic values ​​can help identify abnormal trading patterns, discover potential risks in a timely manner, and reduce the risk exposure of market participants.

[0035] Get real-time weather status data set, including real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation.

[0036] Based on the historical energy storage status characteristic values ​​and historical transaction status characteristic values, combined with the real-time meteorological status data set, the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted grid load are obtained by comparison.

[0037] The specific analysis process is as follows: based on the historical energy storage state characteristic values ​​and the historical transaction state characteristic values, a comprehensive analysis is performed to obtain the predicted characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load; the predicted characteristic values, real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation are stored as designated tags, and the designated tags are compared with the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load corresponding to the designated tags stored in the database to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load corresponding to the designated tags.

[0038] The predicted daily charging times of energy storage batteries refers to the number of times the energy storage batteries are expected to be charged in a day, reflecting the charging demand and usage frequency of the energy storage system in a specific time period; the power factor of the transmission line refers to the ratio between the active power and the apparent power in the power system, which is usually used to measure the efficiency of electric energy use. The power factor value is between 0 and 1. The closer the value is to 1, the higher the efficiency of electric energy use; the predicted grid load refers to the total amount of electricity that the grid is expected to provide in a specific time period, usually expressed in kilowatts (kW) or megawatts (MW). The load can be instantaneous load (load at a certain moment) or daily load (average load within a day).

[0039] When the grid load increases, especially during peak hours, electricity demand rises, and energy storage batteries may need to be charged during low-load periods in order to release electricity during high-load periods. Predicted changes in grid load directly affect the charging strategy of energy storage batteries. Changes in grid load will affect the power factor. When the load increases, if there are a large number of inductive loads in the grid (such as motors, transformers, etc.), the power factor may decrease, resulting in an increase in reactive power. Energy storage batteries can improve the power factor of transmission lines by providing reactive power. When the grid load is unbalanced or the power factor is low, the energy storage system can adjust the power factor of the grid by charging and discharging.

[0040] Combining historical energy storage, transaction status and meteorological data, it is possible to take into account the impact of multiple factors, thereby improving the accuracy and reliability of the forecast. By predicting the number of daily charging times for energy storage batteries, it is possible to better arrange charging time and power scheduling, improve battery efficiency and economy, and the combination of real-time meteorological conditions and predicted characteristic values ​​can provide policymakers with the necessary information to help them make more effective decisions in energy management, demand response and renewable energy integration, and reduce power fluctuations and scheduling pressure.

[0041] The predicted feature value is obtained as follows: ; In the formula, is the predicted feature value.

[0042] Combining historical energy storage and transaction status characteristics can generate more accurate forecast data, making the decision-making process more scientific and reducing the uncertainty caused by market fluctuations. Comprehensive consideration of energy storage status and transaction status can evaluate the market environment in multiple dimensions, helping to better identify opportunities and risks. By using predicted characteristic values, more efficient energy storage scheduling plans can be formulated, battery charging and discharging timing can be reasonably planned, and the utilization efficiency of energy storage systems can be improved. By combining the prediction of energy storage and transaction status, market participants can identify potential risks and their impacts, formulate countermeasures in advance, and reduce operational risks.

[0043] Figure 5 The graph of the predicted characteristic value changing with the historical transaction state characteristic value, where the x-axis represents the historical transaction state characteristic value and the y-axis represents the predicted characteristic value, can help intuitively understand how the historical transaction state characteristic value affects the predicted characteristic value; the larger the historical transaction state characteristic value, the larger the predicted characteristic value. As the historical transaction state characteristic value increases, the influence of the historical transaction state characteristic value on the predicted characteristic value gradually weakens. The historical energy storage state characteristic value is set to 5 unchanged, and only the size of the historical transaction state characteristic value is changed. The example values ​​of the historical transaction state characteristic value are as follows: Table 1 Example values ​​of historical transaction status feature values ​​in prediction feature values

[0044] Based on the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load, an optimization plan for the dispatching of the electricity spot market platform is obtained through comparison.

