CN115358515A - Power prediction method and system for distributed photovoltaic system - Google Patents
Power prediction method and system for distributed photovoltaic system Download PDFInfo
- Publication number
- CN115358515A CN115358515A CN202210807589.0A CN202210807589A CN115358515A CN 115358515 A CN115358515 A CN 115358515A CN 202210807589 A CN202210807589 A CN 202210807589A CN 115358515 A CN115358515 A CN 115358515A
- Authority
- CN
- China
- Prior art keywords
- data
- prediction
- historical data
- power
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The application relates to a power prediction method of a distributed photovoltaic system, wherein the method comprises the following steps: acquiring historical data, wherein the historical data comprises: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area; preprocessing historical data to obtain a historical data set of a target granularity, and segmenting the historical data set into a training set and a prediction set; respectively training a pre-constructed XGboost model and a Bagging model through a training set; predicting based on the prediction sets respectively through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and linearly combining the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system. Through the application, the accuracy of the power prediction result is improved, effective data support is provided for the whole operation and maintenance of the distributed photovoltaic system, and safety hidden patients are reduced.
Description
Technical Field
The application relates to the field of distributed energy management, in particular to a power prediction method and system for a distributed photovoltaic system.
Background
The comprehensive energy management system is an energy management and control platform integrating photovoltaic, energy storage, wind power, load, carbon management and the like, adopts a layered and graded control system structure, and realizes centralized monitoring and unified scheduling on various electrical energy media and various energy supply systems. The energy utilization rate can be improved through multi-angle and multi-hand mutual combination modes such as energy prediction, energy monitoring, energy statistics, energy analysis and loss analysis.
In the related art, in a distributed photovoltaic energy system, each photovoltaic device is dispersed in each position of a city, so that the construction scale is relatively small, the operation and maintenance difficulty is high, and the manual management cost is high. In order to realize unmanned operation and maintenance of distributed photovoltaic equipment and improve the intelligent level, the technologies of intelligent gateway + big data processing and the like are adopted by part of comprehensive energy management systems, energy is optimized, monitored and managed, and the efficient operation of the distributed photovoltaic energy system is guaranteed.
However, for each photovoltaic energy system, the overall operation condition of the system cannot be accurately determined only from the real-time power generation condition and the equipment operation condition of the photovoltaic, and the abnormal interference of the surface dust of the photovoltaic module on the output power of the equipment cannot be eliminated, so that the operation state of the distributed photovoltaic system cannot be efficiently and accurately evaluated. In addition, each distributed device (power station) runs under the unmanned patrol condition for a long time, accident hidden dangers cannot be predicted in advance, and accident responses cannot be responded in time, so that major safety accidents are caused.
At present, no effective solution is provided for the problem that the distributed photovoltaic energy system cannot be efficiently and accurately evaluated.
Disclosure of Invention
The embodiment of the application provides a power prediction method, a power prediction system, computer equipment and a computer readable storage medium for a distributed photovoltaic system, so as to at least solve the problem that the distributed photovoltaic energy system cannot be efficiently and accurately evaluated in the related art.
In a first aspect, an embodiment of the present application provides a power prediction method for a distributed photovoltaic system, where the method includes:
obtaining historical data, wherein the historical data comprises: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in a target area;
preprocessing the historical data to obtain a historical data set of a target granularity, and segmenting the historical data set into a training set and a prediction set;
respectively training a pre-constructed XGboost model and a Bagging model through the training set;
predicting based on the prediction set respectively through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and performing linear combination on the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system.
In some of these embodiments, pre-processing the historical data comprises:
judging whether the integrity rate of the historical data is smaller than a preset threshold value or not, if so,
performing data cleaning, data deduplication and abnormal value processing on the historical data to obtain a historical data set of the target granularity;
if not, after the historical data is filled with data, data cleaning, data deduplication and abnormal value processing are carried out, and the historical data set of the target granularity is obtained.
