Energy storage dispatching method, system and equipment for energy storage power station and storage medium

Abstract

The embodiment of the invention provides an energy storage scheduling method, system and device for an energy storage power station and a storage medium. The method comprises the steps that multiple different types of new energy data are acquired; performing data preprocessing on the multiple different types of new energy data to obtain multiple different types of target new energy data respectively corresponding to the multiple different types; predicting the target new energy data through a predetermined energy prediction model, and determining an energy prediction result; and generating an energy storage scheduling sequence according to the energy prediction result to control switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence, the energy storage scheduling sequence including an input scheduling sequence and an output scheduling sequence. According to the scheme, optimization among different energy sources can be realized, and the stability of the power grid voltage is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of electric energy storage, in particular to an energy storage scheduling method, system, device and storage medium for an energy storage power station. BACKGROUND

[0002] With the increasing demand for clean energy worldwide, the proportion of renewable energy such as wind energy, water energy and solar energy in power supply is gradually increasing. However, wind energy, water energy and solar energy have significant randomness and volatility, and their power generation output is greatly affected by natural conditions such as wind speed, water resources, light intensity and other factors, which brings great challenges to the stable operation of the power grid. For example, when the wind speed suddenly changes, water resources are scarce or sunlight is blocked, the output power of wind farms, hydropower plants and photovoltaic power stations will change sharply, which may cause problems such as power grid voltage fluctuation and frequency instability.

[0003] In order to alleviate these problems, energy storage technology is introduced into the wind-water-light power generation system. The existing related technology has deficiencies in dealing with the uncertainty of wind-water-light power generation and the efficient use of energy storage systems. Some researches only focus on the optimal configuration of energy storage capacity, ignoring the collaborative scheduling strategy between different types of power generation. Therefore, it is of great practical significance to develop an optimal scheduling method that can effectively integrate wind-water-light resources. SUMMARY

[0004] The embodiments of the present application expect to provide an energy storage scheduling method, system, device and storage medium for an energy storage power station, which can realize the optimization of different energies and improve the stability of the power grid voltage.

[0005] The technical solution of the present application is implemented as follows: In a first aspect, the embodiments of the present application provide an energy storage scheduling method for an energy storage power station, which comprises: acquiring a plurality of different types of new energy data; performing data preprocessing on the plurality of different types of new energy data to obtain target new energy data corresponding to each of the plurality of different types; predicting the target new energy data through a predetermined energy prediction model to determine an energy prediction result; generating an energy storage scheduling sequence according to the energy prediction result to control the switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence, wherein the energy storage scheduling sequence comprises an input scheduling sequence and an output scheduling sequence.

[0006] In the above scheme, the data preprocessing on the plurality of different types of new energy data to obtain the target new energy data corresponding to each of the plurality of different types comprises: The plurality of different types of new energy data are respectively subjected to data cleaning, and missing data, error data, duplicate data and format conflict data in the new energy data are removed to obtain initial new energy data corresponding to each of the plurality of different types; The initial new energy data corresponding to each of the plurality of different types are respectively subjected to data format unification processing, and target new energy data corresponding to each of the plurality of different types are determined; wherein each group of the target new energy data comprises a group of prediction marks, and the prediction marks are used to represent the iteration number of the corresponding data in the prediction process.

[0007] In the above scheme, the energy prediction model comprises a plurality of sub-prediction models; the plurality of different types of new energy data comprises solar energy new energy data, wind energy new energy data and water energy new energy data; the number of the plurality of sub-prediction models is consistent with the number of types of the plurality of new energy data, and the plurality of sub-prediction models and the plurality of new energy data have a one-to-one correspondence; The target new energy data are predicted by the predetermined energy prediction model to determine the energy prediction result, comprising: The target new energy data corresponding to the solar energy new energy data are predicted by a first sub-prediction model corresponding to the solar energy new energy data in the plurality of sub-prediction models to obtain a first prediction result; wherein the first prediction result comprises a first array, and the first array is composed of the serial number of each group of solar energy new energy data and the iteration number of the prediction marks in each group of the solar energy new energy data in the first sub-prediction model; The target new energy data corresponding to the wind energy new energy data are predicted by a second sub-prediction model corresponding to the wind energy new energy data in the plurality of sub-prediction models to obtain a second prediction result; wherein the second prediction result comprises a second array, and the second array is composed of the serial number of each group of wind energy new energy data and the iteration number of the prediction marks in each group of the wind energy new energy data in the second sub-prediction model; The target new energy data corresponding to the water energy new energy data are predicted by a third sub-prediction model corresponding to the water energy new energy data in the plurality of sub-prediction models to obtain a third prediction result; wherein the third prediction result comprises a third array, and the third array is composed of the serial number of each group of water energy new energy data and the iteration number of the prediction marks in each group of the water energy new energy data in the third sub-prediction model; Based on the first prediction result, the second prediction result and the third prediction result, prediction fusion is performed to obtain the energy prediction result.

[0008] In the scheme, the prediction fusion based on the first prediction result, the second prediction result and the third prediction result obtains the energy prediction result, which includes: Obtain the geographical location information and climate information corresponding to the solar new energy data, the wind new energy data and the water new energy data respectively; For any one of the solar new energy data, the wind new energy data and the water new energy data, based on the geographical location information and the climate information, the spatial feature is determined by feature extraction, and the geographical climate weight is determined according to the spatial feature; Based on the geographical climate weight corresponding to the solar new energy data, the wind new energy data and the water new energy data, the first prediction result, the second prediction result and the third prediction result are fused to obtain the energy prediction result; wherein the energy prediction result includes a fourth array, and the fourth array is composed of each new energy data sequence number and the sum of corresponding iteration numbers in the first array, the second array and the third array.

