Monitoring method and device for photovoltaic power station operation data

Abstract

The present invention discloses a method and device for monitoring the operation data of a photovoltaic power station, which relates to the field of data processing technology, and the main purpose is to solve the problem of low effectiveness of third-party enterprises in monitoring the operation data of photovoltaic power stations. It includes: obtaining power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data; determining the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and performing data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station; when the third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain the monitoring result of the operation data.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for monitoring operation data of a photovoltaic power station. Background Art

[0002] Photovoltaic power stations refer to photovoltaic power station systems that directly convert solar energy into electrical energy. The most widely used photovoltaic power station type is distributed photovoltaic power stations, which are photovoltaic power station systems that install photovoltaic modules used for power generation on the roofs of power users. Since photovoltaic power station companies have relatively scattered power stations and a wide distribution range, it is difficult for third-party companies that have a cooperative relationship with photovoltaic power station companies to grasp the actual operating data of photovoltaic power stations, and it is impossible to make an accurate assessment of the operating conditions of photovoltaic power stations.

[0003] At present, the existing monitoring of photovoltaic power station operation data is usually based on manual inspections of each photovoltaic power station or the collection of photovoltaic power station operation data provided by photovoltaic power station companies to monitor the operation status of photovoltaic power stations. However, this method has high labor costs, and the accuracy and timeliness of monitoring are low, which is not conducive to accurately and timely discovering the operation status of photovoltaic power stations, and thus cannot meet the monitoring needs of third-party companies, reducing the effectiveness of using the operation data obtained from monitoring for third-party business processing. Summary of the invention

[0004] In view of this, the present invention provides a method and device for monitoring operation data of a photovoltaic power station, the main purpose of which is to solve the problem of low effectiveness of using the operation data obtained by monitoring to process business of third-party enterprises.

[0005] According to one aspect of the present invention, a method for monitoring operation data of a photovoltaic power station is provided, comprising:

[0006] Acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data;

[0007] Determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station;

[0008] When a third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain monitoring results of the operation data. The operation monitoring model is trained based on the resource allocation information configuration model weights of the business resource data.

[0009] Further, the determining of the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data includes:

[0010] Parsing the grid-connected status information of the photovoltaic sub-station in the device information;

[0011] The power generation data is divided into power supply series and parallel according to the grid connection status information, and the business resource data corresponding to the divided power generation data is classified to obtain the business resource types of the power generation data corresponding to different power supply series and parallel classifications;

[0012] The power generation efficiency is calculated based on the power generation data corresponding to the power supply series-parallel classification, and the transaction data is calculated based on the business resource data corresponding to the business resource type.

[0013] Furthermore, performing data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station includes:

[0014] Determine a data curve fitting function based on the power supply series-parallel classification and the business resource type, wherein the data curve fitting function is used to fit the power generation efficiency and / or the transaction data;

[0015] If the third party is a virtual resource type, the power generation efficiency and the transaction data are fitted respectively according to the data curve fitting function to obtain operation data including power generation efficiency operation data and transaction operation data;

[0016] If the third party is a physical resource type, the power generation efficiency and the transaction data are integrally fitted according to the data curve fitting function to obtain the operating data.

[0017] Furthermore, before predicting the operation data based on the operation monitoring model for which model training has been completed to obtain the monitoring result of the operation data, the method further includes:

[0018] Obtaining running training sample data and constructing a prediction network matching the business resource type, wherein the prediction network is a single-input or multi-input classification prediction network of at least three layers;

[0019] Determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence, wherein the resource allocation information is used to characterize the business resource allocation capability, and the preset business resource allocation correspondence records resource allocation information corresponding to distribution intervals of different business resource data;

[0020] The model weights of the prediction network are configured based on the resource allocation information, and the prediction model after the model weights are configured is trained through the operation training sample data to obtain the operation monitoring model.

[0021] Furthermore, before acquiring power generation data collected by a third-party terminal from at least one photovoltaic sub-station and business resource data matching the power generation data, the method further includes:

[0022] Establish data communication connections with third-party servers and allocate business communication interfaces to different third parties;

[0023] After determining the resource type of the third party, a business communication interface matching the resource type is retrieved, and the business operation is performed through the business communication interface. The resource type includes a virtual resource type and a physical resource type.

[0024] Furthermore, the method further comprises:

[0025] Calculating the operation monitoring coefficient of the operation data based on the monitoring results, the operation monitoring coefficient is used to characterize the extreme value floating range of different operation data under different monitoring requirements, and the monitoring results include normal operation status, abnormal operation status, and high-risk operation status;

[0026] If the operation monitoring coefficient in the monitoring result is greater than the preset monitoring threshold, an alarm message is sent to a third-party service end so that the third party can adjust the power generation and input resource data.

[0027] Furthermore, the third party includes at least one of a financial data enterprise, a physical industrial enterprise, and a technology product enterprise, and the method further includes:

[0028] Terminal collection rights are allocated to the third party, where the collection rights are used to indicate the rights of different third-party terminals to collect data from different photovoltaic sub-stations.