In some embodiments, determining whether the integrity rate of the historical data is less than a preset threshold comprises:
searching the historical data at different moments from the historical data;
calculating the whole data missing rate of the historical data according to the historical data at different moments, and judging whether the whole rate of the historical data is smaller than a preset threshold value or not according to the whole data missing rate, wherein the preset threshold value is determined according to empirical knowledge in the field.
In some embodiments, after obtaining the power prediction data for the distributed photovoltaic energy system, the method further comprises:
calculating an evaluation index according to the power prediction data, wherein the evaluation index is used for indicating the accuracy of the power prediction data and comprises the following steps: root mean square error, mean absolute error, correlation coefficient, and maximum prediction error.
In some embodiments, the evaluation index is calculated by the following formula:
δ max ＝max(|P Mi -P Pi |)
wherein RMSE is the root mean square error, MAE is the mean absolute error, r is the correlation coefficient, δ max Is the maximum prediction error, n is the number of all samples, P Mi Is the actual power at time i, P Pi The predicted power at the ith moment, cap is the starting capacity of the photovoltaic power station,
is the average of the actual power of all samples,
is the average of all predicted power samples.
In some embodiments, in the process of training the XGBoost model and the Bagging model respectively through the training set, model input is defined as numerical weather in the training set, and model output is defined as photovoltaic power at a predicted time point.
In a second aspect, an embodiment of the present application provides a power prediction system for a distributed photovoltaic system, where the system includes: the device comprises an acquisition module, a preprocessing module, a model training module and a prediction module, wherein:
the obtaining module is configured to obtain historical data, where the historical data includes: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area;
the preprocessing module is used for preprocessing the historical data to obtain a historical data set of a target granularity and segmenting the historical data set into a training set and a prediction set;
the model training module is used for respectively training a pre-constructed XGboost model and a Bagging model through the training set;
the prediction module is used for predicting based on the prediction set through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and performing linear combination on the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system.
In some embodiments, the preprocessing module, performing preprocessing on the historical data, comprises:
judging whether the integrity rate of the historical data is smaller than a preset threshold value or not, if so,
performing data cleaning, data deduplication and abnormal value processing on the historical data to obtain a historical data set of the target granularity;
if not, after the historical data is subjected to data filling, data cleaning, data deduplication and abnormal value processing are carried out, and the historical data set of the target granularity is obtained.
Compared with the related art, the power prediction method of the distributed photovoltaic system provided by the embodiment of the application obtains historical data; preprocessing historical data to obtain a historical data set of target granularity, and segmenting the historical data set into a training set and a prediction set; respectively training a pre-constructed XGboost model and a Bagging model through a training set; predicting based on the prediction sets respectively through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and linearly combining the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system. Through the method and the device, the problem that the distributed photovoltaic energy system cannot be accurately and efficiently evaluated in the existing mode is solved, the power of the photovoltaic energy system is accurately and efficiently predicted through multiple models, the accuracy of a power prediction result is improved, effective data support is provided for the whole operation and maintenance of the distributed photovoltaic system, and potential safety hazards are reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic application environment diagram of a power prediction method of a distributed photovoltaic system according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of power prediction for a distributed photovoltaic system according to an embodiment of the present application;
FIG. 3 is a block diagram of a power prediction system for a distributed photovoltaic system according to an embodiment of the present application;
FIG. 4 is an architectural diagram of a power prediction system of a distributed photovoltaic system according to an embodiment of the present application;
fig. 5 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the application, and that it is also possible for a person skilled in the art to apply the application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of describing the invention (including a single reference) are to be construed in a non-limiting sense as indicating either the singular or the plural. The use of the terms "including," "comprising," "having," and any variations thereof herein, is meant to cover a non-exclusive inclusion; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as used herein means two or more. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, "a and/or B" may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The power prediction method of the distributed photovoltaic system provided by the application can be applied to an application environment shown in fig. 1, fig. 1 is an application environment schematic diagram of the power prediction method of the distributed photovoltaic system according to the embodiment of the application, and as shown in fig. 1, information channels are established between each photovoltaic device and the integrated energy management system, wherein the photovoltaic devices are widely arranged at the top of a building in a city, on a balcony and the like. The comprehensive energy management system obtains the power generation condition and the equipment operation condition of each photovoltaic equipment through the information channel. Furthermore, the comprehensive energy management system can also acquire numerical weather corresponding to the weather from a third-party platform, and perform photovoltaic power prediction based on accumulated historical weather information and historical equipment power generation conditions through an internal prediction model to obtain a photovoltaic power prediction value at a future moment. By utilizing the predicted value, energy assessment and risk management and control can be performed, and effective data support is provided for efficient and accurate operation of the comprehensive energy management system.