[0009] In the above scheme, the energy storage scheduling sequence is generated according to the energy prediction result to control the switching of the corresponding access terminal and output terminal in the energy storage power station through the energy storage scheduling sequence, which includes: According to the preset switching frequency, a preset number of points corresponding to the time nodes with larger sum of iteration numbers are selected from the fourth array to generate an output scheduling sequence; Select the new energy data type corresponding to the maximum iteration number in the corresponding first array, second array and third array at each time node as the main energy type to generate an input scheduling sequence.

[0010] In the above scheme, before the energy prediction result is determined by predicting the target new energy data through the pre-determined energy prediction model, the method further includes: Obtain a plurality of different types of new energy historical data, historical geographical location information and historical climate information; wherein the new energy historical data includes new energy training data and new energy test data; Determine the initial geographical climate weight corresponding to the plurality of different types of new energy historical data through the historical geographical location information and the historical climate information; Train the initial sub energy prediction model corresponding to the plurality of different types of new energy historical data through the plurality of different types of new energy training data and the initial geographical climate weight to determine the trained initial sub energy prediction model; Test the trained initial sub-energy prediction model through the new energy test data, and adjust the initial geographical and climate weight according to the test result to determine a historical geographical and climate weight; Based on the historical geographical and climate weight and the multiple different types of new energy training data, continue to train the trained initial sub-energy prediction model until the model accuracy reaches a preset condition to determine the energy prediction model.

[0011] In the above scheme, the method further comprises: Compress the target new energy data to obtain compressed data, and encode the compressed data to obtain a hybrid feature vector; Based on a unified standardized protocol and a double channel, the hybrid feature vector is sent to the energy storage power station; wherein the double channel includes a fiber channel and a 5G channel; If the time for the energy storage power station to receive the hybrid feature vector is greater than a preset time or the energy storage power station does not receive the hybrid feature vector, the hybrid feature vector is re-uploaded until the time for the energy storage power station to receive the hybrid feature vector is less than or equal to the preset time.

[0012] In a second aspect, the embodiments of the present application provide an energy storage scheduling system of an energy storage power station, which comprises an acquisition module, a preprocessing module, a determination module and a scheduling module; wherein, The acquisition module is configured to acquire multiple different types of new energy data; The preprocessing module is configured to perform data preprocessing on the multiple different types of new energy data to obtain target new energy data corresponding to each of the multiple different types; The determination module is configured to predict the target new energy data through a pre-determined energy prediction model to determine an energy prediction result; The scheduling module is configured to generate an energy storage scheduling sequence according to the energy prediction result to control the switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence, wherein the energy storage scheduling sequence comprises an input scheduling sequence and an output scheduling sequence.

[0013] In a third aspect, the embodiments of the present application provide an energy storage scheduling device of an energy storage power station, which comprises a processor and a memory; wherein, The memory is configured to store a computer program; The processor is configured to call and run the computer program from the memory to execute the method as described in the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium storing executable instructions for causing a processor to execute the method according to the first aspect.

[0015] The embodiment of the present application provides a kind of energy storage power station energy storage scheduling method, system, equipment and storage medium, the method comprises: the data preprocessing of the multiple different types of new energy data obtained, obtains the target new energy data of multiple different types respectively;Through data preprocessing, the amount of data transmission can be reduced, so as to improve transmission efficiency;Through the energy prediction model determined in advance, the target new energy data is predicted, and the energy prediction result is determined;Since the target new energy data of multiple different types is predicted, the future resource trend of each new energy data can be understood, and the energy storage scheduling sequence is generated according to the future resource trend of each new energy data to control the switching of corresponding access terminal and output terminal in energy storage power station through energy storage scheduling sequence, the optimization of different energy can be realized, so as to avoid the problems such as grid voltage fluctuation and frequency instability caused by weather change, improve the stability of grid voltage. BRIEF DESCRIPTION OF DRAWINGS

[0016] The drawings incorporated into the specification and forming part of the specification, these drawings show the embodiments consistent with the present application, and together with the specification for the purpose of illustrating the technical solutions of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creating labor.

[0017] The flowchart shown in the drawings is only illustrative, not necessarily including all contents and operations / steps, and not necessarily executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so that the actual execution order may be changed according to the actual situation.

[0018] Figure 1 An optional flowchart of a kind of energy storage power station energy storage scheduling method provided by the embodiment of the present application Figure 1 ; Figure 2 An optional flowchart of a kind of energy storage power station energy storage scheduling method provided by the embodiment of the present application Figure 2 ; Figure 3 An optional flowchart of a kind of energy storage power station energy storage scheduling method provided by the embodiment of the present application Figure 3 ; Figure 4 The structure diagram of a kind of energy storage power station energy storage scheduling system provided by the embodiment of the present application; Figure 5A structural schematic diagram of an energy storage scheduling device of an energy storage power station is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below with reference to the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0021] In the following description, the terms “some embodiments”, “the embodiment”, “the embodiments of the present application” and the like describe a subset of all possible embodiments, but it can be understood that “some embodiments” can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0022] If the application file appears “first / second” similar description, the following description is added, in the following description, the terms “first\second\third” only distinguish similar objects, and do not represent the specific order of the objects. It can be understood that “first\second\third” can be interchanged in a specific order or sequence as allowed, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0023] Based on this, the embodiments of the present application provide an energy storage scheduling method of an energy storage power station, Figure 1 An optional flowchart of an energy storage scheduling method of an energy storage power station is provided for an embodiment of the present application Figure 1 will be described below. Figure 1 The steps shown will be described.

[0024] S101, acquiring a plurality of different types of new energy data.

[0025] In some embodiments of the present application, the plurality of different types of new energy data includes solar new energy data, wind new energy data and water new energy data.

[0026] In some embodiments of the present application, the solar new energy data is new energy data related to photovoltaic power generation. Photovoltaic power generation is a technology that converts solar radiation energy directly into electrical energy through the photovoltaic effect of semiconductor materials, mainly composed of solar panels, controllers and inverters. The energy conversion principle of photovoltaic power generation is that photons hitting semiconductors excite electron flow, realizing direct conversion of light energy to electrical energy, without fuel consumption or pollutant emissions. Factors affecting the efficiency of photovoltaic power generation include light angle, environmental conditions and cleanliness.