[0029] According to another aspect of the present invention, a device for monitoring operation data of a photovoltaic power station is provided, comprising:

[0030] An acquisition module, used to acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data;

[0031] A fitting module, configured to determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station;

[0032] Prediction module: used to predict the operation data based on the operation monitoring model that has completed model training when a third party performs business operations, and obtain the monitoring results of the operation data. The operation monitoring model is trained based on the resource allocation information configuration model weights of the business resource data.

[0033] Furthermore, the fitting module includes:

[0034] A parsing unit, configured to parse the grid-connected status information of the photovoltaic sub-station in the device information;

[0035] a classification unit, configured to classify the power generation data into power series and parallel connections according to the grid-connected state information, and classify the business resource data corresponding to the divided power generation data to obtain business resource types of the power generation data corresponding to different power series and parallel connection classifications;

[0036] A calculation unit is used to calculate the power generation efficiency based on the power generation data corresponding to the power supply series-parallel classification, and calculate the transaction data based on the business resource data corresponding to the business resource type.

[0037] Furthermore, the fitting module also includes:

[0038] A first fitting unit, configured to determine a data curve fitting function based on the power supply series-parallel classification and the business resource type, wherein the data curve fitting function is used to fit the power generation efficiency and / or the transaction data;

[0039] A second fitting unit is used for fitting the power generation efficiency and the transaction data according to the data curve fitting function to obtain operation data including power generation efficiency operation data and transaction operation data if the third party is a virtual resource type;

[0040] The third fitting unit is used to perform overall fitting on the power generation efficiency and the transaction data according to the data curve fitting function to obtain operation data if the third party is a physical resource type.

[0041] Furthermore, the device also includes:

[0042] A training module, used to obtain running training sample data and build a prediction network matching the business resource type, wherein the prediction network is a single-input or multi-input classification prediction network of at least three layers;

[0043] An allocation module, configured to determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence, wherein the resource allocation information is used to characterize the business resource allocation capability, and the preset business resource allocation correspondence records resource allocation information corresponding to distribution intervals of different business resource data;

[0044] A training module is used to configure the model weight of the prediction network based on the resource allocation information, and to perform model training on the prediction model after the model weight is configured through the operation training sample data to obtain the operation monitoring model.

[0045] Furthermore, the device also includes:

[0046] The allocation module is used to establish a data communication connection with a third-party server and allocate business communication interfaces to different third parties;

[0047] The execution module is used to call the business communication interface matching the resource type after determining the resource type of the third party, and execute the business operation through the business communication interface. The resource type includes a virtual resource type and a physical resource type.

[0048] Furthermore, the device also includes:

[0049] A calculation module, used for calculating the operation monitoring coefficient of the operation data based on the monitoring result, wherein the operation monitoring coefficient is used to characterize the extreme value floating range of different operation data under different monitoring requirements, and the monitoring result includes a normal operation state, an abnormal operation state, and a high-risk operation state;

[0050] The alarm module is used to send an alarm message to a third-party server if the operation monitoring coefficient in the monitoring result is greater than a preset monitoring threshold, so that the third party can adjust the power generation and input resource data.

[0051] Furthermore, the device also includes:

[0052] The allocation module is further used to allocate terminal collection rights to the third party, and the collection rights are used to represent the rights of different third-party terminals to collect data from different photovoltaic sub-stations.

[0053] According to another aspect of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a processor to execute operations corresponding to the above-mentioned method for monitoring photovoltaic power station operation data.

[0054] According to another aspect of the present invention, there is provided a computer device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0055] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned photovoltaic power station operation data monitoring method.

[0056] By means of the above technical solution, the technical solution provided by the embodiment of the present invention has at least the following advantages:

[0057] The present invention provides a method and device for monitoring the operation data of a photovoltaic power station. Compared with the prior art, the embodiment of the present invention obtains the power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and the business resource data matching the power generation data; determines the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and performs data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station; when the third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain the monitoring result of the operation data, which greatly reduces the labor cost, improves the timeliness and accuracy of the photovoltaic power station operation data, and thus improves the effectiveness of using the monitored photovoltaic power station operation data for third-party enterprise business processing.

[0058] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0060] Figure 1 A flow chart of a method for monitoring operation data of a photovoltaic power station provided by an embodiment of the present invention is shown;

[0061] Figure 2 A flow chart of another method for monitoring operation data of a photovoltaic power station provided by an embodiment of the present invention is shown;

[0062] Figure 3 A flow chart of another method for monitoring operation data of a photovoltaic power station provided by an embodiment of the present invention is shown;

[0063] Figure 4 A block diagram showing the composition of a photovoltaic power station operation data monitoring device provided by an embodiment of the present invention;

[0064] Figure 5 A schematic structural diagram of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0065] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0066] The embodiment of the present invention provides a method for monitoring operation data of a photovoltaic power station, such as Figure 1 As shown, the method includes:

[0067] 101. Acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station and business resource data matching the power generation data.