Fig. 2 is a flowchart of a power prediction method of a distributed photovoltaic system according to an embodiment of the present application, and as shown in fig. 2, the flowchart includes the following steps:
s201, acquiring historical data, wherein the historical data comprises: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area;
the method is applied to an integrated energy management platform, wherein the integrated energy management system is a system for performing cluster monitoring and unified scheduling on an electric energy medium and an energy supply system.
Further, the historical photovoltaic power can be obtained from a local database of the integrated energy management system, and the weather value can be obtained from a third-party meteorological data platform.
Specifically, the weather numerical value is numerical calculation through a large-scale computer under the condition of a certain initial value and a certain boundary value according to the actual weather condition to obtain numerical weather data; and historical photovoltaic power is the actual generated power in the distributed photovoltaic system.
S202, preprocessing historical data to obtain a historical data set of a target granularity, and segmenting the historical data set into a training set and a prediction set;
since the data format obtained in step S201 is not standardized, the integrity of the data is not sufficient. Therefore, in order to obtain fine-grained data that can be used for algorithm training, the acquired historical data needs to be preprocessed. Specifically, the method comprises the following steps: data filling, data cleaning, data deduplication, outlier processing and the like.
Further, the data after preprocessing is divided into two parts, i.e., a training set and a prediction set. It is understood that the training set is used for model training, and the prediction set is used for actual result prediction after model training is finished. In this embodiment, the training data and the prediction data are strictly distinguished, so as to ensure the rigor of the model prediction result.
S203, respectively training a pre-constructed XGboost model and a Bagging model through a training set;
in the process of respectively training the XGboost model and the Bagging model through the training set, input is defined as numerical weather in the training set, and output is defined as photovoltaic power of a prediction time point.
Furthermore, the XGboost algorithm is an improvement of the GBDT algorithm, is a common supervised ensemble learning algorithm, and has the characteristics of strong flexibility, convenience, capability of constructing models in parallel and the like;
the Bagging algorithm (also called a Bagging algorithm) is a group learning algorithm in the field of machine learning, can be combined with other classification and regression algorithms, improves the accuracy and stability of the algorithm, and avoids overfitting by reducing the variance of the result.
Specifically, for how to set the model parameters and perform the training, the technical details are conventional technical means in the art, and those skilled in the art can reasonably select the model parameters without creative efforts, so that details are not described in this embodiment.
S204, forecasting is respectively carried out on the basis of the forecasting sets through the trained XGboost model and the trained Bagging model to obtain first forecasting data and second forecasting data reflecting photovoltaic power, and the first forecasting data and the second forecasting data are linearly combined to obtain power forecasting data of the distributed photovoltaic system.
It should be noted that, in this embodiment, the XGBoost model and the Bagging model are respectively used for prediction, and after two prediction results are obtained, the two results are linearly combined. Because the prediction logics and the prediction principles of the two models are different, the difference of the two models is integrated with the result obtained by combining the two prediction results, so that the error possibly generated by a single model is avoided as much as possible, and the finally obtained predicted photovoltaic power is more accurate.
Through the steps S201 to S204, compared with the method in the related art, which only determines the power of the distributed system from the real-time power generation condition of the photovoltaic and the equipment operation condition. According to the method and the device, through multiple models, prediction is carried out according to historical data, abnormal interference of conditions such as surface dust deposition of the photovoltaic module on the output power of the device is fully considered, and the difference prediction results of the two models are integrated, so that the prediction results of the models are more accurate compared with the existing mode. Therefore, effective data support is provided for the overall operation and maintenance of the photovoltaic system, and potential safety hazards are reduced and avoided.