[0027] In some embodiments of the present application, the wind energy new energy data is new energy data related to wind power generation. Wind power generation is a technology that uses wind power to drive turbine blades to rotate, and converts mechanical energy into electrical energy through a transmission system. The main types of wind power generators include doubly-fed asynchronous wind power generators, direct-drive permanent magnet synchronous generators and semi-direct-drive synchronous generators, which are suitable for different wind speed environments and grid requirements. Key components of mainstream models include blades and transmission systems. The material of the blades is mostly composite material (such as glass fiber reinforced resin).

[0028] In some embodiments of the present application, the water energy new energy data is new energy data related to water power generation. Water power generation mainly uses the potential energy (water head) of water bodies to drive water turbines to rotate, converting mechanical energy into electrical energy. Water flows through the water diversion system to impact the water turbine blades, driving the generator rotor to cut the magnetic lines to generate current, achieving energy conversion.

[0029] In some embodiments of the present application, the energy storage scheduling method of the energy storage power station is applied to energy storage scheduling scenarios of multiple different types of new energy data.

[0030] In some embodiments of the present application, the energy storage scheduling method of the energy storage power station is applicable to the energy storage scheduling system of the energy storage power station.

[0031] In some embodiments of the present application, the solar new energy data, wind energy new energy data and water energy new energy data are obtained.

[0032] It should be noted that the solar new energy data includes multiple groups of solar new energy data, and the multiple groups of solar new energy data are numbered; the wind energy new energy data includes multiple groups of wind energy new energy data, and the multiple groups of wind energy new energy data are numbered; the water energy new energy data includes multiple groups of water energy new energy data, and the multiple groups of water energy new energy data are numbered, and the new energy data with the same number is taken as a group of to-be-predicted data.

[0033] S102, data preprocessing is performed on multiple different types of new energy data to obtain target new energy data corresponding to each type of new energy data.

[0034] In some embodiments of the present application, data cleaning is a process of identifying, correcting and deleting errors, missing data, duplicates or inconsistent content in various types of new energy data, aiming to improve data quality and consistency and provide a reliable basis for subsequent analysis.

[0035] In some embodiments of the present application, data cleaning is performed on various types of new energy data respectively to remove missing data, error data, duplicate data and format conflict data in the new energy data, and obtain initial new energy data corresponding to each type of new energy data. Data format uniform processing is performed on the initial new energy data corresponding to each type of new energy data respectively to determine target new energy data corresponding to each type of new energy data; wherein each set of target new energy data includes a set of prediction markers, which are used to represent the number of iterations in the prediction process.

[0036] For example, data identification is performed on each type of new energy data in various types of new energy data to determine missing data, error data, duplicate data and format conflict data; and the missing data, error data, duplicate data and format conflict data in the new energy data are removed to obtain initial new energy data corresponding to each type of new energy data. The data formats of the initial new energy data corresponding to each type of new energy data are not the same, and the data formats of the initial new energy data of various types are uniformly processed to obtain target new energy data corresponding to each type of new energy data.

[0037] S103, predicting the target new energy data by using a predetermined energy prediction model to determine an energy prediction result.

[0038] In some embodiments of the present application, the energy prediction model includes a plurality of sub-prediction models; the various types of new energy data include solar energy data, wind energy data and water energy data; the number of the plurality of sub-prediction models is consistent with the number of types of the various new energy data, and the plurality of sub-prediction models have a one-to-one correspondence with the various new energy data.

[0039] In some embodiments of the present application, the first prediction result is obtained by predicting the target new energy data corresponding to the solar new energy data through a first sub-prediction model corresponding to the solar new energy data in the plurality of sub-prediction models; the first prediction result includes a first array, and the first array is composed of the serial number of each group of solar new energy data and the iteration number of the prediction mark in the first sub-prediction model in each group of solar new energy data. The second prediction result is obtained by predicting the target new energy data corresponding to the wind energy data through a second sub-prediction model corresponding to the wind energy data in the plurality of sub-prediction models; the second prediction result includes a second array, and the second array is composed of the serial number of each group of wind energy data and the iteration number of the prediction mark in the second sub-prediction model in each group of wind energy data. The third prediction result is obtained by predicting the target new energy data corresponding to the water energy data through a third sub-prediction model corresponding to the water energy data in the plurality of sub-prediction models; the third prediction result includes a third array, and the third array is composed of the serial number of each group of water energy data and the iteration number of the prediction mark in the third sub-prediction model in each group of water energy data. The energy prediction result is obtained by performing prediction fusion based on the first prediction result, the second prediction result and the third prediction result.

[0040] It should be noted that the energy prediction result includes the prediction results of a plurality of groups of new energy data.

[0041] In some embodiments of the present application, the energy prediction result is analyzed to determine energy trend information corresponding to each of a plurality of different types; the energy storage scheduling sequence is generated based on the energy trend information corresponding to each of the plurality of different types and the pre-acquired future meteorological data; and the energy storage scheduling sequence includes an input scheduling sequence and an output scheduling sequence.

[0042] In some embodiments of the present application, the energy prediction result is analyzed to determine energy trend information corresponding to each of a plurality of different types; the energy storage scheduling sequence is generated based on the energy trend information corresponding to each of the plurality of different types and the pre-acquired future meteorological data; and the energy storage scheduling sequence includes an input scheduling sequence and an output scheduling sequence.

[0043] In some embodiments of the present application, the output scheduling sequence is generated according to a preset number of time nodes corresponding to points with a larger sum of iteration numbers in the fourth array according to a preset switching frequency; and the input scheduling sequence is generated by selecting a main energy type as the new energy data type corresponding to the maximum iteration number in the corresponding first array, second array and third array at each time node.

