Energy storage system reliability assessment method and system based on data analysis

Abstract

The present application provides a method and system for evaluating the reliability of an energy storage system based on data analysis, and the method steps are as follows: S1: With days as the sampling unit and hours as the sampling interval, collect the historical load data, operation data and environmental data of the power supply system to construct a historical data set; S2: Construct a load prediction model based on data analysis, and train the load prediction model through the historical data set; S3: Predict the load of the power supply system according to the trained load prediction model; S4: Predict the power generation of the photovoltaic power generation system in a day; S5: Evaluate the reliability of the energy storage system; and execute corresponding decisions based on the reliability of the energy storage system. The present application constructs a load prediction model by analyzing historical data, predicts the power load, and evaluates the reliability of the energy storage system, which not only ensures the reliability of the operation of the energy storage system but also saves fuel costs.

Description

Technical Field

[0001] The present application relates to the field of reliability assessment of energy storage systems, and specifically to a reliability assessment method and system for energy storage systems based on data analysis. Background Art

[0002] In some islands or remote areas, it is difficult to connect the power supply system to the power grid. Therefore, it is necessary to establish a multi-energy power supply system based on the actual situation of the area. The existing multi-energy power supply system mainly includes photovoltaic power generation system, wind power generation system, diesel power generation system, energy storage system, etc. By utilizing clean energy such as solar energy and wind power, the power supply cost can be effectively reduced.

[0003] However, solar energy, wind power and other energy sources are greatly affected by environmental changes, and diesel generator systems are often needed to supplement the power supply system. Diesel generator systems consume a lot of diesel during the power generation process, which is costly and difficult to transport to islands or remote areas. Therefore, regulating the power supply system through energy storage systems has become the most important means to reduce the electricity cost in the region. At the same time, ensuring the reliability of the energy storage system during the adjustment of the power supply system through the energy storage system is related to the stability of the power supply in the region, which is an important guarantee for production and life in the region. Summary of the invention

[0004] The present application provides a method for evaluating the reliability of an energy storage system based on data analysis, which is used to solve the technical problems of poor stability and reliability of the energy storage system and high power supply cost in the independent power supply system in the prior art.

[0005] A reliability assessment method for an energy storage system based on data analysis, wherein the power supply system includes an energy storage system, a photovoltaic power generation system, and a diesel power generation system; the specific steps of the reliability assessment method for the energy storage system are:

[0006] S1: With days as sampling units and hours as sampling intervals, collect historical load data, operation data and environmental data of the power supply system to build a historical data set;

[0007] S2: Using environmental data as input and historical load data as output, a load prediction model based on data analysis is constructed, and the load prediction model is trained using historical data sets;

[0008] S3: Obtain environmental variables at the time point to be evaluated, and predict the load of the power supply system according to the trained load prediction model;

[0009] S4: predicting the power generation of the photovoltaic power generation system in a day based on the operation data of the power supply system and the environmental data;

[0010] S5: Evaluate the reliability of the energy storage system based on the predicted power supply system load data, photovoltaic power generation system power generation data and energy storage system data; and make corresponding decisions based on the reliability of the energy storage system.

[0011] Preferably, the specific method of data collection in step S1 is:

[0012] The load data includes the power consumption of the power supply area within a unit sampling time, the environmental data includes the sunshine duration and temperature extremes of a day, and the operation data of the power supply system includes the power generation power of the photovoltaic power generation system within a unit sampling time, the output power of the energy storage system within a unit sampling time, and the output power of the diesel power generation system within a unit sampling time;

[0013] The historical data set also includes the maximum power that the energy storage system is allowed to output per unit time, and the maximum power that the diesel power generation system is allowed to output per unit time.

[0014] Preferably, the specific steps of analyzing the historical data set and constructing the load prediction model in step S2 are:

[0015] S2.1: Cluster the temperature extreme value data using the K nearest neighbor algorithm to obtain Q data subsets, and calculate the load mean data of the Q data subsets respectively;

[0016]

[0017] Where P i j is the load of the i-th sampling period in the j-th data subset in one day, m is the number of data in the j-th data subset, p z is the load of the zth data in the jth data subset in the i-th sampling time period.

[0018] S2.2: Take the mean data as the load data of a single data subset, and build a load prediction model based on data analysis through the load data of Q data subsets. The input of the load prediction model is the temperature extreme value data, and the output is the mean data of the load data within a single sampling time period.

[0019] Preferably, the specific steps of predicting the load of the power supply system in step S3 are:

[0020] S3.1: Obtain the temperature extreme value data and sunshine duration data of the day to be evaluated through weather forecast data;

[0021] S3.2: Using the extreme temperature data as the input of the load prediction model trained in step S2, the extreme temperature data is matched to the corresponding data subset, and the historical load average of the data subset is output as the load value for each time period on the day to be evaluated.

