Mobile platform short-term photovoltaic power generation power prediction method and device based on weather type division

Abstract

The invention provides a mobile platform short-term photovoltaic power generation power prediction method and device based on weather type division, and the method comprises the steps: collecting photovoltaic data and meteorological data at different moments in a to-be-measured time period based on a built photovoltaic power generation power prediction mobile platform, the meteorological data comprises rainfall data at each moment; correcting the rainfall data at each moment, and updating meteorological data according to the corrected rainfall data at each moment; performing similar day clustering according to the photovoltaic data and the updated meteorological data, and determining a weather type; and according to the weather type, the photovoltaic generation power in the time period is predicted based on a pre-constructed CNN-LSTM combined deep learning model, so that the randomness and volatility of single-machine photovoltaic output can be reduced, and the precision of photovoltaic generation power prediction can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power systems, and in particular to a method and device for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification. Background Art

[0002] At present, my country is vigorously promoting the transformation of its energy system to a cleaner and lower-carbon one. Power generation forecasting is one of the leading basic tasks in promoting the construction of a new power system. Compared with renewable energy sources such as wind energy and hydrogen energy, solar energy has more significant periodicity and predictability characteristics. The research on short-term photovoltaic power generation forecasting technology is of great significance to alleviating power generation pressure, reducing environmental pollution, and ensuring safe dispatch and operation of power grids.

[0003] At present, short-term photovoltaic power generation prediction generally adopts statistical models represented by auto-regressive moving average (ARMA), Markov chain (MC), etc., or deep learning models represented by artificial neural network (ANN), recurrent neural network (RNN), etc., to establish the potential mapping relationship between meteorological parameters and actual power generation. The main meteorological characteristics affecting photovoltaic power generation, such as irradiance, rainfall, ambient temperature, relative humidity and wind speed, are input into the prediction model to obtain the short-term photovoltaic power generation prediction results. The prediction effect is limited by the quantity and quality of data. For example, in practical applications, it is difficult to find effective rules from a small amount of photovoltaic power data due to multiple factors such as equipment failure, noise interference, and sensor failure. The obvious differences in photovoltaic output power caused by different seasons and changes in weather types are not conducive to model learning and prediction.

[0004] Mobile photovoltaic power generation equipment can meet the power generation needs of remote areas and mobile scenarios far away from the power grid, such as islands, deserts, and the wild. However, the data obtained by relying solely on a single device is more random and volatile, which is different from photovoltaic power stations. Among them, small ultrasonic rainfall and light meteorological stations are often used as meteorological data collection devices in mobile devices, while the data obtained by optical rain gauges that monitor rainfall in actual applications is the accumulated value of rainfall, which cannot be directly used as effective data in mobile platform power prediction, which has a greater impact on the prediction accuracy. Summary of the invention

[0005] The present disclosure provides a method and device for predicting short-term photovoltaic power generation of a mobile platform based on weather type classification. According to a first aspect of the present disclosure, a method for predicting short-term photovoltaic power generation of a mobile platform based on weather type classification is provided, the method comprising: Based on the established photovoltaic power generation prediction mobile platform, photovoltaic data and meteorological data at different times during the test period are collected, wherein the meteorological data includes rainfall data at each time; Correcting the rainfall data at each time, and updating the meteorological data according to the corrected rainfall data at each time; Performing clustering of similar days based on the photovoltaic data and the updated meteorological data to determine the weather type; According to the weather type, the photovoltaic power generation power in the time period is predicted based on the pre-built CNN-LSTM combined deep learning model.

[0006] According to the above aspects and any possible implementation, a further implementation is provided, which corrects the rainfall data at each moment, including: According to the rainfall data at each moment, the rainfall collected at each moment is compared with the rainfall collected at the corresponding previous moment; If the difference between the rainfall collected at the current moment and the rainfall collected at the corresponding previous moment is 0, it means that the instantaneous rainfall at the current moment is 0; If the difference between the rainfall collected at the current moment and the rainfall collected at the corresponding previous moment is not 0, the difference is taken as the instantaneous rainfall at the current moment.