[0044] It should be noted that the preset number is set according to specific conditions.

[0045] It can be understood that the data preprocessing can reduce the amount of data transmission, thereby improving the transmission efficiency; the target new energy data is predicted through the predetermined energy prediction model, and an energy prediction result is determined; since the target new energy data of multiple different types is predicted, the future resource trend of each type of new energy data can be understood, and a storage scheduling sequence is generated according to the future resource trend of each type of new energy data to control the switching of the corresponding access terminal and output terminal in the storage power station through the storage scheduling sequence, so that the optimization of different energies can be realized, thereby avoiding problems such as voltage fluctuation and frequency instability of the power grid caused by weather changes, and improving the stability of the power grid voltage.

[0046] In some embodiments of the present application, as shown in Figure 2 S102 can be implemented through S201 and S202, as follows: S201, data cleaning is performed on multiple different types of new energy data respectively, and missing data, error data, duplicate data and format conflict data in the new energy data are removed to obtain initial new energy data corresponding to each of the multiple different types.

[0047] S202, data format uniform processing is performed on the initial new energy data corresponding to each of the multiple different types respectively, and target new energy data corresponding to each of the multiple different types is determined; each group of target new energy data includes a group of prediction marks, and the prediction marks are used to represent the iteration number of the corresponding data in the prediction process.

[0048] In some embodiments of the present application, each group of target new energy data exists in the form of a data sequence, and a key data point in the data sequence is marked to obtain a group of prediction marks of each group of target new energy data. The prediction marks can be used to record the iteration number of the key data point in the subsequent prediction process.

[0049] It should be noted that the key data point is the data corresponding to the time point with high confidence selected in the historical prediction iteration.

[0050] It can be understood that removing missing data, error data, duplicate data and format conflict data in the new energy data can reduce the amount of data transmission, thereby improving the transmission efficiency; the initial new energy data of multiple different data formats is subjected to data format uniform processing to obtain target new energy data of a unified data format, which can facilitate subsequent data transmission. Each group of target new energy data includes a group of prediction marks, and since the prediction marks are used to represent the iteration number of the corresponding data in the prediction process, the main energy type can be determined according to the iteration number of the prediction marks in the subsequent process.

[0051] In some embodiments of the present application, as shown in Figure 3As shown, S103 can be implemented by S301, S302, S303, and S304, as follows: S301, by a first sub-prediction model corresponding to the solar new energy data in the plurality of sub-prediction models, predicting the target new energy data corresponding to the solar new energy data to obtain a first prediction result; wherein the first prediction result includes a first array, and the first array is composed of the serial number of each group of solar new energy data and the iteration number of the prediction marker in the first sub-prediction model in each group of solar new energy data.

[0052] In some embodiments of the present application, the weather information of the future preset time period is obtained, the target new energy data corresponding to the wind energy data is predicted by the second sub-prediction model corresponding to the wind energy data in the plurality of sub-prediction models and the weather information of the future preset time period, and the wind energy trend data curve of the future preset time period is generated; based on the wind energy trend data curve and the prediction marker of the wind energy, the second prediction result containing the second array is determined.

[0053] For example, the future preset time period is 24 hours, and the first prediction result includes the serial number of each group of solar new energy data within 24 hours and the iteration number of the prediction marker in the first sub-prediction model in each group of solar new energy data. Taking a group of solar new energy data as an example, for example, the prediction marker of the solar new energy data with the serial number 1 for 1 hour is 5, the prediction marker of the solar new energy data with the serial number 1 for 2 hours is 10, and the prediction marker of the solar new energy data with the serial number 1 for 3 hours is 3.

[0054] S302, by a second sub-prediction model corresponding to the wind energy data in the plurality of sub-prediction models, predicting the target new energy data corresponding to the wind energy data to obtain a second prediction result; wherein the second prediction result includes a second array, and the second array is composed of the serial number of each group of wind energy data and the iteration number of the prediction marker in the second sub-prediction model in each group of wind energy data.

[0055] In some embodiments of the present application, the weather information of the future preset time period is obtained, the target new energy data corresponding to the wind energy data is predicted by the second sub-prediction model corresponding to the wind energy data in the plurality of sub-prediction models and the weather information of the future preset time period, and the wind energy trend data curve of the future preset time period is generated; based on the wind energy trend data curve and the prediction marker of the wind energy, the second prediction result containing the second array is determined.

[0056] For example, the future preset time period is 24 hours, and the second prediction result includes the iteration number of each group of wind energy new energy data sequence number and the corresponding prediction mark in each group of wind energy new energy data in the second sub-prediction model within 24 hours. Taking one group of wind energy new energy data as an example, for example, the prediction mark of the wind energy new energy data of the first hour sequence number 1 is 3, the prediction mark of the wind energy new energy data of the second hour sequence number 1 is 5, and the prediction mark of the wind energy new energy data of the third hour sequence number 1 is 12.

[0057] S303, by the third sub-prediction model corresponding to the water energy new energy data in the plurality of sub-prediction models, the target new energy data corresponding to the water energy new energy data is predicted to obtain a third prediction result; wherein the third prediction result includes a third array, and the third array is composed of each group of water energy new energy data sequence number and the corresponding iteration number of the prediction mark in each group of water energy new energy data in the third sub-prediction model.

[0058] In some embodiments of the present application, the weather information of the future preset time period is obtained, the target new energy data corresponding to the water energy new energy data is predicted by the third sub-prediction model corresponding to the water energy new energy data in the plurality of sub-prediction models and the weather information of the future preset time period, and the water energy new energy trend data curve of the future preset time period is generated; based on the water energy new energy trend data curve and the prediction mark of the water energy new energy, a third prediction result containing a third array is determined.