[0022] Preferably, the specific steps of predicting the power generation of the photovoltaic power generation system in a day according to the operation data and environmental data of the power supply system in step S4 are:

[0023] S4.1: Taking the sunshine duration data and temperature extreme value data of one day in the historical data set as input and the photovoltaic power generation power in each unit sampling time as output, a power generation prediction model based on a neural network is constructed, and the power generation prediction model is trained with historical data;

[0024] S4.2: Predict the photovoltaic power generation at each time period of the day by using the sunshine duration data and temperature extreme value data obtained in step S3.1 as the input of the power generation prediction model.

[0025] Preferably, the specific steps of evaluating the reliability of the energy storage system in step S5 and executing corresponding decisions according to the reliability of the energy storage system are:

[0026] S5.1: Evaluate the reliability of the energy storage system based on the predicted photovoltaic power generation and the estimated load values ​​at each time period:

[0027]

[0028] In the formula, g is any number from 1 to 24, W fg is the total load power consumption from the initial time to time g in a day, W sg The maximum power that the energy storage system and photovoltaic power generation system are allowed to output from the initial time to time g in a day; is the predicted load data at the gth moment of the day, is the photovoltaic power generation data at the gth moment of the day, W e is the stored capacity of the energy storage system at the initial time of the day, and η is the discharge safety factor of the storage system;

[0029] If g takes any value from 1 to 24, W is satisfied. fg <W sg , then the energy storage system operates reliably, otherwise the energy storage system operates unreliably;

[0030] S5.2: When it is determined that the current energy storage system is unreliable, the power supply system is supplemented with electricity through the diesel generator set:

[0031] If W fg <W sg And W f(g+1) ≥W s(g+1) , then the diesel generator set is started from the gth moment to supplement the power supply system;

[0032] when When the diesel generator set stops working, When , the diesel generator set is started again to work, where: n is any time after time g+1, and k is any time after time n.

[0033] A reliability assessment system for an energy storage system based on data analysis, used to implement the above-mentioned reliability assessment method for an energy storage system based on data analysis, comprising:

[0034] Data collection module: used to collect historical load data, operation data and environmental data of the power supply system with days as the sampling unit and hours as the sampling interval, and build a historical data set;

[0035] Load training module: used to build a load prediction model based on data analysis with environmental data as input and historical load data as output, and train the load prediction model through historical data sets;

[0036] Load prediction module: used to obtain environmental variables at the time point to be evaluated and predict the load of the power supply system based on the trained load prediction model;

[0037] Power generation prediction module: used to predict the power generation of the photovoltaic power generation system in a day based on the operation data and environmental data of the power supply system;

[0038] Reliability assessment module: used to assess the reliability of the energy storage system based on the predicted power supply system load data, photovoltaic power generation system power generation data and energy storage system data; and to make corresponding decisions based on the reliability of the energy storage system.

[0039] Due to the adoption of the above technical solution, the present invention has the following advantages:

[0040] This application builds a load prediction model by analyzing historical data, predicts the power load through environmental data and the load prediction model, and evaluates the reliability of the energy storage system without using a diesel generator set, thereby ensuring the reliability of the energy storage system operation and saving fuel costs.

[0041] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings of the present invention are as follows.

[0043] Figure 1This is a flow chart of the energy storage system reliability assessment method based on data analysis in this application. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] Embodiment 1:

[0046] like Figure 1 A reliability assessment method for an energy storage system based on data analysis is shown, wherein the power supply system includes an energy storage system, a photovoltaic power generation system, and a diesel power generation system; the specific steps of the reliability assessment method for the energy storage system are:

[0047] S1: With days as sampling units and hours as sampling intervals, collect historical load data, operation data and environmental data of the power supply system to build a historical data set;

[0048] S2: Using environmental data as input and historical load data as output, a load prediction model based on data analysis is constructed, and the load prediction model is trained using historical data sets;

[0049] S3: Obtain environmental variables at the time point to be evaluated, and predict the load of the power supply system according to the trained load prediction model;

[0050] S4: predicting the power generation of the photovoltaic power generation system in a day based on the operation data of the power supply system and the environmental data;

[0051] S5: Evaluate the reliability of the energy storage system based on the predicted power supply system load data, photovoltaic power generation system power generation data and energy storage system data; and make corresponding decisions based on the reliability of the energy storage system.

[0052] In this embodiment, taking an island as an example, the island is far away from the land and needs to establish an independent power supply system. At the same time, the island is located in a tropical area with sufficient sunlight. Therefore, photovoltaic power generation is selected as the main power supply energy source for the island. In other embodiments, other clean energy such as wind power generation can also be added as the main power supply energy source.