[0007] According to the above aspects and any possible implementation, an implementation is further provided, performing similar day clustering according to the photovoltaic data and the updated meteorological data to determine the weather type, including: Preprocessing the photovoltaic data and the updated meteorological data, performing feature extraction, and determining a feature sequence; The feature sequence is input into a fuzzy C-means clustering algorithm to identify weather types, wherein the weather types include sunny, cloudy and rainy days.

[0008] According to the above aspects and any possible implementation, a further implementation is provided, wherein the feature sequence is input into a fuzzy C-means clustering algorithm, and after the weather type is identified, the method further includes: If the weather type is a rainy day, the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, or the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the rainfall data at each moment.

[0009] According to the above aspects and any possible implementation, an implementation is further provided, wherein the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, including: The corrected rainfall data at each moment is used as the instantaneous rainfall at each moment; Determine the total rainfall in the time period to be measured according to the instantaneous rainfall at each moment; According to the total rainfall in the time period to be measured, rainy days are divided into light rain, moderate rain, heavy rain and rainstorm.

[0010] According to the above aspects and any possible implementation, an implementation is further provided, wherein the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the rainfall data at each moment, including: According to the rainfall data at each moment in the time period to be measured, the rainfall data collected at the last collection moment and the rainfall data collected at the first collection moment in the time period to be measured are obtained; Determine the total rainfall in the time period to be measured according to the difference between the rainfall data collected at the last collection moment and the rainfall data collected at the first collection moment; According to the total rainfall in the time period to be measured, rainy days are divided into light rain, moderate rain, heavy rain and rainstorm.

[0011] According to the above aspects and any possible implementation, an implementation is further provided, wherein the rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the total rainfall in the time period to be measured, including: If the total rainfall in the time period to be tested is less than the first critical value, the rainy day is light rain; If the total rainfall in the time period to be measured is between the first critical value and the second critical value, the rainy day is moderate rain; If the total rainfall in the time period to be measured is between the second critical value and the third critical value, the rainy day is heavy rain; If the total rainfall in the measured time period is greater than the third critical value, the rainy day is a rainstorm.

[0012] According to a second aspect of the present disclosure, a device for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification is provided, the device comprising: A data acquisition module is used to collect photovoltaic data and meteorological data at different times within the test period based on the established photovoltaic power generation prediction mobile platform, wherein the meteorological data includes rainfall; A rainfall correction module, used to correct the rainfall data at each moment, and update the meteorological data according to the corrected rainfall data at each moment; A weather type classification module, used to cluster similar days according to the photovoltaic data and the updated meteorological data to determine the weather type; The photovoltaic power generation prediction module is used to predict the photovoltaic power generation within the time period based on the weather type and the pre-built CNN-LSTM combined deep learning model.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, comprising a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it retrieves a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the short-term photovoltaic power prediction method for a mobile platform based on weather type classification as described above.

[0014] According to a fourth aspect of the present disclosure, a storage medium is provided, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification as described above is implemented.

[0015] Compared with the prior art, the present invention achieves the following beneficial effects: (1) Based on the mobile platform and remote monitoring through the cloud platform, the data type and time interval can be selected as needed to facilitate the acquisition of sufficient and effective photovoltaic and meteorological data, providing a basis for subsequent photovoltaic power generation prediction.

[0016] (2) The accumulated rainfall data collected at different times are corrected, and then the corrected rainfall data is combined with other meteorological factors closely related to photovoltaic power generation to reduce the randomness and volatility of single-machine photovoltaic output. This is suitable for various future processing situations of photovoltaic power generation, provides more sufficient and reliable information for power system operation and dispatch, and improves the accuracy of photovoltaic power generation prediction.

