An evaluation system, method, computer device and storage medium based on a novel energy storage fusion power market algorithm model

Abstract

The present invention discloses an evaluation system, method, computer equipment and storage medium based on a novel energy storage fusion power market algorithm model, and relates to the field of novel energy storage technology. The real-time data acquisition and analysis capabilities of the evaluation system provide important support for the operation of the power market. By continuously collecting and analyzing relevant data of the power market, the system can fully understand the dynamic changes of the market and achieve an accurate grasp of the market supply and demand relationship. This timely data acquisition and analysis provides more decision-making basis for power market operators, enabling them to more flexibly formulate market participation strategies and energy storage system operation strategies. The algorithm model and evaluation mechanism can accurately detect abnormal changes in power demand and provide corresponding control strategies through learning historical data and monitoring real-time data. Through this comprehensive algorithm model and evaluation mechanism, power market operators can more effectively manage market operations and optimize energy resource utilization.

Description

Technical Field

[0001] The present invention relates to the field of novel energy storage technology, and specifically to an evaluation system, method, computer equipment and storage medium based on a novel energy storage fusion power market algorithm model. Background Art

[0002] With the development of social economy and the adjustment of energy structure, the electricity market is becoming increasingly complex, and the development of new energy storage technology has brought more flexibility and adjustability to the power system. By using advanced algorithm models and data analysis technology, the intelligent collaborative operation of the power market and the energy storage system can be realized to improve the operating efficiency and stability of the power system. In this context, the analysis of the algorithm model not only focuses on price fluctuations and policy changes in the electricity market, but also needs to take into account the characteristics and operating status of the energy storage system. Through in-depth analysis of the electricity market, we can better grasp the market participation strategy and risk management, and provide decision-making support for the operation of the energy storage system. At the same time, accurate prediction and adjustment of engineering power demand has also become one of the important tasks of the platform to meet the factory's electricity demand and optimize energy utilization.

[0003] At present, there are some problems and shortcomings in the traditional power system. First, the power demand of factories is often unstable and volatile. In response to production needs, electricity will rise and fall sharply in different time periods, which is difficult to predict and manage effectively. Secondly, the traditional power system has limited control capabilities for energy storage equipment, and it is not easy to give full play to the potential of the energy storage system. In addition, the operation mechanism of the electricity market and the volatility of market prices are often real-time. In the process of storing energy in new energy storage equipment, there are certain operational difficulties in storing energy at a reasonable price. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies in the prior art, the present invention provides an evaluation system, method, computer device and storage medium based on a novel energy storage fusion power market algorithm model, which solves the problems mentioned in the background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: an evaluation system based on a novel energy storage fusion power market algorithm model, comprising: a power market analysis module, a data detection module, a data acquisition module, a data calculation module and a power evaluation module;

[0008] The power market analysis module is used to build an algorithm model, crawl the historical data of the target market price data and the operation strategy data of the energy storage system and input them into the algorithm model to train and verify the deep learning ability of the algorithm model;

[0009] The data detection module is used to obtain the power demand data of the factory and the comprehensive energy storage data of the new energy storage equipment in real time;

[0010] The data acquisition module is used to generate a first data set and a second data set after classifying, summarizing and preprocessing the acquired power demand data and comprehensive energy storage data;

[0011] The data calculation module is used to analyze and calculate the comprehensive power storage coefficient Cnxs and the power demand coefficient Xqxs after dimensionless processing based on the first data set and the second data set, and associate the comprehensive power storage coefficient Cnxs with the obtained power demand coefficient Xqxs to obtain a comprehensive evaluation coefficient Pgxs;

[0012] The power evaluation module is used to preset the evaluation threshold of the output result through deep learning of the algorithm model, input the obtained power demand coefficient Xqxs and the comprehensive evaluation coefficient Pgxs into the algorithm model, perform comparative evaluation through the preset evaluation threshold, and generate a corresponding control plan.

[0013] Preferably, the energy storage related data include electricity market data and energy storage system status data. The electricity market data include market prices, electricity policy data, weather data and market rule data. The energy storage system status data include SOC, power reserves and charging and discharging power. The participation strategies include energy market, capacity market and backup market.

[0014] Preferably, the power market analysis module includes a power market unit, a strategic operation unit and a deep learning unit;

[0015] The power market unit is used to develop a data crawling tool to use the crawling tool to obtain historical power market data and historical energy storage system status data from relevant websites and API interfaces of the power market, and to pre-process the acquired historical power market data and historical energy storage system status data, wherein the pre-processing includes cleaning, data normalization and standardization processing;

[0016] The strategy operation unit accesses the meteorological system and the power market system, extracts the historical load data, weather factors and power market environmental factors of the power market and the meteorological system, combines the target market price at the future moment and the operation strategy of the energy storage system, and designs the participation strategy of the energy storage system in different markets, where the different markets include the energy market, the capacity market and the reserve market;

[0017] The deep learning unit uses an algorithm model to set the historical data of the target market price data and the operation strategy data of the energy storage system obtained by the power market unit and the strategic operation unit as a training set, and at the same time, feature the peak power demand time period and the off-peak power demand time period of the factory. The feature-marked data is used as a verification set, and the algorithm model is trained using the data in the verification set. After comprehensive analysis and deep learning of the power market, strategic operation and power demand of the factory, an auxiliary evaluation mechanism is generated.

[0018] Preferably, the data detection module includes a first detection unit and a second detection unit;

[0019] The first detection unit is used to build a data acquisition server inside the factory, monitor the power demand data of the factory in real time through the data acquisition server, and use Flask and Django back-end development frameworks to develop a power demand API application interface on the data acquisition server, so as to use the power demand API application interface to provide the real-time monitored power demand data to the energy storage system management platform through the HTTP communication protocol;

[0020] The second detection unit is used to deploy a new energy storage equipment monitoring system, which uses the new energy storage equipment monitoring system to monitor the comprehensive energy storage data of the energy storage equipment in real time. By developing an energy storage API application interface in the new energy storage equipment monitoring system, the energy storage API application interface can be used to provide the real-time monitored comprehensive energy storage data to the new energy storage system management platform through the HTTP communication protocol.