[0053] The specific method of data collection in step S1 is:

[0054] The load data includes the power consumption of the power supply area within a unit sampling time, the environmental data includes the sunshine duration and temperature extremes of a day, and the operation data of the power supply system includes the power generation power of the photovoltaic power generation system within a unit sampling time, the output power of the energy storage system within a unit sampling time, and the output power of the diesel power generation system within a unit sampling time;

[0055] The historical data set also includes the maximum power that the energy storage system is allowed to output per unit time, and the maximum power that the diesel power generation system is allowed to output per unit time.

[0056] The specific steps of analyzing the historical data set and building the load prediction model in step S2 are:

[0057] S2.1: Cluster the temperature extreme value data using the K nearest neighbor algorithm to obtain Q data subsets, and calculate the load mean data of the Q data subsets respectively;

[0058]

[0059] Where P i j is the load of the i-th sampling period in the j-th data subset in one day, m is the number of data in the j-th data subset, p z is the load of the zth data in the jth data subset in the i-th sampling time period.

[0060] S2.2: Take the mean data as the load data of a single data subset, and build a load prediction model based on data analysis through the load data of Q data subsets. The input of the load prediction model is the temperature extreme value data, and the output is the mean data of the load data within a single sampling time period.

[0061] The specific steps of predicting the load of the power supply system in step S3 are:

[0062] S3.1: Obtain the temperature extreme value data and sunshine duration data of the day to be evaluated through weather forecast data;

[0063] S3.2: Using the extreme temperature data as the input of the load prediction model trained in step S2, the extreme temperature data is matched to the corresponding data subset, and the historical load average of the data subset is output as the load value for each time period on the day to be evaluated.

[0064] The specific steps of predicting the power generation of the photovoltaic power generation system in a day according to the operation data and environmental data of the power supply system in step S4 are:

[0065] S4.1: Taking the sunshine duration data and temperature extreme value data of one day in the historical data set as input and the photovoltaic power generation power in each unit sampling time as output, a power generation prediction model based on a neural network is constructed, and the power generation prediction model is trained with historical data;

[0066] S4.2: Predict the photovoltaic power generation at each time period of the day by using the sunshine duration data and temperature extreme value data obtained in step S3.1 as the input of the power generation prediction model.

[0067] In step S5, the reliability of the energy storage system is evaluated; and the specific steps of executing corresponding decisions according to the reliability of the energy storage system are:

[0068] S5.1: Evaluate the reliability of the energy storage system based on the predicted photovoltaic power generation and the estimated load values ​​at each time period:

[0069]

[0070] In the formula, g is any number from 1 to 24, W fg is the total load power consumption from the initial time to time g in a day, W sg The maximum power that the energy storage system and photovoltaic power generation system are allowed to output from the initial time to time g in a day; is the predicted load data at the gth moment of the day, is the photovoltaic power generation data at the gth moment of the day, W e is the stored capacity of the energy storage system at the initial time of the day, and η is the discharge safety factor of the storage system;

[0071] If g takes any value from 1 to 24, W is satisfied. fg <W sg , then the energy storage system operates reliably, otherwise the energy storage system operates unreliably;

[0072] S5.2: When it is determined that the current energy storage system is unreliable, the power supply system is supplemented with electricity through the diesel generator set:

[0073] If W fg <W sg And W f(g+1) ≥W s(g+1) , then the diesel generator set is started from the gth moment to supplement the power supply system;

[0074] when When the diesel generator set stops working, When , the diesel generator set is started again to work, where: n is any time after time g+1, and k is any time after time n.

[0075] Embodiment 2:

[0076] A reliability assessment system for an energy storage system based on data analysis: used to implement the reliability assessment method for an energy storage system based on data analysis described in Example 1, comprising:

[0077] Data collection module: used to collect historical load data, operation data and environmental data of the power supply system with days as the sampling unit and hours as the sampling interval, and build a historical data set;

[0078] Load training module: used to build a load prediction model based on data analysis with environmental data as input and historical load data as output, and train the load prediction model through historical data sets;

[0079] Load prediction module: used to obtain environmental variables at the time point to be evaluated and predict the load of the power supply system based on the trained load prediction model;

[0080] Power generation prediction module: used to predict the power generation of the photovoltaic power generation system in a day based on the operation data and environmental data of the power supply system;

[0081] Reliability assessment module: used to assess the reliability of the energy storage system based on the predicted power supply system load data, photovoltaic power generation system power generation data and energy storage system data; and to make corresponding decisions based on the reliability of the energy storage system.