[0017] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which: Figure 1 A flowchart of a method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification according to an embodiment of the present disclosure is shown; Figure 2 A technical schematic diagram of a method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification according to an embodiment of the present disclosure is shown; Figure 3 A schematic diagram of mobile platform connection according to an embodiment of the present disclosure is shown; Figure 4 A rainfall processing flow chart according to an embodiment of the present disclosure is shown; Figure 5 A diagram showing prediction results of different rainfall processing situations according to an embodiment of the present disclosure is shown; Figure 6 A block diagram of a mobile platform short-term photovoltaic power generation prediction device based on weather type classification according to an embodiment of the present disclosure is shown; Figure 7 A schematic diagram of a computing device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0020] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0021] The present disclosure proposes a method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification, the method comprising: based on a constructed photovoltaic power generation prediction mobile platform, collecting photovoltaic data and meteorological data at different times within a time period to be tested, wherein the meteorological data includes rainfall data at each time; then correcting the rainfall data at each time, and updating the meteorological data according to the corrected rainfall data at each time; and clustering similar days according to the photovoltaic data and the updated meteorological data to determine the weather type; finally, according to the weather type, predicting the photovoltaic power generation within the time period based on a pre-built CNN-LSTM combined deep learning model, in this way, the randomness and volatility of the photovoltaic output of a single machine can be reduced, and the accuracy of photovoltaic power generation prediction can be improved.

[0022] In conjunction with the accompanying drawings, a specific embodiment of a method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification provided by the present disclosure is described below.

[0023] Figure 1FIG. 1 is a flow chart of a method 100 for predicting short-term photovoltaic power generation of a mobile platform based on weather type classification according to an embodiment of the present disclosure. Figure 1 As shown, the method 100 includes: S110, based on the established photovoltaic power generation prediction mobile platform, collecting photovoltaic data and meteorological data at different times within the test time period, wherein the meteorological data includes rainfall data at each time. In some embodiments, the photovoltaic power generation prediction mobile platform mainly includes: Battery: 12V ternary power lithium battery, standard capacity is 30AH, used to store electric energy to achieve continuous and uninterrupted operation of the system; Solar Panels: Photovoltaic panels are tilted and fixed on the equipment control box with free-moving tires to convert solar energy into electrical energy; Maximum power point tracking (MPPT): real-time detection of the power generation voltage of the solar panel to ensure that the system operates at the maximum power point, coordinate the work of the solar panel, battery, and load, and improve the efficiency and performance of each component; Data transfer unit (DTU): transmits data from field devices to cloud servers with high reliability and stability, enabling remote control and device management; Meteorological data acquisition device: It integrates wind speed, wind direction, temperature and humidity, light and rainfall monitoring. The device adopts standard ModBus-RTU communication protocol and RS485 signal output. The data can be uploaded to the monitoring software through 485 communication.

[0024] The mobile platform can be constructed by combining the above components and devices according to the electrical and signal connection requirements. When there is sufficient sunlight, the MPPT controller detects the power generation voltage of the solar panel in real time and tracks the highest voltage and current value, so that the solar panel can supply power to subsequent devices at the maximum power while charging the battery, effectively storing the output power of the solar panel in the battery, ensuring that the mobile platform can work normally even in scenes with no light or insufficient light.

[0025] The connection principle is as follows Figure 3 shown.

[0026] The positive and negative poles of the solar panel are connected to the positive and negative poles indicated by the MPPT controller, and the battery is connected in the same way. Since it is hoped to collect photovoltaic data and meteorological data at the same time, the positive and negative interfaces of the load need to be expanded, and then the DTU module and the meteorological data collection device are connected respectively. After the meteorological data collection device is connected, it is fixed above the equipment control box.

[0027] The antenna is connected to the top of the DTU for sending and receiving wireless signals. The positive and negative voltage interfaces at the bottom are respectively connected to one pair of positive and negative interfaces of the MPPT controller load to power the DTU module. According to the RS485 pin definition of the MPPT controller, the RS485 serial port of the DTU is connected to the RS485 serial port in the MPPT controller to realize the communication function.