[0059] For example, the future preset time period is 24 hours, and the third prediction result includes the iteration number of each group of water energy new energy data sequence number and the corresponding prediction mark in each group of water energy new energy data in the third sub-prediction model within 24 hours. Taking one group of water energy new energy data as an example, for example, the prediction mark of the water energy new energy data of the first hour sequence number 1 is 7, the prediction mark of the water energy new energy data of the second hour sequence number 1 is 2, and the prediction mark of the water energy new energy data of the third hour sequence number 1 is 8.

[0060] S304, based on the first prediction result, the second prediction result and the third prediction result, the prediction fusion is carried out to obtain an energy prediction result.

[0061] In some embodiments of the present application, the energy prediction result includes a fourth array, and the fourth array is composed of each group of new energy data sequence number and the sum of the corresponding iteration number in the first array, the second array and the third array.

[0062] It should be noted that the fourth array includes the sequence numbers of multiple groups of new energy data.

[0063] In some embodiments of the present application, geographical location information and climate information corresponding to the solar new energy data, the wind new energy data and the water new energy data are obtained; for any one of the solar new energy data, the wind new energy data and the water new energy data, spatial features are determined based on the geographical location information and the climate information; and the geographical climate weight is determined according to the spatial features; and the first prediction result, the second prediction result and the third prediction result are fused based on the geographical climate weight corresponding to the solar new energy data, the wind new energy data and the water new energy data to obtain the energy prediction result.

[0064] In some embodiments of the present application, the geographical location information and the climate information corresponding to the solar new energy data are generally regions with long sunshine time and high climate temperature; the geographical location information and the climate information corresponding to the wind new energy data are generally open and windy regions; and the geographical location information and the climate information corresponding to the water new energy data are regions with rich water resources and high terrain. Since each kind of new energy is affected by natural climate, the spatial features are determined by extracting features according to the geographical location information and the climate information of the current various new energy data; and the geographical climate weight is determined according to the spatial features. The first prediction result of the solar new energy data, the second prediction result of the wind new energy data and the third prediction result of the water new energy data are obtained by predicting the various new energy data based on the geographical location information and the climate information. The first prediction result, the second prediction result and the third prediction result can respectively indicate the future resource situation of the current new energy. The first prediction result, the second prediction result and the third prediction result are fused based on the geographical climate weight corresponding to the solar new energy data, the wind new energy data and the water new energy data to obtain the energy prediction result.

[0065] It should be noted that the energy prediction result can represent the trend of the various new energy data at the future moment and the overall trend of all the new energy data.

[0066] For example, the prediction mark of the solar new energy data of 1 hour and sequence number 1 is 5, the prediction mark of the solar new energy data of 2 hours and sequence number 1 is 10, and the prediction mark of the solar new energy data of 3 hours and sequence number 1 is 3. The prediction mark of the wind new energy data of 1 hour and sequence number 1 is 3, the prediction mark of the wind new energy data of 2 hours and sequence number 1 is 5, and the prediction mark of the wind new energy data of 3 hours and sequence number 1 is 12. The prediction mark of the water new energy data of 1 hour and sequence number 1 is 7, the prediction mark of the water new energy data of 2 hours and sequence number 1 is 2, and the prediction mark of the water new energy data of 3 hours and sequence number 1 is 8. The energy prediction result of the fourth array includes: the sum of the iteration times of the new energy of 1 hour and sequence number 1 is 15, the sum of the iteration times of the new energy of 2 hours and sequence number 1 is 17, and the sum of the iteration times of the new energy of 3 hours and sequence number 1 is 23.

[0067] It can be understood that the energy prediction result is determined by predicting the respective new energy data through the sub-prediction model corresponding to the different types of new energy data and weighting through the geographical and climate weight corresponding to the different types of new energy data, which can improve the accuracy of energy prediction.

[0068] In some embodiments of the present application, the output scheduling sequence is generated according to the time nodes corresponding to the preset number of points with larger sum of iteration times in the fourth array according to the preset switching frequency; and the new energy data type corresponding to the maximum iteration value in the corresponding first array, second array and third array at each time node is selected as the main energy type to generate the input scheduling sequence.

[0069] For example, the preset switching frequency can be set to switch once every 1 hour, once every 12 hours, and once every 24 hours, which can be determined according to the change of the environment and climate. The output scheduling sequence is generated according to the time nodes corresponding to the preset number of points with larger sum of iteration times in the fourth array, and the preset number of points can be selected as 3. For example, the energy prediction result of the fourth array is taken as an example: the selected 3 points are 1 hour, 2 hours and 3 hours. The maximum iteration time of the new energy of 1 hour and sequence number 1 is the water new energy data, and the water new energy data of 1 hour and sequence number 1 is taken as the main energy type to generate the input scheduling sequence. The maximum iteration time of the new energy of 2 hours and sequence number 1 is the solar new energy data, and the solar new energy data of 2 hours and sequence number 1 is taken as the main energy type to generate the input scheduling sequence. The maximum iteration time of the new energy of 3 hours and sequence number 1 is the wind new energy data, and the wind new energy data of 1 hour and sequence number 1 is taken as the main energy type to generate the input scheduling sequence.

[0070] In some embodiments of the present application, before S103 is performed, S105-S109 are further performed, as follows: S105, acquiring a plurality of different types of new energy historical data, historical geographic location information and historical climate information; wherein the new energy historical data includes new energy training data and new energy test data.

[0071] S106, determining the initial geographic climate weight corresponding to each of the plurality of different types of new energy historical data through the historical geographic location information and the historical climate information.

[0072] S107, training the initial sub-energy prediction model corresponding to the plurality of different types of new energy historical data through the plurality of different types of new energy training data and the initial geographic climate weight, to determine the trained initial sub-energy prediction model.

[0073] S108, testing the trained initial sub-energy prediction model through the new energy test data, and adjusting the initial geographic climate weight according to the test result to determine the historical geographic climate weight.