[0021] Preferably, the data acquisition module includes a first acquisition unit and a second acquisition unit;

[0022] The first acquisition unit is used to preprocess the detected comprehensive energy storage data, wherein the preprocessing includes removing outliers, cleaning and normalizing, and classifying and aggregating the preprocessed comprehensive energy storage data to generate a first data set;

[0023] The first data set includes an electric load data set, an electric power data set and an electric energy storage data set;

[0024] The electric load data set includes load density Fmd, load peak value Ffz, load valley value Fgz, reference load value Fjz and load change rate Fbh;

[0025] The electric power data set includes rated power Ggl, instantaneous power Gss, peak power Gfz, power response time Gxy and power density Gmd;

[0026] The power storage data set includes a self-discharge rate Dfd, a charging cycle number Dxh, a discharging cycle number Dfx, a cycle rate Dxs and a capacity Drl;

[0027] The second acquisition unit is used to generate a second data set after preprocessing the detected power demand data, and to generate a power demand data set by classifying and aggregating the second data set, wherein the power demand data includes power consumption Xxh, power demand peak Xfz, harmonic content Xxb, harmonic frequency Xpl and total harmonic distortion rate Xjb.

[0028] Preferably, the data calculation module includes a first calculation unit;

[0029] The first calculation unit includes an electric load calculation unit, an electric power calculation unit and an energy storage device calculation unit;

[0030] The power load calculation unit is used to perform dimensionless processing on the power load data set in the first data set, and then perform analysis and calculation to obtain the load factor Fzxs;

[0031] The electric power calculation unit is used to perform dimensionless processing on the electric power data set in the first data set, and then perform analysis and calculation to obtain the electric power coefficient Glxs;

[0032] The energy storage device calculation unit is used to perform dimensionless processing on the electric energy storage data set in the first data set, and then perform analysis and calculation to obtain the electric storage coefficient Dcxs;

[0033] The load factor Fzxs, electric power factor Glxs and electric storage factor Dcxs are obtained by the following formulas:

[0034]

[0035]

[0036]

[0037] Wherein, Fmd represents load density, Ffz represents load peak value, Fgz represents load valley value, Fjz represents reference load value, Fbh represents load change rate; Ggl represents rated power, Gss represents instantaneous power, Gfz represents peak power, Gxy represents power response time, Gmd represents power density; Dfd represents self-discharge rate, Dxh represents number of charging cycles, Dfx represents number of discharge cycles, Dxs represents cycle rate, and Drl represents capacitance.

[0038] Preferably, the data calculation module further includes a second calculation unit, and the second calculation unit is used for performing dimensionless processing and calculation processing on the power demand data set in the second data set to obtain the power demand coefficient Xqxs;

[0039] The power demand coefficient Xqxs is obtained by the following formula:

[0040]

[0041] Wherein, Xxh represents the power consumption, Xfz represents the peak power demand, Xxb represents the harmonic content, Xpl represents the frequency of the harmonic, and Xjb represents the total harmonic distortion rate.

[0042] Preferably, the data calculation module further includes a comprehensive calculation unit, and the comprehensive calculation unit includes a summary unit;

[0043] The summarizing unit is used to perform dimensionless processing on the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs obtained by the first calculating unit, and then perform summarizing calculation to obtain the comprehensive electric energy storage factor Cnxs;

[0044] The comprehensive power storage coefficient Cnxs is obtained by the following formula:

[0045]

[0046] Wherein, a1, a2 and a3 represent the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs respectively, and a1+a2≠a3, a3≠0, 0≤a1≤0.47, 0≤a2≤0.62, 0≤a3≤0.56, and the specific values ​​are adjusted and set by the user, and A is the first correction constant.

[0047] Preferably, the comprehensive calculation unit further includes a correlation unit, which is used to perform a comprehensive correlation calculation after dimensionless processing on the comprehensive power storage coefficient Cnxs obtained by the summary unit and the power demand coefficient Xqxs obtained by the second calculation unit to obtain a comprehensive evaluation coefficient Pgxs;

[0048] The comprehensive evaluation coefficient Pgxs is obtained by the following formula:

[0049]

[0050] In the formula, b1 and b2 represent the preset proportional coefficients of the power demand coefficient Xqxs and the comprehensive power storage coefficient Cnxs respectively, and b1≠b2, 0≤b1≤0.53, 0≤b2≤0.47, the specific value of which is adjusted and set by the user, and B is the second correction constant.

[0051] Preferably, the power evaluation module includes a first evaluation unit and a second evaluation unit, and the evaluation threshold includes a power demand evaluation threshold Q and an energy storage evaluation threshold W;

[0052] The first evaluation unit determines the control scheme of the factory according to the comparison result between the power demand evaluation threshold Q and the power demand coefficient Xqxs, including:

[0053] When the power demand coefficient Xqxs>power demand assessment threshold Q, it means that the current power demand of the factory is abnormal. At this time, the algorithm model is combined to predict the future power price. If the future power price is at the peak of the power price, 80% of the power supply of the factory is set in advance to power the new energy storage equipment, and 20% of the power supply of the factory is set to commercial power supply. If the future power price is at the valley of the power price, the power supply of the factory is set to industrial power, and the new energy storage equipment is stored.

[0054] When the power demand coefficient Xqxs≤the power demand assessment threshold Q, the energy storage assessment threshold W is compared with the comprehensive assessment coefficient Pgxs, and the plant control plan is determined based on the comparison result of the energy storage assessment threshold W and the comprehensive assessment coefficient Pgxs.

[0055] Preferably, the second evaluation unit determines the control scheme of the plant according to the comparison result between the energy storage evaluation threshold W and the comprehensive evaluation coefficient Pgxs, including:

[0056] When the comprehensive evaluation coefficient Pgxs> the energy storage evaluation threshold W, it means that the new energy storage device is abnormal. Then it is necessary to regulate the new energy storage device and open the discharge rate of the new energy storage device to 100%. The new energy storage device is used to fully discharge the factory and replace the factory's industrial electricity.