[0028] In some embodiments, the meteorological data that the mobile platform can monitor mainly include wind speed (m / s), wind direction (direction), temperature (°C), humidity value (%RH), atmospheric pressure (kPa), light intensity (LUX) and rainfall (mm), etc. Except for rainfall, other data collected are instantaneous values ​​at the moment, but rainfall (mm) is the accumulated value of rainfall, and photovoltaic data mainly includes photovoltaic power generation, etc.

[0029] S120, correcting the rainfall data at each moment, and updating the meteorological data according to the corrected rainfall data at each moment.

[0030] In some embodiments, since all data except rainfall are collected at instantaneous values, they can effectively reflect the actual situation and can usually be directly fused into a feature sequence. However, rainfall (mm) is the cumulative value of rainfall. Even if there is no rainfall, the measured rainfall is no longer 0. The data reflects the actual situation and cannot be used as a basis for judging whether it has rained. The usual processing method is to directly ignore the rainfall. In actual research, it is found that whether or not it rains has a certain impact on the subsequent classification of different weather types and the prediction of photovoltaic power generation. If it is not specially processed in advance and directly used as a feature input together with other meteorological factors, or the role of rainfall is ignored, it is very likely to weaken the final prediction performance of the model. Therefore, the correction of unreasonable rainfall is very important in the prediction work.

[0031] In order to correct the unreasonable rainfall, the instantaneous rainfall at each moment in the test time period is determined, such as Figure 4 As shown, the present disclosure corrects the rainfall data at each time, including: According to the rainfall data at each moment, the rainfall collected at each moment is compared with the rainfall collected at the corresponding previous moment, that is, the rainfall data at each moment is subtracted from the rainfall data at the corresponding previous moment, which can be expressed as: ; in, represents the rainfall data collected at the kth collection time, represents the rainfall data collected at the k-1th collection time, It represents the rainfall in the time period between the collection time k and the previous collection time k-1, which can be regarded as the instantaneous rainfall at the time k.

[0032] Furthermore, if the difference is 0, it means the instantaneous rainfall at the current moment is 0; if the difference If it is not 0, the difference is taken as the instantaneous rainfall at the current moment. The rainfall data correction process at other moments is the same as the rainfall data correction process at the above moment k, and will not be described in detail.

[0033] S130, performing similar day clustering according to the photovoltaic data and the updated meteorological data to determine the weather type.

[0034] In some embodiments, Figure 2 As shown, the meteorological data can be updated according to the corrected rainfall data, and the updated meteorological data and the acquired photovoltaic data can be used as input together, which can play a role in rainy days when the photovoltaic power generation power is highly correlated with rainfall, and can better complete the prediction work. Specifically, First, the photovoltaic data and updated meteorological data can be preprocessed, including cleaning data (removing outliers, processing missing values, and checking data consistency), formatting data (converting all data into a unified format and normalizing them), and integrating data (merging photovoltaic data with the corresponding updated meteorological data).

[0035] Secondly, feature extraction is performed on the preprocessed photovoltaic data and updated meteorological data to construct feature sequences.

[0036] Finally, the feature sequence is input into the fuzzy C-means clustering algorithm to identify the weather type by analyzing the features of the cluster centers, wherein the weather type includes sunny, cloudy and rainy days.

[0037] This paper adopts the Fuzzy C-Means (FCM) clustering algorithm for weather type identification because the algorithm has some unique advantages compared with other clustering methods. It is not only more robust to outliers and noise, but also has a certain degree of membership even if the data point is far away from the center of a cluster, which helps to reduce the impact of outliers. In addition, the basic principle of the FCM algorithm is relatively simple and easy to understand.