[0074] S109, continuously training the trained initial sub-energy prediction model based on the historical geographic climate weight and the plurality of different types of new energy training data until the model accuracy reaches the preset condition to determine the energy prediction model.

[0075] For example, the plurality of different types of new energy historical data, historical geographic location information and historical climate information are acquired, the initial geographic climate weight corresponding to each of the plurality of different types of new energy historical data is determined through the historical geographic location information and the historical climate information, the initial geographic climate weight is adjusted during the training of the initial sub-energy prediction model to determine the historical geographic climate weight. The trained initial sub-energy prediction model is continuously trained through the historical geographic climate weight and the plurality of different types of new energy training data until the model accuracy reaches the preset condition to determine the energy prediction model.

[0076] It can be understood that during the training of the initial sub-energy prediction model, the initial geographic climate weight can be adjusted based on the historical geographic location information and the historical climate information corresponding to the different types of new energy historical data to determine the historical geographic climate weight. The historical geographic climate weight of each type can be determined, and the initial sub-energy prediction model is continuously trained through the historical geographic climate weight and the plurality of different types of new energy training data until the model accuracy reaches the preset condition to determine the energy prediction model, which can improve the accuracy of the energy prediction model.

[0077] In some embodiments of this application, the target new energy data is compressed to obtain compressed data; the compressed data is then encoded to obtain a hybrid feature vector; based on a unified standardized protocol and dual channels, the hybrid feature vector is sent to the energy storage power station; wherein, the dual channels include an optical fiber channel and a 5G channel; if the time for the energy storage power station to receive the hybrid feature vector is longer than a preset time or if the hybrid feature vector is not received, the hybrid feature vector is re-uploaded until the time for the energy storage power station to receive the hybrid feature vector is less than or equal to the preset time.

[0078] For example, the target new energy data is compressed to obtain compressed data; the compressed data is then encoded to obtain a hybrid feature vector. Based on a unified standardized protocol, the hybrid feature vector is sent to the energy storage power station through at least one channel, either a fiber optic channel or a 5G channel. The preset time can be 1 hour. If the energy storage power station receives the hybrid feature vector within 1 hour, the data transmission is considered successful. If the transmission time exceeds 1 hour, the data transmission is considered unsuccessful and needs to be re-uploaded.

[0079] Understandably, using both fiber optic and 5G channels for data transmission allows for the use of the alternative channel when one fails, improving data transmission success rates. Furthermore, initiating a retransmission mechanism if a mixed feature vector is not received within a preset timeframe benefits data reception at energy storage power stations.

[0080] Based on the energy storage dispatching method for energy storage power stations described in the above embodiments, this application also provides an energy storage dispatching system for energy storage power stations, such as... Figure 4 As shown, Figure 4 This is a schematic diagram of the structure of an energy storage power station energy storage dispatching system provided in an embodiment of this application. The energy storage power station energy storage dispatching system 4 includes: an acquisition module 401, a preprocessing module 402, a determination module 403, and a dispatching module 404, wherein... The acquisition module 401 is used to acquire various types of new energy data; The preprocessing module 402 is used to preprocess the various types of new energy data to obtain target new energy data corresponding to each of the various types. The determining module 403 is used to predict the target new energy data using a pre-determined energy prediction model and determine the energy prediction result. The scheduling module 404 is used to generate an energy storage scheduling sequence based on the energy forecast results, so as to control the switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence, wherein the energy storage scheduling sequence includes an input scheduling sequence and an output scheduling sequence.

[0081] In some embodiments of the present application, the preprocessing module 402 is further configured to perform data cleaning on the plurality of different types of new energy data respectively, remove missing data, error data, duplicate data and format conflict data in the new energy data, and obtain initial new energy data corresponding to each of the plurality of different types of new energy data respectively; perform data format unification processing on the initial new energy data corresponding to each of the plurality of different types of new energy data respectively, and determine target new energy data corresponding to each of the plurality of different types of new energy data respectively; wherein each set of target new energy data includes a set of prediction markers, and the prediction markers are used to represent the number of iterations of the corresponding data in the prediction process.

[0082] In some embodiments of the present application, the energy prediction model includes a plurality of sub-prediction models; the plurality of different types of new energy data includes solar energy new energy data, wind energy new energy data and water energy new energy data; the number of the plurality of sub-prediction models is consistent with the number of types of the plurality of new energy data, and the plurality of sub-prediction models have a one-to-one correspondence with the plurality of new energy data. The determining module 403 is further configured to perform prediction on the target new energy data of the solar energy new energy data by a first sub-prediction model corresponding to the solar energy new energy data in the plurality of sub-prediction models, and obtain a first prediction result; wherein the first prediction result includes a first array, and the first array is composed of the serial number of each set of solar energy new energy data and the number of iterations of the prediction markers in each set of solar energy new energy data in the first sub-prediction model; perform prediction on the target new energy data of the wind energy new energy data by a second sub-prediction model corresponding to the wind energy new energy data in the plurality of sub-prediction models, and obtain a second prediction result; wherein the second prediction result includes a second array, and the second array is composed of the serial number of each set of wind energy new energy data and the number of iterations of the prediction markers in each set of wind energy new energy data in the second sub-prediction model; perform prediction on the target new energy data of the water energy new energy data by a third sub-prediction model corresponding to the water energy new energy data in the plurality of sub-prediction models, and obtain a third prediction result; wherein the third prediction result includes a third array, and the third array is composed of the serial number of each set of water energy new energy data and the number of iterations of the prediction markers in each set of water energy new energy data in the third sub-prediction model; and perform prediction fusion based on the first prediction result, the second prediction result and the third prediction result, and obtain the energy prediction result.