[0068] In the embodiment of the present invention, in order to ensure the credibility of the power generation data, the third-party enterprise configures the terminal for data collection, which can be a non-contact data collection device for collecting the display data of each photovoltaic sub-station meter. For example, infrared meter data collector, camera meter data collector, etc. The frequency of data collection can be customized according to the needs of the user, such as collecting once every hour, collecting once every natural day, etc., which is not specifically limited in the embodiment of the present invention. The power generation data collected by the third-party terminal includes the electric energy directly provided to the enterprises or individuals under the roof where the photovoltaic sub-station is installed, and the electric energy provided to the enterprises sharing the power generation with the enterprises under the roof or input into the national grid in series or parallel. In order to better analyze the operation data in combination with business information, it is also necessary to obtain business resource data. Among them, the business resource data is used to characterize the data of investment or resource investment in the photovoltaic sub-station, including but not limited to capital investment, manpower investment, power station equipment investment, photovoltaic power station installation site investment, etc.

[0069] It should be noted that the terminal equipment for collecting power generation data is configured by a third-party enterprise, which can effectively ensure the accuracy and objectivity of the data, thereby improving the accuracy and timeliness of the monitoring of operating data. In addition, the use of low-cost non-contact data collection equipment to obtain power generation data from the meter end can avoid interference with the operating equipment of the photovoltaic power station due to the installation of third-party terminal equipment, as well as the unclear division of responsibilities for damage to power station equipment during the installation of third-party terminal equipment, and effectively reduce the cost of operating data monitoring, thereby improving the acceptance of third-party enterprises and photovoltaic power station enterprises.

[0070] 102. Determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data, and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station.

[0071] In an embodiment of the present invention, the equipment information of the photovoltaic sub-station includes the equipment installed capacity of the photovoltaic sub-station. The theoretical power generation of the current photovoltaic sub-station can be determined based on the installed capacity. The ratio of the actual power generation to the theoretical power generation in the collected power generation data is the overall power generation efficiency of the photovoltaic sub-station. For the power generation data of the photovoltaic sub-station supported by different business resource inputs, the transaction data is calculated based on the business resource data matching the power generation data. For example, a photovoltaic sub-station financed and constructed by a bank has a power generation of a and a power supply price of b, then the transaction data is the product of a and b. After obtaining the power generation efficiency and transaction data, data fitting is performed based on the power generation efficiency and transaction data of a photovoltaic sub-station over a period of time, and at least one fitting curve of the photovoltaic sub-station can be obtained. The fitting curve is used to characterize the operation data of the photovoltaic sub-station.

[0072] It should be noted that by fitting the power generation efficiency and transaction data to obtain operating data in the form of a curve, it is possible to more accurately reflect the changes in the operating data and the overall trend of change, thereby improving the accuracy and intuitiveness of the photovoltaic sub-station operating data monitoring. In addition, the time period corresponding to the fitted power generation efficiency and transaction data can be customized according to the actual needs of the user. For example, if a third-party enterprise needs to obtain the operating status data of the photovoltaic sub-station equipment, or the failure rate of the equipment operation, a shorter time period can be set; if a third-party enterprise needs to obtain the long-term operating trend of the photovoltaic sub-station, a longer time period can be set. Based on different data analysis needs, the amount of fitted data is set to meet the monitoring needs of different third-party enterprises for operating data, thereby improving the flexibility of operating data monitoring.

[0073] 103. When the third party performs a business operation, the operation data is predicted based on the operation monitoring model for which model training has been completed to obtain a monitoring result of the operation data.

[0074] In an embodiment of the present invention, in order to protect the rights and interests of a third-party enterprise, when a third-party enterprise performs business operations on a photovoltaic sub-station, such as capital investment, photovoltaic equipment investment, and other business operations, the operating status of the photovoltaic sub-station is evaluated based on the operating data of the photovoltaic sub-station. Specifically, the operating data is predicted and processed using an operation monitoring model to obtain monitoring results of the operating data. The operation monitoring model is trained based on the resource allocation information configuration model weights of the business resource data, and can accurately predict the monitoring results of the photovoltaic sub-station operating data, so as to provide reference and guidance for the business operations of the third-party enterprise for the photovoltaic enterprise, thereby ensuring the effectiveness of the third-party enterprise's business operation processing of the photovoltaic sub-station.

[0075] In an embodiment of the present invention, for further explanation and limitation, as Figure 2 As shown, the step 102 of determining the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data includes:

[0076] 201. Analyze the grid-connected status information of the photovoltaic sub-station in the device information.

[0077] 202. Divide the power generation data into series and parallel power supply according to the grid-connected status information, and classify the business resource data corresponding to the divided power generation data to obtain the business resource types of the power generation data corresponding to different series and parallel power supply classifications.