[0045] The specific analysis process is as follows: based on the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load, a comprehensive analysis is performed to obtain the dispatch optimization characteristic value, and the dispatch optimization characteristic value is used as the analysis basis for comparing the dispatch optimization plan of the electricity spot market platform; the dispatch optimization characteristic value is compared with the dispatch optimization plan of the electricity spot market platform corresponding to each dispatch optimization characteristic value stored in the database to obtain the dispatch optimization plan of the electricity spot market platform corresponding to the dispatch optimization characteristic value.

[0046] The dispatch optimization scheme can better adapt to the changing electricity market environment, thereby improving the stability and effectiveness of operation; the dispatch optimization characteristic value can significantly improve the efficiency of resource allocation, thereby reducing operating costs, and efficiently utilize energy storage equipment within a specific charging cycle to avoid unnecessary electricity bills; by comparing the dispatch optimization characteristic value with the grid load, the power generation plan and energy storage strategy can be adjusted in time to ensure the stable operation of the grid during peak load periods; the dispatch optimization characteristic value helps to improve the integration capability of renewable energy (such as wind power, solar energy, etc.), thereby reducing dependence on fossil fuels and promoting the transformation of the energy structure. Through flexible dispatching, the charging and discharging of the energy storage system can be dynamically adjusted under the condition of unstable renewable energy output, helping to optimize the power factor and reduce system losses.

[0047] The method for obtaining the scheduling optimization characteristic value is as follows: ; In the formula, is the scheduling optimization characteristic value, cn is the predicted daily charging times of the energy storage battery, ys is the predicted power factor of the transmission line, fh is the predicted power grid load, is the compensation factor of the set cn, is the compensation factor of the set ys, is the compensation factor of the set fh.

[0048] Predicting the number of daily charging times for energy storage batteries can reasonably arrange the timing of charging and discharging, improve battery efficiency, and reduce energy loss; based on the prediction of grid load and power factor, scheduling plans can be formulated more quickly, reducing decision-making time in the scheduling process and improving overall efficiency; accurately predicting grid load allows dispatchers to better balance electricity supply and demand, reduce the risk of power outages and excess electricity, and improve system stability; predicting the number of charging times for energy storage batteries and grid load can better utilize renewable energy generation, reduce dependence on traditional energy, and promote the integration of renewable energy; accurately predicting grid load enables the power system to quickly adjust power generation and energy storage strategies to cope with rapid changes in load and ensure power supply reliability. The scheduling optimization eigenvalues ​​can support the operation of the intelligent scheduling system and improve the level of automation in scheduling.

[0049] Example 2: Figure 2 As shown, based on the energy storage transaction data processing model in the electricity spot market environment, it is used to implement the method in the embodiment, including an energy storage state characteristic value analysis module, a transaction state characteristic value analysis module, a meteorological state data set acquisition module, a prediction data analysis module and a scheduling optimization scheme comparison module.

[0050] The energy storage state characteristic value analysis module is used to analyze the historical energy storage state of the power spot market platform to obtain the historical energy storage state characteristic value.

[0051] The transaction status characteristic value analysis module is used to analyze the historical transaction status of the power spot market platform and obtain the historical transaction status characteristic value.

[0052] The meteorological status data set acquisition module is used to acquire the real-time meteorological status data set.

[0053] The prediction data analysis module is used to obtain the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load based on the historical energy storage state characteristic values ​​and the historical transaction state characteristic values, combined with the real-time meteorological state data set.

[0054] The scheduling optimization scheme comparison module is used to obtain the scheduling optimization scheme of the power spot market platform based on the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load.

Claims

1. A method for processing energy storage transaction data in a power spot market environment, characterized in that: The following steps are involved: Analyze the historical energy storage status of the electricity spot market platform and obtain the historical energy storage status characteristic value; Analyze the historical transaction status of the power spot market platform and obtain the characteristic value of the historical transaction status; Get real-time weather status data set; Based on the historical energy storage state characteristic values ​​and historical transaction state characteristic values, combined with the real-time meteorological state data set, the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load are obtained by comparison; Based on the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted grid load, an optimization plan for the dispatching of the electricity spot market platform is obtained through comparison.

2. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 1 is characterized in that: The process of analyzing the historical energy storage status of the power spot market platform is as follows: Obtain historical energy storage status data sets, including maximum battery capacity, battery efficiency, average battery usage temperature, and traditional energy usage ratio; Based on the acquired historical energy storage status data set, a comprehensive analysis is performed to obtain the historical energy storage status characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load.

3. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 2 is characterized in that: The formula for obtaining the historical energy storage state characteristic value is: ； In the formula, is the historical energy storage state characteristic value, rl is the maximum capacity of the battery, xl is the battery efficiency, wd is the average temperature of the battery, ct is the proportion of traditional energy use, is the compensation factor of the set rl, is the compensation factor of the set xl, is the compensation factor of the set wd, is the compensation factor of the set ct.

4. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 1 is characterized in that: The process of analyzing the historical transaction status of the power spot market platform is as follows: Obtain a historical transaction status data set, which includes the average transaction time of historical transactions, the frequency of historical transaction orders, and the matching rate of historical transaction orders; Based on the acquired historical transaction status data set, a comprehensive analysis is performed to obtain the historical transaction status characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted power grid load.

5. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 4 is characterized in that: The method for obtaining the historical transaction status characteristic value is as follows: ； In the formula, is the historical transaction status characteristic value, sc is the average transaction time of historical transactions, pl is the order frequency of historical transactions, pp is the order matching rate of historical transactions, is the compensation factor of the set sc, is the compensation factor of the set pl, is the compensation factor of the set pp, and e is a natural constant.

6. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 1 is characterized in that: The real-time meteorological status data set includes real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation.

7. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 6 is characterized in that: The process of comparing and obtaining the predicted number of daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted load of the power grid is as follows: Based on the historical energy storage state characteristic values ​​and historical transaction state characteristic values, a comprehensive analysis is performed to obtain the predicted characteristic values, which are used as the basis for comparison to obtain the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted load of power grids; The predicted characteristic value, real-time temperature, real-time humidity, real-time wind speed, and real-time precipitation are stored as designated tags, and the designated tags are compared with the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load corresponding to each designated tag stored in the database to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load corresponding to the designated tags.

8. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 1 is characterized by: The process of obtaining the optimization plan for dispatching the power spot market platform by comparison is as follows: Based on the predicted daily charging times of energy storage batteries, the predicted power factor of transmission lines, and the predicted load of power grids, a comprehensive analysis is conducted to obtain the dispatch optimization characteristic value, which is used as the analysis basis for comparing the dispatch optimization plan of the power spot market platform; The dispatch optimization characteristic value is compared with the power spot market platform dispatch optimization plan corresponding to each dispatch optimization characteristic value stored in the database to obtain the power spot market platform dispatch optimization plan corresponding to the dispatch optimization characteristic value.

9. The method for processing energy storage transaction data based on the electricity spot market environment according to claim 8 is characterized in that: The method for obtaining the scheduling optimization characteristic value is: ； In the formula, is the scheduling optimization characteristic value, cn is the predicted daily charging times of the energy storage battery, ys is the predicted power factor of the transmission line, fh is the predicted power grid load, is the compensation factor of the set cn, is the compensation factor of the set ys, is the compensation factor of the set fh, and e is a natural constant.

10. A data processing model for energy storage transaction based on the electricity spot market environment is used to implement the data processing method for energy storage transaction based on the electricity spot market environment as described in any one of claims 1 to 9, characterized in that: It includes energy storage state characteristic value analysis module, transaction state characteristic value analysis module, meteorological state data set acquisition module, forecast data analysis module and dispatch optimization scheme comparison module, among which: The energy storage state characteristic value analysis module is used to analyze the historical energy storage state of the power spot market platform and obtain the historical energy storage state characteristic value; The transaction status characteristic value analysis module is used to analyze the historical transaction status of the power spot market platform and obtain the historical transaction status characteristic value; A meteorological status data set acquisition module is used to acquire a real-time meteorological status data set; The prediction data analysis module is used to compare the historical energy storage state characteristic values ​​and historical transaction state characteristic values ​​with the real-time meteorological state data set to obtain the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load; The scheduling optimization scheme comparison module is used to obtain the scheduling optimization scheme of the power spot market platform based on the predicted daily charging times of the energy storage battery, the predicted power factor of the transmission line, and the predicted power grid load.

Images