In some embodiments, in order to obtain fine-grained data that can satisfy model training, after obtaining historical data, a preprocessing step needs to be performed on the historical data, which specifically includes:
firstly, judging whether the integrity rate of the historical data is smaller than a preset threshold value, wherein the concrete implementation of judging the integrity rate of the data comprises the following steps: searching historical data at different moments from the historical data, and calculating the overall data missing rate of the historical data according to the historical data at different moments; and judging whether the integrity rate of the historical data is smaller than a preset threshold value or not according to the integral data missing rate. It should be noted that the preset threshold is determined according to empirical knowledge in the field;
secondly, if the data integrity rate meets the requirement, directly performing data cleaning, data deduplication and abnormal value processing on the historical data to obtain a historical data set of the target granularity;
and if the data integrity rate does not meet the requirement, the data is required to be filled, and then data cleaning, data deduplication and abnormal value processing are carried out to obtain a historical data set of the target granularity.
In some embodiments, after obtaining the power prediction data of the distributed photovoltaic energy system, an evaluation index of the prediction result is further calculated according to the power prediction data, where the evaluation index is used for knowing the accuracy of the prediction result, and the method includes: the power estimation method comprises the following steps of root mean square error, average absolute error, correlation coefficient and maximum prediction error, wherein the correlation coefficient is the correlation coefficient of predicted power and actual power.
Specifically, the evaluation index may be calculated by the following formula:
δ max ＝max(|P Mi -P Pi |)
where RMSE is the root mean square error, MAE is the mean absolute error, r is the correlation coefficient, δ max Is the maximum prediction error, n is the number of all samples, P Mi Is the actual power at time i, P Pi The predicted power at the ith moment, cap is the starting capacity of the photovoltaic power station,
is the average of the actual power of all samples,
is the average of all predicted power samples.
It should be noted that, through practical investment verification, in the photovoltaic power prediction result obtained by the scheme of the present application: the monthly mean square root error is less than 10 percent, and the monthly correlation coefficient is more than 90 percent.
The embodiment also provides a power prediction system of a distributed photovoltaic system, which is used for implementing the above embodiments and preferred embodiments, and the description of the system is omitted. As used below, the terms "module," "unit," "sub-unit," and the like may implement a combination of software and/or hardware of predetermined functions. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware or a combination of software and hardware is also possible and contemplated.
Fig. 3 is a block diagram of a power prediction system of a distributed photovoltaic system according to an embodiment of the present application, and as shown in fig. 3, the system includes: an acquisition module 30, a pre-processing module 31, a model training module 32 and a prediction module 33, wherein:
the obtaining module 30 is configured to obtain historical data, where the historical data includes: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area;
the preprocessing module 31 is configured to preprocess the historical data to obtain a historical data set of a target granularity, and segment the historical data set into a training set and a prediction set;
the model training module 32 is used for respectively training a pre-constructed XGboost model and a Bagging model through a training set;
the prediction module 33 is configured to perform prediction based on the prediction sets through the trained XGBoost model and the trained Bagging model, respectively, to obtain first prediction data and second prediction data reflecting the photovoltaic power, and perform linear combination on the first prediction data and the second prediction data, to obtain power prediction data of the distributed photovoltaic system.
In some embodiments, fig. 4 is an architecture diagram of a power prediction system of a distributed photovoltaic system according to an embodiment of the present application, as shown in fig. 4:
the system firstly obtains historical data, and further preprocesses the historical data, and segments the preprocessed historical data into a training set and a prediction set. And respectively inputting the training set data into a pre-constructed XGboost model and a Bagging model for model training.
Furthermore, after model training and model verification, two prediction models which can be used for actual prediction business are obtained. And predicting according to the prediction sets through the XGboost model and the Bagging model respectively to obtain a first prediction result and a second prediction result respectively, and finally, linearly combining the two prediction results to obtain a prediction result reflecting the power of the distributed photovoltaic system.