[0038] In some embodiments, due to the large differences in photovoltaic output in different types of rainfall weather, in order to study the characteristics of photovoltaic power generation under different rainfall scenarios, a qualitative analysis of photovoltaic power generation under different types of rainfall is conducted. It can be observed that under different rainfall conditions, the change trend of photovoltaic power generation is not exactly the same. The amount of rainfall affects the performance of photovoltaic modules in absorbing solar radiation, and thus affects the size of photovoltaic power generation. Therefore, the prediction results of photovoltaic power generation under rainy weather cannot be directly and simply determined, and further special analysis of specific rainfall types is required. If you want to obtain more accurate prediction results, the rainfall weather is further divided into light rain, moderate rain, heavy rain and rainstorm according to the provided rainfall processing method, and the four situations are predicted separately in combination with the characteristics of photovoltaic power generation for each weather type to improve the prediction accuracy of each rainfall situation.

[0039] The method of dividing the rainy day into light rain, moderate rain, heavy rain and rainstorm mainly includes: The rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, or the rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the rainfall data at each moment, and the calculation results of the two are completely consistent.

[0040] Specifically, the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, including: First, the corrected rainfall data at each moment is used as the instantaneous rainfall at each moment; Secondly, according to the instantaneous rainfall at each moment, the total rainfall in the time period to be measured is determined. For example, according to the corrected rainfall data collected at 96 moments (collected every 15 minutes) in the time period to be measured (within one day), the total rainfall in one day can be expressed as: ; in, It means the first The instantaneous rainfall at the time of collection.

[0041] Finally, rainy days are divided into light rain, moderate rain, heavy rain and torrential rain according to the total rainfall in the measured time period.

[0042] Alternatively, the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the obtained rainfall data at each moment (i.e., accumulated rainfall data), including: According to the rainfall data collected at each time, the rainfall data collected at the last collection time and the rainfall data collected at the first collection time in the test time period are obtained; The total rainfall in the time period to be measured is determined based on the difference between the rainfall data collected at the last collection moment and the rainfall data collected at the first collection moment. For example, 96 moments (collected every 15 minutes) are collected in the time period to be measured (within one day). The rainfall data at the first collection moment and the rainfall data at the 96th collection moment are obtained respectively, and the difference between the two is used to determine the total rainfall in one day, that is:

[0043] in, is the rainfall data at the 96th collection moment, It is the rainfall data at the first collection moment.

[0044] Finally, rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the total rainfall in the time period to be measured.

[0045] In some embodiments, as shown in Table 1 of the meteorological rainfall level classification table, rainy days are classified into light rain, moderate rain, heavy rain and rainstorm according to the total rainfall in the time period to be measured, including: If the total rainfall in the time period to be tested is less than the first critical value , then the rainy day is light rain; If the total rainfall in the time period to be tested is within the first critical value and the second critical value If the rainy day is between , the rainy day is moderate rain; If the total rainfall during the test period is within the second critical value and the third critical value If the rainy day is between , the rainy day is heavy rain; If the total rainfall in the test period is greater than the third critical value , then the rainy day is a rainstorm.

[0046] Table 1

[0047] In the actual classification of rainfall weather, the values ​​of each critical point can refer to the following actual critical point value table 2.

[0048] Table 2

[0049] S140, predicting the photovoltaic power generation in the time period based on the pre-built CNN-LSTM combined deep learning model according to the weather type. In some embodiments, in order to achieve accurate prediction, the present disclosure adopts a combined model of a convolutional neural network (CNN) and a long short-term memory network (LSTM) (CNN-LSTM). The combined model CNN-LSTM combines the powerful ability of CNN in spatial feature extraction and the advantage of LSTM in maintaining long-term dependencies in the network. It can effectively process time series data and extract key features that are helpful in predicting future photovoltaic power generation, which has great advantages for photovoltaic power generation prediction.