[0082] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0083] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A reliability assessment method for an energy storage system based on data analysis, a power supply system includes an energy storage system, a photovoltaic power generation system, and a diesel power generation system; characterized in that: The specific steps of the energy storage system reliability assessment method are: S1: With days as sampling units and hours as sampling intervals, collect historical load data, operation data and environmental data of the power supply system to build a historical data set; S2: Using environmental data as input and historical load data as output, a load prediction model based on data analysis is constructed, and the load prediction model is trained using historical data sets; S3: Obtain environmental variables at the time point to be evaluated, and predict the load of the power supply system according to the trained load prediction model; S4: predicting the power generation of the photovoltaic power generation system in a day based on the operation data of the power supply system and the environmental data; S5: Evaluate the reliability of the energy storage system based on the predicted power supply system load data, the power generation data of the photovoltaic power generation system and the data of the energy storage system; and make corresponding decisions based on the reliability of the energy storage system; The specific method of data collection in step S1 is: The load data includes the power consumption of the power supply area within a unit sampling time, the environmental data includes the sunshine duration and temperature extremes of a day, and the operation data of the power supply system includes the power generation power of the photovoltaic power generation system within a unit sampling time, the output power of the energy storage system within a unit sampling time, and the output power of the diesel power generation system within a unit sampling time; The historical data set also includes the maximum power allowed to be output per unit time by the energy storage system and the maximum power allowed to be output per unit time by the diesel power generation system; The specific steps of analyzing the historical data set and building the load prediction model in step S2 are: S2.1: Cluster the temperature extreme value data using the K nearest neighbor algorithm to obtain Q data subsets, and calculate the load mean data of the Q data subsets respectively; In the formula, For the The first The load during the sampling period, For the The number of data in a data subset, For the In the data subset The data is in The load during each sampling period; S2.2: Taking the mean data as the load data of a single data subset, and constructing a load prediction model based on data analysis through the load data of Q data subsets, the input of the load prediction model is the temperature extreme value data, and the output is the mean data of the load data within a single sampling time period; In step S5, the reliability of the energy storage system is evaluated; and the specific steps of executing corresponding decisions according to the reliability of the energy storage system are: S5.1: Evaluate the reliability of the energy storage system based on the predicted photovoltaic power generation and the estimated load values ​​at each time period: In the formula, Any number from 1 to 24. From the beginning of the day to The total load power consumption at the moment, From the beginning of the day to The maximum power that the energy storage system and photovoltaic power generation system are allowed to output at the moment; For the day Forecast load data at the moment, For the day Photovoltaic power generation data at the moment, is the amount of electricity stored in the energy storage system at the beginning of the day, is the discharge safety factor of the storage system; like When any value from 1 to 24 is taken, it satisfies , the energy storage system operates reliably, otherwise the energy storage system operates unreliably; S5.2: When it is determined that the current energy storage system is unreliable, the power supply system is supplemented with electricity through the diesel generator set: like and , then from Always start the diesel generator set to supplement the power supply system; when When the diesel generator set stops working, When the diesel generator set is started again, the following steps are performed: for At any time after the time, for Any time after time.

2. A method for evaluating the reliability of an energy storage system based on data analysis as claimed in claim 1, characterized in that: The specific steps of predicting the load of the power supply system in step S3 are: S3.1: Obtain the temperature extreme value data and sunshine duration data of the day to be evaluated through weather forecast data; S3.2: Using the extreme temperature data as the input of the load prediction model trained in step S2, the extreme temperature data is matched to the corresponding data subset, and the historical load average of the data subset is output as the load value for each time period on the day to be evaluated.

3. A method for evaluating the reliability of an energy storage system based on data analysis as claimed in claim 2, characterized in that: The specific steps of predicting the power generation of the photovoltaic power generation system in a day according to the operation data and environmental data of the power supply system in step S4 are: S4.1: Taking the sunshine duration data and temperature extreme value data of one day in the historical data set as input and the photovoltaic power generation power in each unit sampling time as output, a power generation prediction model based on a neural network is constructed, and the power generation prediction model is trained with historical data; S4.2: Predict the photovoltaic power generation at each time period of the day by using the sunshine duration data and temperature extreme value data obtained in step S3.1 as the input of the power generation prediction model.

4. A reliability assessment system for energy storage systems based on data analysis, characterized in that: The method for evaluating the reliability of an energy storage system based on data analysis according to any one of claims 1 to 3 comprises: Data collection module: used to collect historical load data, operation data and environmental data of the power supply system with days as the sampling unit and hours as the sampling interval, and build a historical data set; Load training module: used to build a load prediction model based on data analysis with environmental data as input and historical load data as output, and train the load prediction model through historical data sets; Load prediction module: used to obtain environmental variables at the time point to be evaluated and predict the load of the power supply system based on the trained load prediction model; Power generation prediction module: used to predict the power generation of the photovoltaic power generation system in a day based on the operation data and environmental data of the power supply system; Reliability assessment module: used to assess the reliability of the energy storage system based on the predicted power supply system load data, photovoltaic power generation system power generation data and energy storage system data; and to make corresponding decisions based on the reliability of the energy storage system.

Images