[0078] 203. Calculate power generation efficiency based on the power generation data corresponding to the power supply series-parallel classification, and calculate transaction data based on the business resource data corresponding to the business resource type.

[0079] In an embodiment of the present invention, the equipment information includes specification information such as the installed capacity of the power station and the inverter model, and also includes grid-connected status information and power supply user information, wherein the grid-connected status information includes status information used to characterize whether the photovoltaic sub-station has been grid-connected, and status information whether it has grid-connected conditions, etc. The power supply user information is used to characterize the type of power supply user, such as heavy industry enterprises, breeding enterprises, ordinary residents, etc. Since in actual power supply application scenarios, there is often a situation where a single photovoltaic sub-station cannot meet the power demand of power supply users, it is necessary to achieve high current or high voltage by connecting each photovoltaic sub-station in series or in parallel to the power supply network, so as to meet the power demand of different power supply users. For example, industrial and mining enterprises and chemical enterprises, the equipment they use requires a higher current, and it is necessary to operate two photovoltaic sub-stations in parallel to support the normal operation of the equipment. For different types of power supply users and different power supply voltage levels, the electricity price per unit of power generation is quite different. Therefore, it is necessary to divide the power generation data into power supply series and parallel based on the grid-connected state of each photovoltaic sub-station, which is series or parallel. For example, when the current photovoltaic sub-station is connected to the power supply grid in series, the power generated by it is classified as power supply series; when the photovoltaic sub-station is connected to the power supply grid in parallel, the power generated by it is classified as power supply series-parallel.

[0080] Furthermore, due to the different business resource types corresponding to the photovoltaic sub-stations, the electricity prices and transaction modes are different, and there are third-party enterprises that invest resources in photovoltaic power stations and are also power users of photovoltaic power stations. For example, as a photovoltaic panel supplier that invests photovoltaic panel resources in a photovoltaic sub-station and is also a power user of a photovoltaic sub-station, the power generation provided by the photovoltaic sub-station to the power user will be converted into the number of photovoltaic panels of the photovoltaic panel manufacturer for trading. Therefore, according to different power supply prices and transaction modes, business resource types are set, for example, physical business resource types for physical resource investment in photovoltaic power stations, and virtual resource types for capital investment in photovoltaic power stations. And the mapping relationship between different business resource types and different power supply series and parallel classifications is preset, and then the power generation data corresponding to each series and parallel classification is matched with the business resource type according to the preset mapping relationship, and the business resource type of the power generation data corresponding to each power supply series and parallel type is obtained. Further, according to the installed capacity and power generation data of all sub-stations corresponding to each series and parallel classification, the power generation efficiency corresponding to each series and parallel classification is calculated, and the transaction data is calculated according to the business resource data and power generation data corresponding to the business resource type.

[0081] It should be noted that, by dividing the power generation data according to the grid-connected status information, it is possible to obtain the power generation data of different power supply grid-connected classifications, as well as the distribution and development trend of the power generation data of different power supply grid-connected types. Further, for each power supply series and parallel classification, it is possible to divide the power generation data of different power supply prices and different transaction modes accurately according to the business resource type, so that the calculation of transaction data is more accurate, thereby greatly improving the accuracy of power generation data statistics and analysis, and at the same time improving the accuracy of transaction data.

[0082] In an embodiment of the present invention, for further explanation and limitation, as Figure 2 As shown, the step 102 of performing data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station includes:

[0083] 204. Determine a data curve fitting function based on the power supply series-parallel classification and the service resource type.

[0084] 205. If the third party is a virtual resource type, the power generation efficiency and the transaction data are fitted according to the data curve fitting function to obtain operation data including power generation efficiency operation data and transaction operation data.

[0085] 206. If the third party is a physical resource type, the power generation efficiency and the transaction data are integrally fitted according to the data curve fitting function to obtain operation data.

[0086] In the embodiment of the present invention, according to the resource types invested by the third-party enterprises in the photovoltaic power station, the third party can be divided into a physical resource type and a virtual resource type. Among them, the physical resource type refers to an enterprise that uses physical resources such as photovoltaic power station equipment as investment; the virtual resource type refers to an enterprise that uses virtual forms such as funds or software products as investment. Since third-party enterprises of different resource types focus on different operating data, for example, financial investment enterprises often pay attention to power generation efficiency operating data and transaction operating data at the same time. Therefore, for enterprises of virtual resource type, it is necessary to use a quadratic polynomial fitting regression equation fitting function to fit the power generation efficiency and transaction data respectively, and obtain a power generation efficiency operating data curve and a transaction operating data curve; and as a physical resource type enterprise that only invests in photovoltaic equipment, it is often more concerned about the overall operating status of the photovoltaic power station. Therefore, for enterprises of physical resource type, it is necessary to use a cubic polynomial fitting regression equation fitting function to fit the power generation efficiency and transaction data, so as to obtain a curve of the overall operating data.