[0050] In some embodiments, in order to verify the necessity of rainfall processing in the present disclosure, photovoltaic power generation power is predicted for three cases: rainfall processing, rainfall not processing, and rainfall ignoring. The effectiveness of rainfall processing is verified based on the prediction results. Unprocessed rainfall means directly taking the accumulated rainfall value collected by the mobile platform as one of the meteorological characteristics. Ignoring rainfall means no longer considering rainfall in the meteorological factors affecting photovoltaic power generation. The other conditions of the three cases are exactly the same. Since rainfall has a more obvious effect on photovoltaic power generation power on rainy days, choosing rainy days to complete the prediction work is more conducive to reflecting the changes in the corresponding prediction results when the rainfall input changes. The prediction results are shown in Tables 3 and Figure 5 As shown: Table 3

[0051] The prediction effect is evaluated by the root mean square error RMSE and the mean absolute error MAE. The closer the index is to 0, the more consistent the change curve of the predicted power is with the actual power. From the prediction error and the prediction curve, it can be seen that the prediction accuracy of rainfall after being processed by a specific method is the highest. First, the instantaneous value obtained after processing can more effectively reflect the actual situation than the accumulated value. Second, according to the correlation judgment, it can be seen that the introduction of rainfall enriches the meteorological input characteristics. The experimental results verify the necessity of performing rainfall processing and finely dividing weather types in this disclosure.

[0052] According to the embodiments of the present disclosure, the following technical effects are achieved: (1) Based on the mobile platform and remote monitoring through the cloud platform, the data type and time interval can be selected as needed to facilitate the acquisition of sufficient and effective photovoltaic and meteorological data, providing a basis for subsequent photovoltaic power generation prediction.

[0053] (2) By correcting the accumulated rainfall data collected at different times and combining the corrected rainfall data at each time with other meteorological factors closely related to photovoltaic power generation, the randomness and volatility of the output of a single photovoltaic machine can be reduced, which is suitable for various future processing situations of photovoltaic power generation, thereby providing more sufficient and reliable information for the operation and dispatch of the power system and improving the accuracy of photovoltaic power generation prediction.

[0054] (3) Compared with fixed facilities, mobile platforms are not restricted by space and can be moved to new areas for continuous use at any time. They have great practical value in remote and desolate areas far away from the power grid.

[0055] (4) It can improve the flexibility of prediction, process and perform predictive analysis on the data collected in real time by the mobile platform, and help users make timely adjustments and decisions when faced with special situations.

[0056] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the described order of actions, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0057] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0058] Figure 6 FIG. 6 is a block diagram of a mobile platform short-term photovoltaic power generation prediction device 600 based on weather type classification according to an embodiment of the present disclosure, as shown in FIG. Figure 6 As shown, the device 600 includes: The data acquisition module 610 is used to collect photovoltaic data and meteorological data at different times in the test time period based on the established photovoltaic power generation prediction mobile platform, wherein the meteorological data includes rainfall; A rainfall correction module 620, used to correct the rainfall data at each moment, and update the meteorological data according to the corrected rainfall data at each moment; A weather type classification module 630 is used to perform similar day clustering based on the photovoltaic data and the updated meteorological data to determine the weather type; The photovoltaic power generation prediction module 640 is used to predict the photovoltaic power generation within the time period based on the weather type and the pre-built CNN-LSTM combined deep learning model.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0060] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0061] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0062] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0063] The electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a ROM 702 or a computer program loaded from a storage unit 708 into a RAM 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An I / O interface 705 is also connected to the bus 704.

[0064] Multiple components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0065] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0066] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0067] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0068] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0069] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0070] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0071] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0072] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0073] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for predicting short-term photovoltaic power generation on a mobile platform based on weather type classification, characterized in that: include: Based on the established photovoltaic power generation prediction mobile platform, photovoltaic data and meteorological data at different times during the test period are collected, wherein the meteorological data includes rainfall data at each time; Correcting the rainfall data at each time, and updating the meteorological data according to the corrected rainfall data at each time; Performing clustering of similar days based on the photovoltaic data and the updated meteorological data to determine the weather type; According to the weather type, the photovoltaic power generation power in the time period is predicted based on the pre-built CNN-LSTM combined deep learning model.