[0083] In some embodiments of the present application, the determining module 403 is further configured to: obtain geographical location information and climate information corresponding to the solar new energy data, the wind new energy data, and the water new energy data; perform feature extraction based on the geographical location information and the climate information for any one of the solar new energy data, the wind new energy data, and the water new energy data, to determine a spatial feature; determine a geographical climate weight according to the spatial feature; perform prediction fusion on the first prediction result, the second prediction result, and the third prediction result based on the geographical climate weight corresponding to each of the solar new energy data, the wind new energy data, and the water new energy data, to obtain the energy prediction result; and the energy prediction result includes a fourth array, which is composed of each set of new energy data serial number and the sum of the corresponding iteration numbers in the first array, the second array, and the third array.

[0084] In some embodiments of the present application, the scheduling module 404 is further configured to: generate an output scheduling sequence according to a preset switching frequency from the fourth array, the time nodes corresponding to a preset number of points with larger sum of corresponding iteration numbers; and select the new energy data type corresponding to the maximum value of the corresponding iteration numbers in the first array, the second array, and the third array at each time node as a main energy type to generate an input scheduling sequence.

[0085] In some embodiments of the present application, the obtaining module 401 is configured to: obtain a plurality of different types of new energy historical data, historical geographical location information, and historical climate information before the energy prediction model is determined by predicting the target new energy data; and the new energy historical data includes new energy training data and new energy test data. The determining module 403 is further configured to: determine an initial geographical climate weight corresponding to each of the plurality of different types of new energy historical data through the historical geographical location information and the historical climate information; train an initial sub-energy prediction model corresponding to the plurality of different types of new energy historical data through the plurality of different types of new energy training data and the initial geographical climate weight, to determine a trained initial sub-energy prediction model; test the trained initial sub-energy prediction model through the new energy test data, and adjust the initial geographical climate weight according to the test result to determine a historical geographical climate weight; and continue to train the trained initial sub-energy prediction model based on the historical geographical climate weight and the plurality of different types of new energy training data until the model accuracy reaches a preset condition, to determine the energy prediction model.

[0086] In some embodiments of the present application, the acquisition module 401 is further configured to perform compression processing on the target new energy data to obtain compressed data, encode the compressed data to obtain a mixed feature vector, and send the mixed feature vector to the energy storage power station based on a unified standardization protocol and a dual channel. The dual channel includes a fiber channel and a 5G channel. If the time for the energy storage power station to receive the mixed feature vector is greater than a preset time or the energy storage power station does not receive the mixed feature vector, the mixed feature vector is re-uploaded until the time for the energy storage power station to receive the mixed feature vector is less than or equal to the preset time.

[0087] Based on the energy storage scheduling method of the energy storage power station in the above embodiments, the embodiments of the present application further provide an energy storage scheduling device of an energy storage power station. Figure 5 As shown in Figure 5 FIG. 5 is a structural schematic diagram of an energy storage scheduling device of an energy storage power station according to an embodiment of the present application. The energy storage scheduling device 5 of the energy storage power station includes a processor 501 and a memory 502. The memory 502 is configured to store a computer program. The processor 501 is configured to call and run the computer program from the memory to perform the energy storage scheduling method of the energy storage power station as described in the above embodiments.

[0088] In the embodiments of the present application, the processor 501 can be at least one of an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller, or a microprocessor. It can be understood that, for different devices, the electronic device used to implement the functions of the processor can also be other devices, and the embodiments of the present application are not limited in this regard.

[0089] The embodiments of the present application provide a computer readable storage medium storing a computer program, which is configured to be executed by a processor to implement the energy storage scheduling method of the energy storage power station according to any one of the above embodiments.

[0090] Exemplarily, the program instruction corresponding to the energy storage station energy storage scheduling method in the embodiment can be stored on a storage medium such as an optical disc, a hard disk, a U disk, and the like. When the program instruction corresponding to the energy storage station energy storage scheduling method in the embodiment is read by an electronic device or executed, the energy storage station energy storage scheduling method described in any one of the above embodiments can be implemented.

[0091] In addition, each functional module in the embodiments of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional module.

[0092] The integrated unit, if realized in the form of a software functional module and not sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments can be embodied in the form of a software product, the computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the embodiments. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0093] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in some embodiments" appearing throughout the specification does not necessarily mean the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the serial number of the above processes does not mean the execution order, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The serial number of the above embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between each embodiment, and the same or similar parts can be referred to each other. For the sake of brevity, this paper will not repeat here.

[0094] The modules described above as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical modules; they can be located in one place or distributed on multiple network units; and part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0095] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each module can be a separate unit, or two or more modules can be integrated in one unit; the integrated module can be realized in the form of hardware or in the form of hardware plus software function unit.

[0096] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the above program can be stored in a computer readable storage medium, and the program executes the steps including the above method embodiments when executed; and the above storage medium includes mobile storage device, read only memory (Read Only Memory, ROM), magnetic disc or optical disc and various storage program codes.

[0097] The methods disclosed in the several method embodiments provided by the embodiments of the present application can be combined arbitrarily without conflict to obtain new method embodiments.

[0098] The features disclosed in the several product embodiments provided by the embodiments of the present application can be combined arbitrarily without conflict to obtain new product embodiments.

[0099] The features disclosed in the several method or device embodiments provided by the embodiments of the present application can be combined arbitrarily without conflict to obtain new method or device embodiments.

[0100] The above is only an implementation manner of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the embodiments of the present application. Therefore, the protection scope of the embodiments of the present application should be subject to the protection scope of the claims.

Claims

1. A method for energy storage dispatching of an energy storage power station, characterized in that, The method includes: Acquire various types of new energy data; Data preprocessing is performed on the various types of new energy data to obtain the target new energy data corresponding to each of the various types. The target new energy data is predicted using a pre-determined energy prediction model to determine the energy prediction results. An energy storage scheduling sequence is generated based on the energy forecast results to control the switching of corresponding access terminals and output terminals in the energy storage power station. The energy storage scheduling sequence includes an input scheduling sequence and an output scheduling sequence.