[0057] When the comprehensive evaluation coefficient Pgxs ≤ the energy storage evaluation threshold W, it means that the new energy storage device is in a normal state. In this case, the discharge of the new energy storage device is shut down, and the trained algorithm model is combined to identify the target time point corresponding to the valley price of electricity in the electricity market, so as to use commercial power supply to charge the new energy storage device at the target time point.

[0058] An evaluation method based on a novel energy storage fusion power market algorithm model includes the following steps:

[0059] S1. First, by building an algorithm model, the crawled target market price data and historical data of the energy storage system's operation strategy data are input into the algorithm model to train and verify the algorithm model's deep learning capabilities and generate an auxiliary evaluation mechanism.

[0060] S2, then establish a data acquisition server and energy storage equipment monitoring system to obtain the factory power demand and energy storage equipment data in real time, use the back-end development framework to develop an API application interface, transmit the real-time monitoring data to the management platform, and then pre-process the acquired data to generate the first and second data sets;

[0061] S3, using the first data set and the second data set to perform dimensionless processing, calculate the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs, and perform summary calculation to obtain the comprehensive electric energy storage factor Cnxs, and perform correlation calculation with the electric power demand factor Xqxs to obtain the comprehensive evaluation coefficient Pgxs;

[0062] S4. Combined with the power demand assessment threshold Q set by the algorithm model, conduct a preliminary comparative assessment, and adjust the factory power supply mode according to the assessment results to optimize energy utilization efficiency;

[0063] S5. Set the energy storage evaluation threshold W, conduct a secondary comparative evaluation of the comprehensive evaluation coefficient Pgxs, and adjust the energy storage equipment according to the evaluation results to respond to the power market and optimize energy utilization.

[0064] Preferably, the storage medium stores program instructions for executing the above-mentioned evaluation system based on the novel energy storage fusion power market algorithm model;

[0065] A computer device comprising: one or more processors;

[0066] The processor is used to store one or more programs;

[0067] When the one or more programs are executed by the one or more processors, an evaluation system based on a novel energy storage fusion power market algorithm model as described above is implemented.

[0068] (III) Beneficial effects

[0069] The present invention provides an evaluation system, method, computer device and storage medium based on a novel energy storage fusion power market algorithm model. It has the following beneficial effects:

[0070] (1) The real-time data collection and analysis capabilities of the evaluation system provide important support for the operation of the power market. By continuously collecting and analyzing relevant data of the power market, the system can fully understand the dynamic changes of the market and accurately grasp the market supply and demand relationship. This timely data acquisition and analysis provides more decision-making basis for power market operators, enabling them to formulate market participation strategies and energy storage system operation strategies more flexibly. In terms of identifying abnormal situations in power demand, the algorithm model and evaluation mechanism can accurately detect abnormal changes in power demand by learning historical data and monitoring real-time data. Once an abnormal situation is found, the system will immediately respond and provide corresponding control strategies. Through this comprehensive algorithm model and evaluation mechanism, power market operators can manage market operations more effectively and optimize the utilization of energy resources. According to the real-time data and analysis results provided by the system, they can timely adjust market participation strategies and energy storage system operation strategies to adapt to market changes and demand fluctuations, improve the operational efficiency of the power market, and maximize the utilization efficiency of energy resources.

[0071] (2) The evaluation system combines market price forecasts, load forecasts and energy storage system operation strategies, and can flexibly adjust the operation mode of energy storage equipment according to real-time market conditions and load demand, thereby realizing intelligent management of power demand. This helps reduce the energy costs of the factory, and at the same time, by considering risk management factors, it reduces the losses that may be caused by market fluctuations and improves the economy and stability of energy utilization.

[0072] (3) The evaluation system learns about the power market and strategic operations through deep learning units, combines the characteristic markers of the factory's peak power consumption and off-peak power consumption time periods, and realizes intelligent management and optimization of energy storage equipment. This enables energy storage equipment to respond to market demand more accurately, improves its utilization rate and responsiveness, provides reliable energy support for the factory, and also provides important support for the smooth operation of the power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a flow chart of an evaluation system based on a novel energy storage fusion power market algorithm model of the present invention;

[0074] Figure 2 This is a schematic diagram of the steps of an evaluation method based on a novel energy storage fusion electricity market algorithm model of the present invention. DETAILED DESCRIPTION

[0075] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Example 1

[0077] See also Figure 1 , the present invention provides an evaluation system based on a novel energy storage fusion power market algorithm model, including a power market analysis module, a data detection module, a data acquisition module, a data calculation module and a power evaluation module;

[0078] The power market analysis module is used to build an algorithm model and crawl the historical data of the target market price data and the operation strategy data of the energy storage system and input them into the algorithm model to train and verify the deep learning ability of the algorithm model;

[0079] The data detection module is used to obtain the power demand data of the factory and the comprehensive energy storage data of the new energy storage equipment in real time;

[0080] The data acquisition module is used to classify, summarize and pre-process the acquired power demand data and comprehensive energy storage data to generate a first data set and a second data set;

[0081] The data calculation module is used to analyze and calculate the comprehensive power storage coefficient Cnxs and the power demand coefficient Xqxs after dimensionless processing based on the first data set and the second data set, and associate the comprehensive power storage coefficient Cnxs with the obtained power demand coefficient Xqxs to obtain the comprehensive evaluation coefficient Pgxs;

[0082] The power assessment module is used to preset the assessment threshold of the output results of deep learning of the algorithm model, input the obtained power demand coefficient Xqxs and comprehensive assessment coefficient Pgxs into the algorithm model, conduct comparative evaluation through the preset assessment threshold, and generate a corresponding control plan.

[0083] In this embodiment, through the power market analysis module and the data detection module, the system can automatically obtain and analyze the power market data and the power demand data of the factory, thereby providing intelligent decision support for decision makers. This enables decision makers to formulate power market participation strategies and energy storage system operation strategies more accurately based on the data and analysis results provided by the system to cope with the dynamic changes in the market and the fluctuations in power demand. The data detection module can monitor the operating status of the factory power system and the energy storage system in real time, and timely capture the abnormal situation of power demand and the abnormal operation of energy storage equipment. This helps to discover potential problems in advance and take corresponding control measures to ensure the stable operation of the power system and the effective use of energy resources. The data acquisition module and the data calculation module can pre-process, classify and summarize the collected power demand data and comprehensive energy storage data, and perform corresponding calculations and analyses. This helps to extract key feature data and calculate the correlation coefficient based on these data to provide a basis for subsequent decision-making. The power evaluation module generates a corresponding evaluation mechanism by setting the power demand evaluation threshold and the energy storage evaluation threshold, combining the obtained power demand coefficient and the comprehensive evaluation coefficient. This enables the system to comprehensively evaluate power demand and the status of the energy storage system, and take corresponding regulatory measures based on the evaluation results to ensure the normal operation of the power system and the effective use of energy resources.

[0084] Example 2

[0085] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the power market analysis module includes the power market unit, ,strategy operation unit and deep learning unit;

[0086] Energy storage-related data include electricity market data and energy storage system status data. Electricity market data include market prices, electricity policy data, weather data and market rule data. Energy storage system status data include SOC, power reserves and charging and discharging power.

[0087] The power market unit is used to develop data crawling tools to obtain historical power market data and historical energy storage system status data from relevant websites and API interfaces of the power market, pre-process the acquired historical power market data and historical energy storage system status data, and establish a market price prediction mechanism based on historical power market price data. It also uses time series analysis and machine learning methods to combine the power market with the acquired real-time power market data to predict the target market price at a future time. The pre-processing includes cleaning, data normalization and standardization.

[0088] The strategic operation unit establishes a load forecasting strategy based on historical load data, weather factors, and power market environmental factors, and combines time series analysis and machine learning methods. It combines the load forecasting strategy with the acquired real-time load data to predict the target load at future times. At the same time, based on the real-time market price and the predicted target load at future times, it considers the market participation strategy and risk management factors, designs the operation strategy of the energy storage system, and combines the target market price at future times with the operation strategy of the energy storage system to design the participation strategy of the energy storage system in different markets, including the energy market, capacity market, and reserve market.

[0089] Through the algorithm model, the deep learning unit sets the historical data of the target market price data and the operation strategy data of the energy storage system obtained by the power market unit and the strategic operation unit as the training set, and at the same time, performs feature marking on the peak power demand time period and the off-peak power demand time period of the factory. The feature-marked data is used as the verification set, and the algorithm model is trained using the data in the verification set. After comprehensive analysis and deep learning of the power market, strategic operation and factory power demand, an auxiliary evaluation mechanism is generated.

[0090] In this embodiment, through the data crawling tool and market price prediction mechanism of the power market unit, the system can realize real-time prediction of power market prices. This helps power market participants to understand market price changes in a timely manner, formulate more targeted trading strategies, and improve market participation efficiency. The strategy operation unit uses time series analysis and machine learning methods, combined with historical load data, weather factors and power market environmental factors, to realize real-time prediction of load and design corresponding energy storage system operation strategies. This helps to optimize the operation of the energy storage system, improve energy utilization efficiency, and reduce electricity costs. The deep learning unit uses neural convolution technology to conduct deep learning of the power market and strategy operations, and at the same time marks the power demand characteristics of the factory, and comprehensively analyzes the power demand and power market situation of the factory. This helps the system generate an auxiliary evaluation mechanism, provide decision makers with more comprehensive and accurate reference information, and further optimize the decision-making effect. Through comprehensive analysis and learning of market price and load forecasting factors, the system can better identify and manage market risks and provide participants with more accurate risk assessment and response strategies. At the same time, the design of participation strategies in different markets can enable the energy storage system to respond to market demand and price changes more flexibly, and improve its benefits and competitiveness in participating in the market.

[0091] Example 3

[0092] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the data detection module includes a first detection unit and a second detection unit;

[0093] The first detection unit is used to build a data acquisition server inside the factory, monitor the power demand data of the factory in real time through the data acquisition server, and use Flask and Django back-end development frameworks to develop a power demand API application interface on the data acquisition server, so as to use the power demand API application interface to provide the real-time monitored power demand data to the energy storage system management platform through the HTTP communication protocol;

[0094] The second detection unit is used to deploy a new energy storage equipment monitoring system, which uses the new energy storage equipment monitoring system to monitor the comprehensive energy storage data of the energy storage equipment in real time, and develop an energy storage API application interface in the new energy storage equipment monitoring system to provide the comprehensive energy storage data monitored in real time to the new energy storage system management platform through the energy storage API application interface via the HTTP communication protocol;

[0095] The sensor group involved includes current sensors, power meters, peak detectors, battery management systems and voltage sensors.

[0096] The data acquisition module includes a first acquisition unit and a second acquisition unit;

[0097] The first acquisition unit is used to preprocess the detected comprehensive energy storage data and power demand data, the preprocessing method includes removing abnormal values, cleaning and normalization, and classifying and aggregating the preprocessed data to generate a first data set and a second data set;

[0098] The first data set includes an electric load data set, an electric power data set, and an electric energy storage data set;

[0099] The power load data set includes load density Fmd, load peak Ffz, load valley Fgz, reference load Fjz and load change rate Fbh;

[0100] The electric power data set includes rated power Ggl, instantaneous power Gss, peak power Gfz, power response time Gxy, and power density Gmd;

[0101] The power storage data set includes the self-discharge rate Dfd, the number of charge cycles Dxh, the number of discharge cycles Dfx, the cycle rate Dxs and the capacity Drl;

[0102] The first acquisition unit is used to pre-process the detected power demand data, classify and summarize them to generate a power demand data set, and the power demand data includes power consumption Xxh, power demand peak Xfz, harmonic content Xxb, harmonic frequency Xpl and total harmonic distortion rate Xjb.