2. The method according to claim 1, characterized in that The rainfall data at each time is corrected, including: According to the rainfall data at each moment, the rainfall collected at each moment is compared with the rainfall collected at the corresponding previous moment; If the difference between the rainfall collected at the current moment and the rainfall collected at the corresponding previous moment is 0, it means that the instantaneous rainfall at the current moment is 0; If the difference between the rainfall collected at the current moment and the rainfall collected at the corresponding previous moment is not 0, the difference is taken as the instantaneous rainfall at the current moment.

3. The method according to claim 2, characterized in that Similar days are clustered based on the photovoltaic data and the updated meteorological data to determine the weather type, including: Preprocessing the photovoltaic data and the updated meteorological data, performing feature extraction, and determining a feature sequence; The feature sequence is input into a fuzzy C-means clustering algorithm to identify weather types, wherein the weather types include sunny, cloudy and rainy days.

4. The method according to claim 3, characterized in that After inputting the feature sequence into the fuzzy C-means clustering algorithm and identifying the weather type, the method further includes: If the weather type is a rainy day, the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, or the rainy day is divided into light rain, moderate rain, heavy rain and rainstorm according to the rainfall data at each moment.

5. The method according to claim 4, characterized in that The rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the corrected rainfall data at each moment, including: The corrected rainfall data at each moment is used as the instantaneous rainfall at each moment; Determine the total rainfall in the time period to be measured according to the instantaneous rainfall at each moment; According to the total rainfall in the time period to be measured, rainy days are divided into light rain, moderate rain, heavy rain and rainstorm.

6. The method according to claim 4, characterized in that The rainy days are divided into light rain, moderate rain, heavy rain and rainstorm according to the rainfall data at each moment, including: According to the rainfall data at each moment in the time period to be measured, the rainfall data collected at the last collection moment and the rainfall data collected at the first collection moment in the time period to be measured are obtained; Determine the total rainfall in the time period to be measured according to the difference between the rainfall data collected at the last collection moment and the rainfall data collected at the first collection moment; According to the total rainfall in the time period to be measured, rainy days are divided into light rain, moderate rain, heavy rain and rainstorm.

7. The method according to any one of claims 5 or 6, characterized in that: The method of dividing rainy days into light rain, moderate rain, heavy rain and rainstorm according to the total rainfall in the time period to be measured includes: If the total rainfall in the time period to be tested is less than the first critical value, the rainy day is light rain; If the total rainfall in the time period to be measured is between the first critical value and the second critical value, the rainy day is moderate rain; If the total rainfall in the time period to be measured is between the second critical value and the third critical value, the rainy day is heavy rain; If the total rainfall in the measured time period is greater than the third critical value, the rainy day is a rainstorm.

8. A short-term photovoltaic power generation prediction device for a mobile platform based on weather type classification, characterized in that: include: A data acquisition module is used to collect photovoltaic data and meteorological data at different times within the test period based on the established photovoltaic power generation prediction mobile platform, wherein the meteorological data includes rainfall; A rainfall correction module, used to correct the rainfall data at each moment, and update the meteorological data according to the corrected rainfall data at each moment; A weather type classification module, used to cluster similar days according to the photovoltaic data and the updated meteorological data to determine the weather type; The photovoltaic power generation prediction module is used to predict the photovoltaic power generation within the time period based on the weather type and the pre-built CNN-LSTM combined deep learning model.

9. An electronic device, characterized in that: It includes a processor, and a memory and a network interface connected to the processor; the network interface is connected to a non-volatile memory in a server; when the processor is running, it calls a computer program from the non-volatile memory through the network interface, and runs the computer program through the memory to execute the method described in any one of claims 1 to 7.

10. A storage medium, characterized in that: Computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by the processor, the method according to any one of claims 1 to 7 is implemented.

Images