2. The method according to claim 1, characterized in that, The process of preprocessing the various types of new energy data to obtain target new energy data corresponding to each of the various types includes: Data cleaning is performed on the various types of new energy data to remove missing data, erroneous data, duplicate data, and data with conflicting formats, thereby obtaining the initial new energy data corresponding to each of the various types. The initial new energy data corresponding to the various different types are processed to unify the data format, and the target new energy data corresponding to the various different types are determined. Each set of target new energy data includes a set of prediction tags, which are used to characterize the number of iterations of the corresponding data in the prediction process.

3. The method according to claim 1, characterized in that, The energy prediction model includes multiple sub-prediction models; the various types of new energy data include solar energy data, wind energy data, and hydropower data; the number of the multiple sub-prediction models is consistent with the number of different types of new energy data, and there is a one-to-one correspondence between the multiple sub-prediction models and the various new energy data. The step of predicting the target new energy data using a pre-determined energy prediction model and determining the energy prediction result includes: The first sub-prediction model, which corresponds to the solar energy data among the multiple sub-prediction models, is used to predict the target new energy data corresponding to the solar energy data to obtain a first prediction result. The first prediction result includes a first array, which consists of the sequence number of each group of solar energy data and the iteration number of the prediction marker in the first sub-prediction model for each group of solar energy data. The target new energy data corresponding to the wind energy new energy data is predicted by the second sub-prediction model corresponding to the wind energy new energy data in the plurality of sub-prediction models to obtain a second prediction result; wherein, the second prediction result includes a second array, the second array is composed of the sequence number of each group of wind energy new energy data and the iteration number of the prediction mark in each group of wind energy new energy data in the second sub-prediction model; The target new energy data corresponding to the hydropower new energy data is predicted by the third sub-prediction model corresponding to the hydropower new energy data among the multiple sub-prediction models, and a third prediction result is obtained; wherein, the third prediction result includes a third array, which consists of the sequence number of each group of hydropower new energy data and the number of iterations of the prediction marker in each group of hydropower new energy data in the third sub-prediction model; Based on the first prediction result, the second prediction result, and the third prediction result, prediction fusion is performed to obtain the energy prediction result.

4. The method according to claim 3, characterized in that, The process of fusing predictions based on the first prediction result, the second prediction result, and the third prediction result to obtain the energy prediction result includes: Obtain the geographical location and climate information corresponding to the solar energy data, wind energy data, and hydropower data respectively; For any one of the solar energy data, wind energy data, and hydropower data, feature extraction is performed based on the geographic location information and the climate information to determine spatial features; and geographic climate weights are determined based on the spatial features. Based on the geographical and climatic weights corresponding to the solar energy data, wind energy data, and hydropower data, the first prediction result, the second prediction result, and the third prediction result are fused to obtain the energy prediction result; wherein, the energy prediction result includes a fourth array, which consists of the sequence number of each new energy data group and the sum of the corresponding iteration numbers in the first, second, and third arrays.

5. The method according to claim 1, characterized in that, The step of generating an energy storage dispatch sequence based on the energy forecast results to control the switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage dispatch sequence includes: Based on the preset switching frequency, the output scheduling sequence is generated by selecting the time nodes corresponding to the preset number of points with the larger sum of iteration counts from the fourth array. The new energy data type corresponding to the maximum iteration count in the first, second, and third arrays at each time point is selected as the primary energy type to generate the input scheduling sequence.

6. The method according to claim 1, characterized in that, Before determining the energy prediction result by predicting the target new energy data using a pre-determined energy prediction model, the method further includes: Acquire various types of historical data on new energy sources, historical geographical location information, and historical climate information; wherein, the historical data on new energy sources includes new energy training data and new energy testing data; The initial geographic and climate weights corresponding to the various types of new energy historical data are determined by using the historical geographic location information and the historical climate information. Using the training data of various types of new energy sources and the initial geographical and climate weights, the initial sub-energy prediction model corresponding to the historical data of various types of new energy sources is trained, and the trained initial sub-energy prediction model is determined. The initial sub-energy prediction model after training is tested using the new energy test data, and the initial geographic climate weights are adjusted based on the test results to determine the historical geographic climate weights. Based on the historical geographical and climate weights and the various types of new energy training data, the initial sub-energy prediction model after training is continuously trained until the model accuracy reaches the preset conditions, and the energy prediction model is determined.

7. The method according to claim 1, characterized in that, The method further includes: The target new energy data is compressed to obtain compressed data; and the compressed data is encoded to obtain a hybrid feature vector. Based on a unified standardized protocol and dual channels, the hybrid feature vector is sent to the energy storage power station; wherein, the dual channels include an optical fiber channel and a 5G channel; If the time it takes for the energy storage power station to receive the hybrid feature vector is greater than a preset time or if the hybrid feature vector is not received, the hybrid feature vector is re-uploaded until the time it takes for the energy storage power station to receive the hybrid feature vector is less than or equal to the preset time.

8. An energy storage power station energy storage dispatch system, characterized in that, The energy storage power station energy storage dispatch system includes: an acquisition module, a preprocessing module, a determination module, and a dispatch module; wherein... The acquisition module is used to acquire various types of new energy data; The preprocessing module is used to preprocess the various types of new energy data to obtain the target new energy data corresponding to each of the various types. The determining module is used to predict the target new energy data using a pre-determined energy prediction model and determine the energy prediction result. The scheduling module is used to generate an energy storage scheduling sequence based on the energy forecast results, so as to control the switching of corresponding access terminals and output terminals in the energy storage power station through the energy storage scheduling sequence. The energy storage scheduling sequence includes an input scheduling sequence and an output scheduling sequence.

9. An energy storage dispatching device for an energy storage power station, characterized in that, include: Processor and memory, of which, The memory is used to store computer programs; The processor is configured to call and run the computer program from the memory to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores executable instructions for causing a processor to execute, thereby implementing the method of any one of claims 1 to 7.

Images