Through the system, the differentiation characteristics of the two models are combined, so that the prediction result is more accurate, more data support is provided for the comprehensive energy management system, and the potential safety hazard is reduced.
It should be noted that the system refers to the national standard "design standard of wind, light and storage combined power station" to realize the photovoltaic power prediction. The photovoltaic power prediction is divided into short-term prediction and ultra-short-term prediction, wherein the short-term prediction refers to prediction of power between the time zero of the next day and 72h in the future, and the ultra-short-term prediction refers to prediction of power between 0.25h and 4h in the future.
In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of power prediction for a distributed photovoltaic system. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
In one embodiment, fig. 5 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application, and as shown in fig. 5, an electronic device is provided, where the electronic device may be a server, and the internal structure diagram may be as shown in fig. 5. The electronic device comprises a processor, a network interface, an internal memory and a non-volatile memory connected by an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used for providing calculation and control capabilities, the network interface is used for communicating with an external terminal through network connection, the internal memory is used for providing an environment for an operating system and the running of a computer program, the computer program is executed by the processor to realize a power prediction method of the distributed photovoltaic system, and the database is used for storing data.
Those skilled in the art will appreciate that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application, and does not constitute a limitation on the electronic device to which the present application is applied, and a particular electronic device may include more or less components than those shown in the drawings, or may combine certain components, or have a different arrangement of components.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, the computer program may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of power prediction for a distributed photovoltaic system, the method comprising:
obtaining historical data, wherein the historical data comprises: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area;
preprocessing the historical data to obtain a historical data set of a target granularity, and segmenting the historical data set into a training set and a prediction set;
respectively training a pre-constructed XGboost model and a Bagging model through the training set;
predicting based on the prediction set respectively through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and performing linear combination on the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system.
2. The method of claim 1, wherein preprocessing the historical data comprises:
judging whether the integrity rate of the historical data is smaller than a preset threshold value or not, if so,
performing data cleaning, data deduplication and abnormal value processing on the historical data to obtain a historical data set of the target granularity;
if not, after the historical data is subjected to data filling, data cleaning, data deduplication and abnormal value processing are carried out, and the historical data set of the target granularity is obtained.
3. The method of claim 2, wherein determining whether the completeness rate of the historical data is less than a preset threshold comprises:
searching the historical data at different moments from the historical data;
calculating the whole data missing rate of the historical data according to the historical data at different moments, and judging whether the whole rate of the historical data is smaller than a preset threshold value or not according to the whole data missing rate, wherein the preset threshold value is determined according to empirical knowledge in the field.
4. The method of claim 1, wherein after obtaining power prediction data for the distributed photovoltaic energy system, the method further comprises:
calculating an evaluation index according to the power prediction data, wherein the evaluation index is used for indicating the accuracy of the power prediction data and comprises the following steps: root mean square error, mean absolute error, correlation coefficient, and maximum prediction error.
5. The method according to claim 4, wherein the evaluation index is calculated by the following formula:
δ max ＝max(|P Mi -P Pi |)
wherein RMSE is the root mean square error, MAE is the mean absolute error, r is the correlation coefficient, δ max Is the maximum prediction error, n is the number of all samples, P Mi Is the actual power at time i, P Pi The predicted power at the ith moment, cap is the starting capacity of the photovoltaic power station,
is the average of the actual power of all samples,
is the average of all predicted power samples.
6. The method according to claim 1, wherein in the process of respectively training the XGboost model and the Bagging model through the training set, model input is defined as numerical weather in the training set, and model output is defined as photovoltaic power at a predicted time point.