[0103] In this embodiment, the real-time monitoring and data transmission mechanism of the first detection unit can ensure the timeliness and accuracy of the data, and provide reliable data support for subsequent decision-making. The second detection unit is used to fully understand the status and performance of the energy storage device and provide necessary data support for the effective operation of the energy storage system. The first acquisition unit of the data acquisition module pre-processes the detected comprehensive energy storage data and power demand data, including removing abnormal values, cleaning and normalization. The pre-processed data is classified and summarized to generate a first data set and a second data set, wherein the first data set includes a power load data set, an electric power data set and a power storage data set, providing basic data for subsequent analysis and decision-making. The first acquisition unit also pre-processes the detected power demand data to generate a power demand data set. Such a data set can fully reflect the power demand of the factory and provide an important reference basis for the optimized operation of the energy storage system. In summary, the data detection module provides important data support and decision-making basis for the effective operation of the energy storage system and the optimization of the power market through real-time monitoring and data transmission, energy storage equipment monitoring system deployment, data pre-processing and classification and summary, and the generation of power demand data sets.

[0104] Example 4

[0105] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the first calculation unit includes an electric load calculation unit, an electric power calculation unit and an energy storage device calculation unit;

[0106] The power load calculation unit is used to perform dimensionless processing on the power load data set in the first data set, and then perform analysis and calculation to obtain the load factor Fzxs;

[0107] The electric power calculation unit is used to perform dimensionless processing on the electric power data set in the first data set, and then perform analysis and calculation to obtain the electric power coefficient Glxs;

[0108] The energy storage device calculation unit is used to perform dimensionless processing on the electric energy storage data set in the first data set, and then perform analysis and calculation to obtain the electric storage coefficient Dcxs;

[0109] The load factor Fzxs, electric power factor Glxs and electric storage factor Dcxs are obtained by the following formulas;

[0110]

[0111]

[0112]

[0113] Wherein, Fmd represents load density, Ffz represents load peak value, Fgz represents load valley value, Fjz represents reference load value, Fbh represents load change rate; Ggl represents rated power, Gss represents instantaneous power, Gfz represents peak power, Gxy represents power response time, Gmd represents power density; Dfd represents self-discharge rate, Dxh represents number of charging cycles, Dfx represents number of discharge cycles, Dxs represents cycle rate, and Drl represents capacitance.

[0114] The second calculation unit is used to extract the power demand data set according to the second data set, perform dimensionless processing, and then perform calculation processing to obtain the power demand coefficient Xqxs;

[0115] The power demand coefficient Xqxs is obtained by the following formula;

[0116]

[0117] Wherein, Xxh represents the power consumption, Xfz represents the peak power demand, Xxb represents the harmonic content, Xpl represents the frequency of the harmonic, and Xjb represents the total harmonic distortion rate.

[0118] In this embodiment, the first calculation unit obtains the load coefficient Fzxs, the electric power coefficient Glxs and the electric storage coefficient Dcxs. The calculation of these coefficients provides important indicators and reference basis for the subsequent power demand analysis and energy storage system operation. The second calculation unit obtains the power demand coefficient Xqxs based on the second data set. This coefficient reflects the power demand of the factory and is one of the important bases for formulating the operation strategy of the energy storage system. By dimensionless processing the data, the dimension effect of the data can be eliminated, so that different indicators are comparable, which is conducive to comprehensive analysis and decision-making. At the same time, the analysis and calculation process of the data can deeply explore the characteristics and laws of the data, and provide a scientific basis for system optimization and efficiency improvement. Through these calculation units, the system can comprehensively process information from different data sources and extract key indicators, providing comprehensive data support for system operation and optimization. In general, the effective operation of the first calculation unit and the second calculation unit provides important data support and guidance for the operation strategy formulation and power demand analysis of the energy storage system, which helps to improve the efficiency and performance of the system.

[0119] Example 5

[0120] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the comprehensive calculation unit includes a summary unit and an associated unit;

[0121] The summarizing unit is used to perform dimensionless processing on the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs obtained by the first calculation unit, and then perform summary calculation to obtain the comprehensive electric energy storage factor Cnxs;

[0122] The comprehensive power storage coefficient Cnxs is obtained by the following formula;

[0123]

[0124] Wherein, a1, a2 and a3 represent the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs respectively, and a1+a2≠a3, a3≠0, 0≤a1≤0.47, 0≤a2≤0.62, 0≤a3≤0.56, and the specific values ​​are adjusted and set by the user, and A is the first correction constant.

[0125] The correlation unit is used to perform dimensionless processing on the comprehensive power storage coefficient Cnxs obtained by the summary unit and the power demand coefficient Xqxs obtained by the second calculation unit, and then perform comprehensive correlation calculation to obtain the comprehensive evaluation coefficient Pgxs;

[0126] The comprehensive evaluation coefficient Pgxs is obtained by the following formula:

[0127]

[0128] In the formula, b1 and b2 represent the preset proportional coefficients of the power demand coefficient Xqxs and the comprehensive power storage coefficient Cnxs respectively, and b1≠b2, 0≤b1≤0.53, 0≤b2≤0.47, the specific value of which is adjusted and set by the user, and B is the second correction constant.

[0129] In this embodiment, the summary unit performs dimensionless processing and summary calculation on the load coefficient Fzxs, the electric power coefficient Glxs and the electric storage coefficient Dcxs to obtain the comprehensive electric energy storage coefficient Cnxs. This coefficient comprehensively considers multiple factors such as power load, power and energy storage equipment, and provides an effective indicator for evaluating the energy storage capacity and potential storage capacity of the system. The correlation unit performs dimensionless processing and comprehensive correlation calculation on the comprehensive electric energy storage coefficient Cnxs and the power demand coefficient Xqxs to obtain the comprehensive evaluation coefficient Pgxs. This coefficient comprehensively considers the relationship between power demand and energy storage capacity, and provides an important basis for the comprehensive evaluation and decision-making of the system. Users can flexibly adjust the coefficients and constants in the formula according to actual conditions to adapt to different factory environments and demand characteristics. This flexibility helps to customize and optimize the system, improves the applicability and practicality of the system. The comprehensive evaluation coefficient Pgxs comprehensively considers the matching of the energy storage capacity and power demand of the energy storage system, and can comprehensively evaluate the performance and operating status of the system, providing an important reference for further optimization and improvement of the system. Overall, the effective operation of the comprehensive calculation unit can provide comprehensive data support and scientific basis for the system's performance evaluation and decision-making, which is conducive to the optimization and improvement of the system.

[0130] Example 6

[0131] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: the power evaluation module includes a first evaluation unit, and the evaluation threshold includes a power demand evaluation threshold Q and an energy storage evaluation threshold W;

[0132] The first evaluation unit is used to output a power demand evaluation threshold Q after performing deep learning analysis based on the power market price using the trained algorithm model, and compare the output power demand evaluation threshold Q with the power demand coefficient Xqxs obtained by the second calculation unit;

[0133] The first evaluation unit determines the control scheme of the factory according to the comparison result between the power demand evaluation threshold Q and the power demand coefficient Xqxs, including:

[0134] When the power demand coefficient Xqxs>power demand assessment threshold Q, it means that the current power demand of the factory is abnormal. At this time, the algorithm model is combined to predict the future power price. If the future power price is at the peak of the power price, 80% of the power supply of the factory is set in advance to power the new energy storage equipment, and 20% of the power supply of the factory is set to commercial power supply. If the future power price is at the valley of the power price, the power supply of the factory is set to industrial power, and the new energy storage equipment is stored.

[0135] When the power demand coefficient Xqxs≤power demand assessment threshold Q, it means that the current power demand of the factory is in normal state;

[0136] The power evaluation module also includes a second evaluation unit, which uses the trained algorithm model to perform deep learning analysis based on the power storage market operation strategy data, and then outputs the energy storage evaluation threshold W to compare with the comprehensive evaluation coefficient Pgxs obtained by the associated unit, and generates a target evaluation result based on the comparison result, wherein the target evaluation result is generated based on the comparison result, including;

[0137] When the comprehensive evaluation coefficient Pgxs> the energy storage evaluation threshold W, it means that the new energy storage device is abnormal, and it is necessary to regulate the energy storage device, open the discharge rate of the energy storage device to 100%, fully discharge the factory generation, and replace industrial electricity;

[0138] When the comprehensive evaluation coefficient Pgxs ≤ the energy storage evaluation threshold W, it means that the new energy storage equipment is in a normal state, and it is necessary to shut down the discharge, and combine the algorithm model to identify the target time point corresponding to the valley price of electricity in the electricity market, and set the timed charging for the new energy storage equipment.

[0139] In this embodiment, the first evaluation unit combines the algorithm model to evaluate the power demand of the factory in real time, and when an abnormal situation is detected, the corresponding control strategy can be taken in time. By converting industrial electricity and energy storage power supply according to the peak and valley of electricity prices, the abnormal power demand can be effectively responded to and the normal operation of the factory can be guaranteed. The first evaluation unit evaluates the power demand based on the algorithm model, and combines the current power price and meteorological environment and other factors to realize the intelligent scheduling of the factory energy. This intelligent scheduling can maximize the use of cheap electricity and energy storage equipment and reduce electricity costs while ensuring the normal operation of the factory. The second evaluation unit evaluates the state of the energy storage equipment and can make targeted adjustments when an abnormality is detected. By adjusting the discharge rate and charge and discharge strategy of the energy storage equipment, the energy storage equipment is guaranteed to be in normal working condition, which improves the reliability and stability of the system. Through intelligent scheduling and the rational use of energy storage equipment, the energy consumption cost of the factory can be reduced and the energy utilization rate can be improved. In particular, the conversion of industrial electricity and energy storage power supply during the peak and valley of electricity prices can effectively smooth the load and reduce the peak electricity cost. Through real-time monitoring and intelligent scheduling, it can better respond to changes in the power market and improve market operation efficiency. The system's intelligent scheduling can flexibly respond to changes in market prices and demand, providing strong support for the smooth operation of the power market. Overall, the design of the power assessment module can realize real-time monitoring and regulation of factory power demand and energy storage equipment status, improve energy utilization efficiency and power market operation efficiency, and provide important guarantees for the stable operation of factories and power markets.

[0140] Example 7

[0141] See also Figure 1 and Figure 2 , an evaluation system method based on a new energy storage fusion power market algorithm model, comprising the following steps:

[0142] S1. Set up a data detection unit, establish a data acquisition server and an energy storage equipment monitoring system, obtain the factory power demand and energy storage equipment data in real time, use the back-end development framework, develop an API application interface, transmit the real-time monitoring data to the management platform, and then pre-process the acquired data to generate the first and second data sets;

[0143] S2. Build a power market analysis module based on data, including power market unit, strategy operation unit and deep learning unit, use time series analysis and machine learning methods to establish market price forecasting mechanism and load forecasting strategy, use deep learning technology to learn the market and strategy, and generate auxiliary evaluation mechanism;

[0144] S3, using the first data set and the second data set to perform dimensionless processing, calculate the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs, and perform summary calculation to obtain the comprehensive electric energy storage factor Cnxs, and perform correlation calculation with the electric power demand factor Xqxs to obtain the comprehensive evaluation coefficient Pgxs;

[0145] S4. Combined with the power demand assessment threshold Q set by the algorithm model, conduct a preliminary comparative assessment, and adjust the factory power supply mode according to the assessment results to optimize energy utilization efficiency;

[0146] S5. Set the energy storage evaluation threshold W, conduct a secondary comparative evaluation of the comprehensive evaluation coefficient Pgxs, and adjust the energy storage equipment according to the evaluation results to respond to the power market and optimize energy utilization.

[0147] The storage medium stores program instructions for executing any one of the above-mentioned evaluation systems based on a novel energy storage fusion power market algorithm model;

[0148] A computer device comprising: one or more processors;

[0149] The processor is used to store one or more programs;

[0150] When the one or more programs are executed by the one or more processors, an evaluation system based on a novel energy storage fusion power market algorithm model as described above is implemented.

[0151] Specific example:

[0152] Data collection:

[0153] Load density Fmd: 4.52, load peak Ffz: 8.73, load valley Fgz: 9.21, reference load Fjz: 2.84, load change rate Fbh: 6.17;

[0154] Rated power Ggl: 2.04, instantaneous power Gss: 7.38, peak power Gfz: 4.79, power response time Gxy: 9.09, power density Gmd: 8.05, max (Gmd): 10;

[0155] Self-discharge rate Dfd: 2.77, number of charge cycles Dxh: 3.41, number of discharge cycles Dfx: 6.88, cycle rate Dxs: 4.17, capacitance Drl: 5.62;

[0156] Power consumption Xxh: 7.75, power demand peak Xfz: 2.34, harmonic content Xxb: 6.59, harmonic frequency Xpl: 4.29, total harmonic distortion rate Xjb: 5.46;

[0157] a1=0.04, a2=0.27, a3=0.02, b1=0.12, b2=0.34, first correction constant A: 0.05, second correction constant B: 0.07;

[0158] Load factor Fzxs:

[0159] Electric power coefficient Glxs:

[0160] Storage coefficient Dcxs:

[0161] Electricity demand coefficient Xqxs:

[0162] Comprehensive power storage coefficient Cnxs:

[0163] Comprehensive evaluation coefficient Pgxs:

[0164] All data values ​​are retained to two decimal places;

[0165] The power demand assessment threshold Q is set to 1. When the power demand coefficient Xqxs>power demand assessment threshold Q, it means that the current power demand of the factory is abnormal. At this time, the algorithm model is combined to analyze the power price at the current power consumption time. If the current time point is at the peak of the power price, 80% of the industrial power will be shut down and converted to energy storage power supply. If the current time point is at the valley of the power price, the power supply will be converted to industrial power.

[0166] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An evaluation system based on a new energy storage fusion power market algorithm model, characterized in that: include: Power market analysis module, data detection module, data acquisition module, data calculation module and power evaluation module; The power market analysis module is used to build an algorithm model, crawl energy storage related data and historical data of the energy storage system's operation strategy, and input the energy storage related data and historical data of the energy storage system's operation strategy into the algorithm model to train the algorithm model; The data detection module is used to obtain the power demand data of the factory and the comprehensive energy storage data of the new energy storage equipment in real time; The data acquisition module is used to generate a first data set and a second data set after classifying, summarizing and preprocessing the acquired power demand data and comprehensive energy storage data; The data calculation module is used to analyze and calculate the comprehensive power storage coefficient Cnxs and the power demand coefficient Xqxs after dimensionless processing based on the first data set and the second data set, and associate the comprehensive power storage coefficient Cnxs with the obtained power demand coefficient Xqxs to obtain a comprehensive evaluation coefficient Pgxs; The data calculation module includes a first calculation unit; The first calculation unit includes an electric load calculation unit, an electric power calculation unit and an energy storage device calculation unit; The power load calculation unit is used to perform dimensionless processing on the power load data set in the first data set, and then perform analysis and calculation to obtain the load factor Fzxs; The electric power calculation unit is used to perform dimensionless processing on the electric power data set in the first data set, and then perform analysis and calculation to obtain the electric power coefficient Glxs; The energy storage device calculation unit is used to perform dimensionless processing on the electric energy storage data set in the first data set, and then perform analysis and calculation to obtain the electric storage coefficient Dcxs; The load factor Fzxs, electric power factor Glxs and electric storage factor Dcxs are obtained by the following formulas: Where, Fmd represents load density, Ffz represents load peak value, Fgz represents load valley value, Fjz represents reference load, Fbh represents load change rate; Ggl represents rated power, Gss represents instantaneous power, Gfz represents peak power, Gxy represents power response time, Gmd represents power density; Dfd represents self-discharge rate, Dxh represents number of charging cycles, Dfx represents number of discharging cycles, Dxs represents cycle rate, and Drl represents capacitance; The data calculation module further includes a second calculation unit, which is used to perform dimensionless processing on the power demand data set in the second data set and then calculate to obtain the power demand coefficient Xqxs; The power demand coefficient Xqxs is obtained by the following formula: In the formula, Xxh represents the power consumption, Xfz represents the peak power demand, Xxb represents the harmonic content, Xpl represents the frequency of the harmonic, and Xjb represents the total harmonic distortion rate; The data calculation module further includes a comprehensive calculation unit, and the comprehensive calculation unit includes a summary unit; The summarizing unit is used to perform dimensionless processing on the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs obtained by the first calculating unit, and then perform summarizing calculation to obtain the comprehensive electric energy storage factor Cnxs; The comprehensive power storage coefficient Cnxs is obtained by the following formula: Wherein, a1, a2 and a3 represent the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs respectively, and a1+a2≠a3, a3≠0, 0≤a1≤0.47, 0≤a2≤0.62, 0≤a3≤0.56, and the specific values ​​are adjusted and set by the user, and A is the first correction constant; The comprehensive calculation unit further includes a correlation unit, which is used to perform dimensionless processing on the comprehensive power storage coefficient Cnxs obtained by the summary unit and the power demand coefficient Xqxs obtained by the second calculation unit and then perform comprehensive correlation calculation to obtain a comprehensive evaluation coefficient Pgxs; The comprehensive evaluation coefficient Pgxs is obtained by the following formula: Wherein, b1 and b2 represent the preset proportional coefficients of the power demand coefficient Xqxs and the comprehensive power storage coefficient Cnxs respectively, and b1≠b2, 0≤b1≤0.53, 0≤b2≤0.47, and the specific value is adjusted and set by the user, and B is the second correction constant; The power evaluation module is used to output an evaluation threshold using the trained algorithm model, and determine the factory's control plan based on the evaluation threshold, the comprehensive evaluation coefficient Pgxs, and the power demand coefficient Xqxs.

2. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 1 is characterized in that: The energy storage related data include electricity market data and energy storage system status data. The electricity market data include market prices, electricity policy data, weather data and market rule data. The energy storage system status data include SOC, power reserve and charging and discharging power.

3. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 2 is characterized in that: The power market analysis module includes a power market unit, a strategic operation unit and a deep learning unit; The power market unit is used to develop a data crawling tool to use the crawling tool to obtain historical power market data and historical energy storage system status data from relevant websites and API interfaces of the power market, and to pre-process the acquired historical power market data and historical energy storage system status data, wherein the pre-processing includes cleaning, data normalization and standardization processing; The strategy operation unit accesses the meteorological system and the power market system, extracts the historical load data, weather factors and power market environmental factors of the power market and the meteorological system, combines the target market price at the future moment and the operation strategy of the energy storage system, and designs the participation strategy of the energy storage system in different markets, where the different markets include the energy market, the capacity market and the reserve market; The deep learning unit uses an algorithm model to set the historical data of the target market price data and the operation strategy data of the energy storage system obtained by the power market unit and the strategy operation unit as a training set, and at the same time, feature-marks the data in the training set involving the peak power demand time period and the off-peak power demand time period of the factory, and uses the feature-marked data as a verification set, and uses the data in the verification set to train the algorithm model.

4. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 2 is characterized in that: The data detection module includes a first detection unit and a second detection unit; The first detection unit is used to build a data acquisition server inside the factory, monitor the power demand data of the factory in real time through the data acquisition server, and use Flask and Django back-end development frameworks to develop a power demand API application interface on the data acquisition server, so as to use the power demand API application interface to provide the real-time monitored power demand data to the energy storage system management platform through the HTTP communication protocol; The second detection unit is used to deploy a new energy storage equipment monitoring system, which uses the new energy storage equipment monitoring system to monitor the comprehensive energy storage data of the energy storage equipment in real time. By developing an energy storage API application interface in the new energy storage equipment monitoring system, the energy storage API application interface can be used to provide the real-time monitored comprehensive energy storage data to the new energy storage system management platform through the HTTP communication protocol.

5. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 1 is characterized in that: The data acquisition module includes a first acquisition unit and a second acquisition unit; The first acquisition unit is used to preprocess the detected comprehensive energy storage data, wherein the preprocessing includes removing outliers, cleaning and normalizing, and classifying and aggregating the preprocessed comprehensive energy storage data to generate a first data set; The first data set includes an electric load data set, an electric power data set and an electric energy storage data set; The electric load data set includes load density Fmd, load peak value Ffz, load valley value Fgz, reference load value Fjz and load change rate Fbh; The electric power data set includes rated power Ggl, instantaneous power Gss, peak power Gfz, power response time Gxy and power density Gmd; The electric energy storage data set includes a self-discharge rate Dfd, a number of charging cycles Dxh, a number of discharging cycles Dfx, a cycle rate Dxs and a capacity Drl; The second acquisition unit is used to generate a second data set after preprocessing the detected power demand data, and to generate a power demand data set by classifying and aggregating the second data set, wherein the power demand data includes power consumption Xxh, power demand peak Xfz, harmonic content Xxb, harmonic frequency Xpl and total harmonic distortion rate Xjb.

6. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 1 is characterized in that: The power evaluation module includes a first evaluation unit and a second evaluation unit, and the evaluation threshold includes a power demand evaluation threshold Q and an energy storage evaluation threshold W; The first evaluation unit determines the control scheme of the factory according to the comparison result between the power demand evaluation threshold Q and the power demand coefficient Xqxs, including: When the power demand coefficient Xqxs>power demand assessment threshold Q, it means that the current power demand of the factory is abnormal. At this time, the algorithm model is combined to predict the future power price. If the future power price is at the peak of the power price, 80% of the power supply of the factory is set in advance to power the new energy storage equipment, and 20% of the power supply of the factory is set to commercial power supply. If the future power price is at the valley of the power price, the power supply of the factory is set to industrial power, and the new energy storage equipment is stored. When the power demand coefficient Xqxs≤the power demand assessment threshold Q, the energy storage assessment threshold W is compared with the comprehensive assessment coefficient Pgxs, and the plant control plan is determined based on the comparison result of the energy storage assessment threshold W and the comprehensive assessment coefficient Pgxs.

7. The evaluation system based on the novel energy storage fusion power market algorithm model according to claim 6 is characterized in that: The second evaluation unit determines the control scheme of the plant according to the comparison result between the energy storage evaluation threshold W and the comprehensive evaluation coefficient Pgxs, including: When the comprehensive evaluation coefficient Pgxs> the energy storage evaluation threshold W, it means that the new energy storage device is abnormal. Then it is necessary to regulate the new energy storage device and open the discharge rate of the new energy storage device to 100%. The new energy storage device is used to fully discharge the factory and replace the factory's industrial electricity. When the comprehensive evaluation coefficient Pgxs ≤ the energy storage evaluation threshold W, it means that the new energy storage device is in a normal state. In this case, the discharge of the new energy storage device is shut down, and the trained algorithm model is combined to identify the target time point corresponding to the valley price of electricity in the electricity market, so as to use commercial power supply to charge the new energy storage device at the target time point.

8. An evaluation method based on a novel energy storage fusion power market algorithm model, comprising an evaluation system based on a novel energy storage fusion power market algorithm model as described in any one of claims 1 to 7, characterized in that: The following steps are involved: S1. Crawling historical data on energy storage related data and operation strategies of energy storage systems, and inputting the historical data on energy storage related data and operation strategies of energy storage systems into an algorithm model to train the algorithm model; S2. Acquire the power demand data of the factory and the comprehensive energy storage data of the new energy storage equipment in real time, classify, summarize and pre-process the acquired power demand data and comprehensive energy storage data to generate a first data set and a second data set; S3, using the first data set and the second data set to perform dimensionless processing, calculate the load factor Fzxs, the electric power factor Glxs and the electric storage factor Dcxs, and perform summary calculation to obtain the comprehensive electric energy storage factor Cnxs, and perform correlation calculation with the electric power demand factor Xqxs to obtain the comprehensive evaluation coefficient Pgxs; S4. Use the trained algorithm model to output the evaluation threshold, and determine the factory's control plan based on the evaluation threshold, comprehensive evaluation coefficient Pgxs, and power demand coefficient Xqxs.

9. A storage medium, characterized in that: The storage medium stores program instructions for executing an evaluation system based on a novel energy storage fusion power market algorithm model as described in any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, an evaluation system based on a novel energy storage fusion power market algorithm model as described in any one of claims 1 to 7 is implemented.

Images