[0087] It should be noted that based on the actual needs of third-party enterprises with different resource types, different data fitting methods are used to fit the power generation efficiency and transaction data to obtain power generation efficiency operation data, transaction operation data, and operation data representing the overall operation status. This can more specifically meet the data reference needs of different third-party enterprises, thereby improving the operation data monitoring experience of third-party enterprises.

[0088] In an embodiment of the present invention, for further explanation and limitation, as Figure 3 As shown, in step 103, before predicting the operation data based on the operation monitoring model for which model training has been completed and obtaining the monitoring result of the operation data, the method further includes:

[0089] 301. Obtain running training sample data and build a prediction network that matches the business resource type.

[0090] 302. Determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence.

[0091] 303. Configure the model weights of the prediction network based on the resource allocation information, and perform model training on the prediction model after the model weights are configured through the operation training sample data to obtain the operation monitoring model.

[0092] In an embodiment of the present invention, in order to predict the monitoring results, a corresponding prediction network is constructed for different business resource types. Since the operating data corresponding to different business resource types can be one group or multiple groups. For example, the operating data corresponding to the virtual resource type includes two groups of data, namely, power generation efficiency operating data and transaction operating data, while the physical resource type corresponds to a group of integrated operating data. Therefore, the prediction network can be single-input or multi-input. Also, since the business resource type includes at least a virtual resource type and a physical resource type, and each business resource type corresponds to a layer of prediction network, different business resource types need to be superimposed in the prediction network of the last layer according to the weight, therefore, the operation monitoring model needs to be a classification prediction network of at least three layers. Based on the above requirements, the prediction network can be a long short-term memory neural network (LSTM: Long Short-term Memory Networks). Of course, the business resource type can also be a further subdivided type based on the virtual resource type and the physical resource type. For example, the virtual resource type can also be further classified according to the amount of resources invested in the business resource data and the level of the power supply price.

[0093] In the embodiment of the present invention, the resource investment of different business resource types has different degrees of influence on the operation of photovoltaic sub-stations. For example, capital investment can support the operation of a large number of photovoltaic sub-stations, while the number of photovoltaic sub-stations that can be supported by photovoltaic equipment investment is very limited. Therefore, it is necessary to set the business resource allocation correspondence according to the distribution intervals of different business resource data, and match the resource allocation information of different business resource types according to the business resource allocation correspondence, that is, to match different weights for different business resource types. Among them, the distribution interval division method of the business resource data and the specific weights in the resource allocation information can be customized according to actual business needs. For example, the distribution interval of the amount of investment funds in the business resource data is divided, and the amount of investment funds less than 500,000 is divided into an interval, and the corresponding resource allocation information is set, that is, the weight is 0.2, and the amount of investment funds between 500,000 and 2 million (including 500,000 and 2 million) is divided into an interval, and the corresponding resource allocation information is set, that is, the weight is 0.3, and the amount of investment funds greater than 2 million is divided into an interval, and the corresponding resource allocation information is set, that is, the weight is 0.5. Furthermore, based on the weights of different business resource types, corresponding weights are configured for the prediction network layer corresponding to the business resource type, and the prediction model after the model weights are configured is trained using the operation training sample data to obtain the operation monitoring model.

[0094] It should be noted that by constructing a prediction network according to different business resource types and configuring the prediction network layer with corresponding weights according to the degree of influence and importance of different business resource types on the operation of the photovoltaic power station, the monitoring results can be more in line with the actual operating conditions of the actual photovoltaic power station, thereby effectively improving the prediction accuracy of the operation monitoring model.

[0095] In one embodiment of the present invention, for further explanation and limitation, before obtaining the power generation data collected by a third-party terminal from at least one photovoltaic sub-station and the business resource data matching the power generation data in step 101, the method further includes:

[0096] Establish data communication connections with third-party servers and allocate business communication interfaces to different third parties.

[0097] After the resource type of the third party is determined, a business communication interface matching the resource type is retrieved, and the business operation is performed through the business communication interface.

[0098] In the embodiment of the present invention, in order to ensure the information security of third-party enterprises. By allocating corresponding communication interfaces to different third-party enterprise servers, a data communication connection is established with the third-party server, and the resource type corresponding to the third-party server is determined. Among them, the resource type includes virtual resource type and physical resource type. When third-party enterprises of different resource types invest resources in one or more photovoltaic sub-stations, corresponding business operations can be triggered through different data communication interfaces. For example, when a financial enterprise injects funds into a photovoltaic sub-station, it can perform a business operation of fund transfer through the communication interface configured by the bank account; the photovoltaic equipment resource investor can perform a business operation of photovoltaic equipment investment through the communication interface configured by the product ordering system. By establishing data communication interfaces of corresponding resource types with third-party enterprises of different resource types, the data communication interface can be accurately matched with the business operation type of the third-party enterprise, without the need for redundant transit communications, thereby effectively improving the information security and confidentiality of the third-party enterprise.

[0099] In an embodiment of the present invention, for further explanation and limitation, the method further includes:

[0100] Calculating the operation monitoring coefficient of the operation data based on the monitoring results, the operation monitoring coefficient is used to characterize the extreme value floating range of different operation data under different monitoring requirements, and the monitoring results include normal operation status, abnormal operation status, and high-risk operation status;

[0101] If the operation monitoring coefficient in the monitoring result is greater than the preset monitoring threshold, an alarm message is sent to a third-party service end so that the third party can adjust the power generation and input resource data.

[0102] In the embodiment of the present invention, in order to further improve the effectiveness of monitoring, the operation monitoring coefficients of different operation data under different monitoring requirements are calculated based on the monitoring results. Specifically, the power generation efficiency and the transaction data are distributed in the floating range of the maximum value and the minimum value. Taking the power generation efficiency as an example, when the operation state is normal, the power generation efficiency takes the minimum value, when the operation state is high-risk, the power generation efficiency takes the maximum value, and when the operation state is abnormal, the power generation efficiency takes the average value, and the corresponding weight coefficients are set for the operation data according to different monitoring requirements. For example, under the monitoring requirement of focusing more on power generation efficiency, the weight coefficient of power generation efficiency is 0.7, and the weight coefficient of transaction data is 0.3; under the monitoring requirement of focusing more on transaction data, the weight coefficient of power generation efficiency is 0.3, and the weight coefficient of transaction data is 0.7. Multiply each operation data determined based on the monitoring results by the corresponding weight coefficient, and add the product results of each operation data to obtain the operation monitoring coefficient. For example, under the monitoring requirement of focusing more on power generation efficiency, the power generation efficiency is 0.8, and the transaction data is 2, then the operation monitoring coefficient is 0.8×0.7+2×0.3=1.16. Furthermore, a preset monitoring threshold is used to compare and distinguish with the operation monitoring coefficient. When the operation monitoring coefficient is greater than the preset monitoring threshold, a corresponding alarm message is generated and sent to a third-party server, so that the third party can adjust the amount of resources invested or the number of photovoltaic sub-stations invested according to the alarm message. The weight coefficient of the above-mentioned operation data and the setting of the preset monitoring threshold can be customized according to the actual application scenario, and the embodiment of the present invention does not make specific limitations.

[0103] It should be noted that by calculating the operation monitoring coefficient and using the preset monitoring threshold to judge the operation monitoring coefficient, and determining whether to generate early warning information based on the judgment result, when abnormalities occur in the operation data monitoring results, timely and effective notifications can be sent to third-party companies, thereby ensuring the safety and effectiveness of the company's investment operations.

[0104] In an embodiment of the present invention, for further explanation and limitation, the third party includes at least one of a financial data enterprise, a physical industrial enterprise, and a technology product enterprise, and the method further includes:

[0105] Terminal collection rights are allocated to the third party, where the collection rights are used to indicate the rights of different third-party terminals to collect data from different photovoltaic sub-stations.

[0106] In the embodiment of the present invention, the third party includes at least one of the following enterprise parties: a financial data enterprise party, that is, an enterprise that invests in a photovoltaic power station in the form of funds, such as a bank and a financial enterprise; an entity industrial enterprise party, that is, an enterprise that invests in a photovoltaic power station in the form of resources such as photovoltaic equipment or a power station installation site, such as a photovoltaic panel, inverter manufacturer; and a technology product enterprise party, that is, an enterprise that invests in a photovoltaic power station in the form of software resources such as a power station operation platform and an APP, such as a software company. According to the target photovoltaic sub-station invested by the third-party enterprise, the corresponding terminal data collection authority is allocated to it. For example, if an investment bank invests in photovoltaic sub-stations No. 100 to 110, the terminal equipment data collection authority of photovoltaic sub-stations No. 100 to 110 is allocated to the investment bank. Thereby protecting the rights and interests of third-party enterprises. At the same time, different data collection times can also be allocated to each third-party enterprise, thereby alleviating data communication pressure and ensuring data communication stability.

[0107] The present invention provides a method for monitoring the operation data of a photovoltaic power station. The embodiment of the present invention obtains the power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and the business resource data matching the power generation data; determines the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and performs data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station; when a third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain the monitoring result of the operation data, which greatly reduces the labor cost, improves the timeliness and accuracy of the photovoltaic power station operation data, and thus improves the effectiveness of using the monitored photovoltaic power station operation data for third-party enterprise business processing.

[0108] Furthermore, as a response to the above Figure 1 The embodiment of the present invention provides a monitoring device for photovoltaic power station operation data, such as Figure 4 As shown, the device comprises:

[0109] An acquisition module 41 is used to acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data;

[0110] A fitting module 42 is used to determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station;

[0111] Prediction module 43: used to predict the operation data based on the operation monitoring model that has completed model training when a third party performs business operations, and obtain the monitoring results of the operation data. The operation monitoring model is trained based on the resource allocation information configuration model weights of the business resource data.

[0112] Furthermore, the fitting module includes:

[0113] A parsing unit, configured to parse the grid-connected status information of the photovoltaic sub-station in the device information;

[0114] a classification unit, configured to classify the power generation data into power series and parallel connections according to the grid-connected state information, and classify the business resource data corresponding to the divided power generation data to obtain business resource types of the power generation data corresponding to different power series and parallel connection classifications;

[0115] A calculation unit is used to calculate the power generation efficiency based on the power generation data corresponding to the power supply series-parallel classification, and calculate the transaction data based on the business resource data corresponding to the business resource type.

[0116] Furthermore, the fitting module also includes:

[0117] A first fitting unit, configured to determine a data curve fitting function based on the power supply series-parallel classification and the business resource type, wherein the data curve fitting function is used to fit the power generation efficiency and / or the transaction data;

[0118] A second fitting unit is used for fitting the power generation efficiency and the transaction data according to the data curve fitting function to obtain operation data including power generation efficiency operation data and transaction operation data if the third party is a virtual resource type;

[0119] The third fitting unit is used to perform overall fitting on the power generation efficiency and the transaction data according to the data curve fitting function to obtain operation data if the third party is a physical resource type.

[0120] Furthermore, the device also includes:

[0121] A training module, used to obtain running training sample data and build a prediction network matching the business resource type, wherein the prediction network is a single-input or multi-input classification prediction network of at least three layers;

[0122] An allocation module, configured to determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence, wherein the resource allocation information is used to characterize the business resource allocation capability, and the preset business resource allocation correspondence records resource allocation information corresponding to distribution intervals of different business resource data;

[0123] A training module is used to configure the model weight of the prediction network based on the resource allocation information, and to perform model training on the prediction model after the model weight is configured through the operation training sample data to obtain the operation monitoring model.

[0124] Furthermore, the device also includes:

[0125] The allocation module is used to establish a data communication connection with a third-party server and allocate business communication interfaces to different third parties;

[0126] The execution module is used to call the business communication interface matching the resource type after determining the resource type of the third party, and execute the business operation through the business communication interface. The resource type includes a virtual resource type and a physical resource type.

[0127] Furthermore, the device also includes:

[0128] A calculation module, used for calculating the operation monitoring coefficient of the operation data based on the monitoring result, wherein the operation monitoring coefficient is used to characterize the extreme value floating range of different operation data under different monitoring requirements, and the monitoring result includes a normal operation state, an abnormal operation state, and a high-risk operation state;

[0129] The alarm module is used to send an alarm message to a third-party server if the operation monitoring coefficient in the monitoring result is greater than a preset monitoring threshold, so that the third party can adjust the power generation and input resource data.

[0130] Furthermore, the device also includes:

[0131] The allocation module is further used to allocate terminal collection rights to the third party, and the collection rights are used to represent the rights of different third-party terminals to collect data from different photovoltaic sub-stations.

[0132] The present invention provides a monitoring device for photovoltaic power station operation data. The embodiment of the present invention obtains power generation data collected by a third-party terminal from at least one photovoltaic sub-station and business resource data matching the power generation data; determines the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and performs data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station; when a third party performs a business operation, the operation data is predicted based on an operation monitoring model that has completed model training to obtain the monitoring result of the operation data, which greatly reduces the labor cost, improves the timeliness and accuracy of the photovoltaic power station operation data, and thus improves the effectiveness of using the monitored photovoltaic power station operation data for third-party enterprise business processing.

[0133] According to an embodiment of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, and the computer executable instruction can execute the data query method in any of the above method embodiments.

[0134] Figure 5 A schematic diagram of the structure of a computer device provided according to an embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computer device.

[0135] like Figure 5 As shown, the computer device may include: a processor (processor) 502 , a communication interface (Communications Interface) 504 , a memory (memory) 506 , and a communication bus 508 .

[0136] The processor 502 , the communication interface 504 , and the memory 506 communicate with each other via a communication bus 508 .

[0137] The communication interface 504 is used to communicate with other devices such as clients or other servers.

[0138] The processor 502 is used to execute the program 510, and specifically can execute the relevant steps in the above-mentioned photovoltaic power station operation data monitoring embodiment.

[0139] Specifically, the program 510 may include program codes, which include computer operation instructions.

[0140] The processor 502 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computer device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0141] The memory 506 is used to store the program 510. The memory 506 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0142] The program 510 may be specifically configured to enable the processor 502 to perform the following operations:

[0143] Acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data;

[0144] Determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station;

[0145] When a third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain monitoring results of the operation data. The operation monitoring model is trained based on the resource allocation information configuration model weights of the business resource data.

[0146] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0147] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring operation data of a photovoltaic power station, characterized in that: include: Acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station and business resource data matching the power generation data, wherein the business resource data is used to represent data for investment or resource input into the photovoltaic sub-station; Determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station, wherein the fitting curve is used to characterize the operation data of the photovoltaic sub-station; When a third party performs a business operation, the operation data is predicted based on the operation monitoring model that has completed model training to obtain a monitoring result of the operation data, wherein the operation monitoring model is trained based on the resource allocation information configuration model weight of the business resource data, and the business operation includes capital investment and photovoltaic equipment investment; Wherein, before predicting the operation data based on the operation monitoring model that has completed model training to obtain the monitoring result of the operation data, the method further includes: Obtaining running training sample data and constructing a prediction network matching the business resource type, wherein the prediction network is a single-input or multi-input classification prediction network of at least three layers; Determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence, wherein the resource allocation information is used to characterize the business resource allocation capability, and the preset business resource allocation correspondence records resource allocation information corresponding to distribution intervals of different business resource data; The model weight of the prediction network is configured based on the resource allocation information, and the prediction network after the model weight is configured is trained through the operation training sample data to obtain the operation monitoring model.

2. The method according to claim 1, characterized in that The determining of the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data includes: Parsing the grid-connected status information of the photovoltaic sub-station in the device information; The power generation data is divided into power supply series and parallel according to the grid connection status information, and the business resource data corresponding to the divided power generation data is classified to obtain the business resource types of the power generation data corresponding to different power supply series and parallel classifications; The power generation efficiency is calculated based on the power generation data corresponding to the power supply series-parallel classification, and the transaction data is calculated based on the business resource data corresponding to the business resource type.

3. The method according to claim 2, characterized in that The performing data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station includes: Determine a data curve fitting function based on the power supply series-parallel classification and the business resource type, wherein the data curve fitting function is used to fit the power generation efficiency and / or the transaction data; If the third party is a virtual resource type, the power generation efficiency and the transaction data are fitted respectively according to the data curve fitting function to obtain operation data including power generation efficiency operation data and transaction operation data; If the third party is a physical resource type, the power generation efficiency and the transaction data are integrally fitted according to the data curve fitting function to obtain the operating data.

4. The method according to claim 1, characterized in that: Before acquiring power generation data collected by a third-party terminal from at least one photovoltaic sub-station and business resource data matching the power generation data, the method further includes: Establish data communication connections with third-party servers and allocate business communication interfaces to different third parties; After determining the resource type of the third party, a business communication interface matching the resource type is retrieved, and the business operation is performed through the business communication interface. The resource type includes a virtual resource type and a physical resource type.

5. The method according to claim 1, characterized in that The method further comprises: Calculating the operation monitoring coefficient of the operation data based on the monitoring results, the operation monitoring coefficient is used to characterize the extreme value floating range of different operation data under different monitoring requirements, and the monitoring results include normal operation status, abnormal operation status, and high-risk operation status; If the operation monitoring coefficient in the monitoring result is greater than the preset monitoring threshold, an alarm message is sent to a third-party service end so that the third party can adjust the power generation and input resource data.

6. The method according to any one of claims 1 to 5, characterized in that: The third party includes at least one of a financial data enterprise, a physical industrial enterprise, and a technology product enterprise, and the method further includes: Terminal collection rights are allocated to the third party, where the collection rights are used to indicate the rights of different third-party terminals to collect data from different photovoltaic sub-stations.

7. A monitoring device for photovoltaic power station operation data, characterized in that: include: An acquisition module, used to acquire power generation data collected by a third-party terminal from at least one photovoltaic sub-station, and business resource data matching the power generation data, wherein the business resource data is used to represent data for investment or resource input into the photovoltaic sub-station; a fitting module, configured to determine the power generation efficiency and transaction data of the photovoltaic sub-station based on the equipment information of the photovoltaic sub-station, the power generation data and the business resource data, and to perform data curve fitting on the power generation efficiency and the transaction data to obtain the operation data of the photovoltaic sub-station, wherein the fitting curve is used to characterize the operation data of the photovoltaic sub-station; Prediction module: used for predicting the operation data based on the operation monitoring model that has completed model training when the third party performs business operations, and obtaining the monitoring results of the operation data. The operation monitoring model is obtained by completing the training based on the resource allocation information configuration model weight of the business resource data. The business operations include capital investment and photovoltaic equipment investment. The device also includes: A training module, used to obtain running training sample data and build a prediction network matching the business resource type, wherein the prediction network is a single-input or multi-input classification prediction network of at least three layers; An allocation module, configured to determine resource allocation information matching the business resource data based on a preset business resource allocation correspondence, wherein the resource allocation information is used to characterize the business resource allocation capability, and the preset business resource allocation correspondence records resource allocation information corresponding to distribution intervals of different business resource data; A training module is used to configure the model weight of the prediction network based on the resource allocation information, and to perform model training on the prediction network after the model weight is configured through the operation training sample data to obtain the operation monitoring model.

8. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and the executable instruction enables a processor to execute an operation corresponding to the method for monitoring photovoltaic power station operation data according to any one of claims 1 to 6.

9. A computer device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform an operation corresponding to the method for monitoring photovoltaic power station operation data according to any one of claims 1 to 6.

Images