7. A power prediction system for a distributed photovoltaic system, the system comprising: the device comprises an acquisition module, a preprocessing module, a model training module and a prediction module, wherein:
the obtaining module is configured to obtain historical data, where the historical data includes: historical photovoltaic power of the distributed photovoltaic system and historical numerical weather in the target area;
the preprocessing module is used for preprocessing the historical data to obtain a historical data set of target granularity and segmenting the historical data set into a training set and a prediction set;
the model training module is used for respectively training a pre-constructed XGboost model and a Bagging model through the training set;
the prediction module is used for predicting based on the prediction set through the trained XGboost model and the trained Bagging model to obtain first prediction data and second prediction data reflecting photovoltaic power, and performing linear combination on the first prediction data and the second prediction data to obtain power prediction data of the distributed photovoltaic system.
8. The system of claim 7, wherein the pre-processing module to perform pre-processing on the historical data comprises:
judging whether the integrity rate of the historical data is smaller than a preset threshold value or not, if so,
performing data cleaning, data deduplication and abnormal value processing on the historical data to obtain a historical data set of the target granularity;
if not, after the historical data is subjected to data filling, data cleaning, data deduplication and abnormal value processing are carried out, and the historical data set of the target granularity is obtained.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210807589.0A CN115358515A (en) | 2022-07-07 | 2022-07-07 | Power prediction method and system for distributed photovoltaic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210807589.0A CN115358515A (en) | 2022-07-07 | 2022-07-07 | Power prediction method and system for distributed photovoltaic system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115358515A true CN115358515A (en) | 2022-11-18 |
Family
ID=84031639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210807589.0A Pending CN115358515A (en) | 2022-07-07 | 2022-07-07 | Power prediction method and system for distributed photovoltaic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358515A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116316617A (en) * | 2023-05-26 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Multi-station intelligent fusion new energy generation power region prediction method and system |
-
2022
- 2022-07-07 CN CN202210807589.0A patent/CN115358515A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116316617A (en) * | 2023-05-26 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Multi-station intelligent fusion new energy generation power region prediction method and system |
| CN116316617B (en) * | 2023-05-26 | 2023-09-15 | 南方电网数字电网研究院有限公司 | Multi-station intelligent fusion new energy generation power region prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | An edge computing framework for real-time monitoring in smart grid | |
| CN110492480B (en) | Power distribution network topology identification method and device, computer equipment and readable storage medium | |
| Yan et al. | Wind power grouping forecasts and its uncertainty analysis using optimized relevance vector machine | |
| CN112488395A (en) | Power distribution network line loss prediction method and system | |
| CN110929954A (en) | Load prediction method, load prediction device, computer equipment and storage medium | |
| CN104200288A (en) | Equipment fault prediction method based on factor-event correlation recognition | |
| CN111080072A (en) | Distribution transformer health index evaluation method, device and system | |
| CN114988241B (en) | Elevator energy consumption on-line monitoring analysis system | |
| CN115358515A (en) | Power prediction method and system for distributed photovoltaic system | |
| CN107527121A (en) | A kind of method of the information system running status diagnosis prediction of power network | |
| CN106849064B (en) | Regional power grid load prediction management system based on meteorological data | |
| CN103617447A (en) | Evaluation system and method for intelligent substation | |
| WO2023050534A1 (en) | Method and device for predicting energy consumption of rail transit station apparatus, and apparatus and storage medium | |
| CN112926863B (en) | Six-large-early-warning-center-based comprehensive power grid disaster monitoring system | |
| CN114357670A (en) | Power distribution network power consumption data abnormity early warning method based on BLS and self-encoder | |
| WO2024056050A1 (en) | Massive flexible load rapid aggregation control method and apparatus | |
| CN117200352A (en) | Photovoltaic power generation regulation and control method and system based on cloud edge fusion | |
| CN115529315B (en) | Cloud edge cooperative system | |
| CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
| CN115062847A (en) | Carbon fiber heating energy consumption prediction method and system based on logistic regression algorithm | |
| CN112531679A (en) | Load measuring characteristic big data monitoring equipment and monitoring method | |
| CN111626494A (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| CN112330003B (en) | Periodic capacity data prediction method, system and storage medium based on bidirectional cyclic neural network | |
| CN112132325B (en) | Power transmission line current-carrying capacity quota assessment method and device considering weather confidence | |
| CN117081088B (en) | Power grid load dispatching control method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |