CN118195056A - Charging station load prediction method and device, electronic equipment and storage medium - Google Patents
Charging station load prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118195056A CN118195056A CN202410145362.3A CN202410145362A CN118195056A CN 118195056 A CN118195056 A CN 118195056A CN 202410145362 A CN202410145362 A CN 202410145362A CN 118195056 A CN118195056 A CN 118195056A
- Authority
- CN
- China
- Prior art keywords
- historical
- charging
- prediction
- result
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 230000008859 change Effects 0.000 claims abstract description 31
- 230000007774 longterm Effects 0.000 claims abstract description 13
- 230000015654 memory Effects 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 18
- 238000012886 linear function Methods 0.000 claims description 12
- 230000000737 periodic effect Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 230000002068 genetic effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 11
- 238000012549 training Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000035772 mutation Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000010076 replication Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a charging station load prediction method, a charging station load prediction device, electronic equipment and a storage medium, wherein the charging station load prediction method comprises the following steps: acquiring historical charging load data and historical meteorological factor data of a charging station; inputting historical charging load data into a first prediction model, determining the change trend and periodicity of charging station load, and outputting a first prediction result; inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term dependence of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result; and determining weights of the first predicted result and the second predicted result, and determining a final predicted result according to the first predicted result, the second predicted result, the weights of the first predicted result and the weights of the second predicted result. And the final prediction result comprehensively considers the influence of various load factors, so that the prediction precision is higher.
Description
Technical Field
The present application relates to the field of charging load prediction technologies, and in particular, to a charging station load prediction method, a charging station load prediction device, an electronic device, and a storage medium.
Background
The process of electric automobile industrialization is steadily accelerated, the construction of charging infrastructure becomes the important development in the future, and the growth space of the electric automobile charging industry in the future is huge, so that the running pressure of a power grid is gradually increased.
In the related art, the method for predicting the load of the electric vehicle charging station is low in precision, and the future charging load condition cannot be predicted accurately, so that a certain difficulty is brought to planning and construction of a charging infrastructure. Therefore, the load prediction precision of the electric vehicle charging station is improved, and the method has important significance for making reasonable charging station/pile construction planning, ensuring the running safety and stability of the electric power system and improving the economic benefit and social benefit of the charging station.
Disclosure of Invention
In view of the above, an object of the present application is to provide a charging station load prediction method, apparatus, electronic device, and storage medium that solve or at least partially solve the above problems.
Based on the above object, a first aspect of the present application provides a charging station load prediction method, including:
Acquiring historical charging load data and historical meteorological factor data of a charging station;
Inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load, and outputting a first prediction result;
Inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term dependence of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result;
And determining weights of the first predicted result and the second predicted result, and determining a final predicted result according to the first predicted result, the second predicted result, the weights of the first predicted result and the weights of the second predicted result.
Optionally, the historical charging load data includes a charging date and a charging amount corresponding to the charging date;
inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load, and outputting a first prediction result, wherein the method comprises the following steps:
capturing a periodic variation of the charge amount with the charge date in the historical charge load data;
capturing holiday variation of the charge amount with the charge date in the historical charge load data;
And according to the periodic change and the holiday change, determining a linear function of the charge quantity along with the charging date, and determining the change trend of the charge quantity along with the charging date.
Optionally, the second prediction model at least comprises a long-term and short-term memory network layer and a full-connection layer;
inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term dependence relationship of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result, wherein the method comprises the following steps of:
establishing a connection relationship for the historical charging load data and the historical meteorological data based on the full connection layer;
And processing the connection relation based on the long-short-term memory network layer to obtain the long-term dependency relation of the historical charging data and the historical meteorological data.
Optionally, determining the weights of the first prediction result and the second prediction result includes:
randomly generating an initial population of weights for the first predictor;
Utilizing the error of the final prediction result as a fitness function of individuals in the initial population;
according to the fitness function, carrying out iterative computation on individuals in an initial population of the weight of the first prediction result by utilizing a genetic algorithm until the preset iteration times are reached, and determining that the individual with the minimum fitness function in the current population is the weight of the first prediction result;
And obtaining the weight of the second predicted result through the weight of the first predicted result.
Optionally, the fitness function is expressed as:
Where h represents the charging days of the charging station, y t represents the true charging station load result, Representing the final prediction result.
Optionally, the method further comprises:
calculating root mean square error according to the real charging load result and the final prediction result;
calculating an average absolute percentage error according to the real charging load result and the final prediction result;
and determining the accuracy of the final prediction result according to the root mean square error and the average absolute percentage error.
Alternatively, the root mean square error is expressed as:
the mean absolute percentage error is expressed as:
Wherein RMSE represents root mean square error, MAPE represents mean absolute percentage error, T represents predicted start time, h represents charging days of the charging station, T represents predicted initial days, Representing the final predicted result, y t represents the actual charging station load result.
In a second aspect of the present application, there is provided a charging station load prediction apparatus comprising:
the acquisition module is used for acquiring historical charging load data and historical meteorological factor data of the charging station;
the first prediction module is used for inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load and outputting a first prediction result;
The second prediction module is used for inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term relation between the historical charging load data and the historical meteorological factor data and outputting a second prediction result;
And the final prediction module is used for determining the weights of the first prediction result and the second prediction result, and determining a final prediction result according to the first prediction result, the second prediction result, the weights of the first prediction result and the weights of the second prediction result.
In a third aspect the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to the first aspect when executing the program.
In a fourth aspect of the application, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect.
From the above, it can be seen that the charging station load prediction method, the device, the electronic equipment and the storage medium provided by the application utilize the first prediction model to determine the variation trend and periodicity of the charging station load, thereby determining the linear relation of the historical charging load data, obtaining the first prediction result, utilize the second prediction model to determine the nonlinear relation of the historical charging load data and the historical meteorological factor data, obtaining the second prediction result, finally optimize the weights of the first prediction result and the second prediction result, obtaining the final prediction result, and comprehensively consider the influence of various load factors by the final prediction result, so that the prediction precision is higher.
Drawings
In order to more clearly illustrate the technical solutions of the present application or related art, the drawings that are required to be used in the description of the embodiments or related art will be briefly described below, and it is apparent that the drawings in the following description are only embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort to those of ordinary skill in the art.
FIG. 1 is a flowchart of a charging station load prediction method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a genetic algorithm for obtaining weights of a first prediction result according to an embodiment of the present application;
FIG. 3 is a schematic diagram showing comparison of final prediction results according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a charging station load prediction apparatus according to an embodiment of the present application;
Fig. 5 is a schematic diagram of an electronic device according to an embodiment of the application.
Detailed Description
The present application will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present application more apparent.
It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present application should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present application belongs. The terms "first," "second," and the like, as used in embodiments of the present application, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As described in the background art above, in the related art, regarding charging station load prediction, only the influence of time factors on the load is paid attention to, and it is generally assumed that charging station load changes have temporal continuity and periodicity, but in practice charging station load changes may be affected by various uncertain factors such as sudden weather changes, policy adjustments, and the like. These factors have a large impact on the load, but do not provide accurate predictions for variations in the factors to be determined.
In addition, the traditional charge load prediction depends on a probability model, and the charge rules of different regions are different, so that the probability model has larger randomness for the charge load prediction, and an accurate prediction result can not be provided. And under the condition that the prediction result of the charging station load is inaccurate, effective decision support cannot be provided for planning and management of the charging station.
Fig. 1 provides a flowchart of a charging station load prediction method according to one embodiment of the present application.
The method in fig. 1 aims at establishing the change trend and periodicity of the charging station load, adding historical weather factor data, strengthening the correlation between the historical charging load data and the historical weather factor data, obtaining a more accurate final prediction result, and providing powerful support for the optimal management of the power system and the reasonable distribution of power resources.
The charging station load prediction method provided by the embodiment of the application comprises the following steps:
s101, acquiring historical charging load data and historical meteorological factor data of the charging station.
According to the embodiment of the application, the change of the charging load along with time under the historical condition is fully considered through the historical charging load data of the charging station, and the linear relation between the charging load and time is determined for the first prediction model according to the historical charging load data. In addition, the historical meteorological factors are considered simultaneously, the correlation between the historical charging load data and the historical meteorological factor data is determined for the second prediction model according to the historical charging load data and the historical meteorological factor data, and the influence of the historical meteorological factors on the charging load in the linear relation of the charging load and time is considered.
It should be appreciated that the historical charging load data and the historical weather factor data of the charging station are preprocessed before being input into the first prediction model and the second prediction model, including cleaning, sorting and feature extraction of the historical charging load data and the historical weather factor data, including removing outliers, filling missing values, and normalizing the data, so as to obtain effective historical charging load data and historical weather factor data.
S102, inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load along with time, and outputting a first prediction result.
In some embodiments, the historical charge load data includes a charge date and a charge amount corresponding to the charge date. In this embodiment, the charging date can cover at least different seasons, so as to determine different period intervals, for example, the period intervals are from small to large, and different period intervals such as week, month, year can be determined, and the change trend and periodicity of the charging station load in different period interval ranges are defined, so as to obtain the first prediction result.
It can be understood that in the case that the charging date covers different seasons, different holidays are included, and the load change trend of the charging station on different holidays can be incorporated into the first prediction model, so that the change trend of the charging station load caused by different holidays can be predicted.
In some embodiments, step S102 includes:
The periodic variation of the charge amount with the charge date in the historical charge load data is captured. The change trend of the charge amount in the different cycle sections of the week, month, year, etc. is summarized according to the change of the charge amount with the charging date, for example, in the cycle section of the week, the change of the charge amount of each day in the week is determined, and thus the periodicity of the charge amount in the week is determined. The change in the charge amount per day or the charge amount per week over one month is determined with the month as the period interval, thereby determining the periodicity of the charge amount over one month. The change in the charge amount per day or the charge amount per week or the charge amount per month over the period of one year is determined with the year as the period interval, thereby determining the periodicity of the charge amount over the period of one year.
And then capturing holiday variation of the charge amount with the charge date in the historical charge load data. Different holiday time periods are different, the charge amount of the charging stations/piles on the expressway can be correspondingly increased in the holidays of different time periods, the charge amount of the charging stations/piles in the office area can be correspondingly reduced, and the change of the charge amount in the holidays of different time periods is determined according to the charge amounts in the holidays of different time periods.
And according to the periodic change and the holiday change, determining a linear function of the charge quantity along with the charging time, and determining the change trend of the charge quantity along with the charging date.
In this embodiment, the periodic variation of the charge amount with the charge date is determined using the charge date as a variable, the holiday variation of the charge amount with the charge date is determined, and the two are coupled, so that the linear function of the charge amount and the charge date can be determined, and the variation trend of the charge amount with the charge date is determined using the linear function of the charge amount and the charge date.
It may be appreciated that the first prediction model includes a linear function module, where the function module may be configured to perform visualization according to a charging date in the historical charging load data and a charging amount corresponding to the charging date, so as to calculate a linear function coupled according to a visualization result, so as to write the linear function into the linear function module. The training of the preset model may be performed directly by using the charging date and the charging amount corresponding to the charging date in the historical charging load data, and the training result obtained by training the preset model may be used as a linear function module, which is not particularly limited herein.
The input data of the first prediction model is a charging date and a charging amount, a prediction result of a specific date is set in the first prediction model, and the charging amount of the specific date is calculated as the first prediction result by using the determined linear function and is directly output.
Wherein the input data of the first predictive model is represented as:
Where d s represents the charge amount, d n represents the charge amount on the nth day, y represents the charge date, and y n represents the date on the nth day.
It can be understood that in the first prediction model, the first prediction result is obtained only by taking the charging date as a variable, that is, in the time sequence, the charging amount contains the influence of different weather factor data on the charging amount in different charging dates, but the first prediction result output by the first prediction model is not considered correspondingly, meanwhile, the events of the weather factor data in different charging dates are not determined, so that the weather factor data cannot be directly coupled into a linear function of the charging amount and the charging date, and the weather factor data is considered through the second prediction model.
And S103, inputting the historical charging data and the historical meteorological factor data into a second prediction model, determining the long-term dependence of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result.
In some embodiments, the second predictive model includes at least a long and short term memory network layer (LSTM layer) and a fully connected layer (Dense layer).
And establishing a connection relation for the historical charging load data and the historical meteorological data based on the full connection layer.
Optionally, the historical meteorological factor data includes temperature, humidity and rainfall.
As described by the above embodiment, the history charge load data includes the charge date and the charge amount corresponding to the charge date.
In some optional embodiments, in the process of training the second prediction model by taking the charging date and the charging amount in the historical charging load data and the temperature, the humidity and the rainfall in the historical meteorological data as input data, a full connection layer is utilized, according to the relevance of the historical charging load data and the historical meteorological data, the connection relation between the charging date and the charging amount and the temperature, the humidity and the rainfall is established, and meanwhile, the relevance degree of the connection relation can be clarified for different connection relations in the trained second prediction model. For example, the charge amount establishes a connection relationship with the temperature and the humidity, respectively, but the degree of association of the charge amount with the temperature is relatively large, and the degree of association with the humidity is relatively small, and then in the prediction process of the load of the charging station for the future, the influence of the predicted temperature on the charge amount in the output of the second prediction result is relatively large.
And processing the connection relation based on the long-short-term memory network layer to obtain the long-term dependency relation of the historical charging data and the historical meteorological data.
And establishing a long-term dependency relationship by utilizing a long-term and short-term memory network layer according to the connection relationship between the obtained historical charging load data and the historical meteorological factor data. That is, it can be understood that, in the training process of the second prediction model, the input historical charging load data and the historical meteorological factor data are also input based on time sequence arrangement, the long-short-term memory network layer increases along with the time sequence length, and the long-time dependency problem of the historical charging load data and the historical meteorological factor data is processed by utilizing the advantage of processing the long-time sequence gradient by utilizing the long-short-term memory network layer. And through the second prediction model, the nonlinear relation between the historical charging load data and the historical meteorological factor data can be determined.
In some alternative embodiments, the second predictive model may be a Long-short term memory network model (Long-Short Term Memory, LSTM), where the historical charge load data and the historical meteorological factor data are first arranged in a time series and according to 8: the ratio of 2 is divided into a training set and a testing set, the training set is used for training the long-period memory network model, and the testing set is used for evaluating the performance.
In some alternative embodiments, the second prediction model further includes a discarding layer (Dropout layer), and in order to prevent the second prediction model from over-fitting during training, some neurons are randomly discarded with a probability of 0.01 during each training, i.e. the historical charging load data and the redundant data in the historical meteorological factor data are randomly discarded.
S104, determining weights of the first predicted result and the second predicted result, and determining a final predicted result according to the first predicted result, the second predicted result, the weights of the first predicted result and the weights of the second predicted result.
Randomly generating an initial population of weights for the first predictor;
Utilizing the error of the final prediction result as a fitness function of the individuals in the initial population;
According to the fitness function, carrying out iterative computation on individuals in an initial individual group of the weight of the first prediction result by utilizing a genetic algorithm until the preset iteration times are reached, and determining that the individual with the smallest fitness function in the current group is the weight of the first prediction result;
And obtaining the weight of the second predicted result through the weight of the first predicted result.
The initial population of weights of the first predictor is located within the [0,1] interval, and individuals represented by the weights of the first predictor as variables are represented as binary strings of {0,1}, forming the initial population of individuals of weights of the first predictor.
Alternatively, the length of the individuals in the initial population of weights for the first predictor is 6. Optionally, the preset number of iterations is 50.
The first prediction model and the second prediction model are established by using historical charging station load data and/or historical meteorological factor data, so that correspondingly, for a real charging station load result with any time history based on the historical data, the error of the final prediction result is taken as a fitness function if the final prediction result is accurate.
In some embodiments, the fitness evaluation function is expressed as:
Where h represents the charging days of the charging station, y t represents the true charging station load result, Representing the final prediction result.
And when the fitness function is minimum, the error representing the final prediction result is minimum, namely the accuracy of the obtained final prediction result is highest. For example, if the fitness function is 0, then the final prediction result is the same as the real charging station load result, then the final prediction result is the most accurate.
Referring to fig. 2, when the genetic algorithm is used to perform iterative computation on individuals in the initial population of the weight of the first prediction result, three iterative methods of replication, exchange and mutation are performed respectively. In fig. 3, gen represents the number of iterations, i represents each individual in the population, and M represents the number of individuals in the population.
The replication iteration includes: and selecting one individual with the highest fitness in the initial population, copying the one individual with the highest fitness, adding a copying result to the new population, and deleting the one individual with the lowest fitness from the new population, wherein P-t represents selecting the one with the highest fitness.
The exchange iteration includes: two individuals are selected according to the fitness, partial genes of the two individuals are exchanged by adopting a random positioning method, the exchanged new individuals are added into the new population to replace the old individuals, for example, the individuals included in the initial population are represented as [1,1,0,0,1,0] and [0,0,0,1,0,0] by using binary representations, and the first gene in the first individual and the first gene in the second individual can be exchanged to obtain [0,1,0,0,1,0] and [1,0,0,1,0,0], wherein P-c represents the selection of the two individuals according to the fitness.
The mutation iteration includes: mutation is performed on individuals in the initial population, and the mutation results are added to the new population, where P-m represents performing the mutation. For example, the initial population includes individuals represented by binary representation [1,1,0,0,1,0], then a mutation is made to one of the positions, 1 becomes 0, or 0 becomes 1.
Repeating the steps of copying, exchanging and mutating iteration for the new population until the preset iteration times are reached, obtaining the current population, and determining the weight of the first prediction result of the individual with the minimum fitness function in the current population.
The sum of the weights of the first predicted result and the second predicted result is 1, and the second predicted result can be obtained through the weight of the first predicted result.
Optionally, the first prediction result has a weight of w 1 =0.567, and the second prediction result has a weight of w 2 =0.433.
And obtaining a final predicted result by using the first predicted result, the second predicted result, the weight of the first predicted result and the weight of the second predicted result, wherein the final predicted result is expressed as follows:
yt＝w1f1t+w2f2t，
Where f 1t denotes the first predictor and f 2t denotes the second predictor.
The final prediction results obtained by different models are shown in fig. 3, wherein the prediction precision of the propset model and the LSTM model is higher than that of the ARIMA model, and the prediction results of the propset model show that the propset model can basically achieve the change trend and the periodic effect of the real charging load, but the prediction curve is smoother, the fluctuation frequency is lower, and the real data is difficult to fit closely at a specific point; the single LSTM model prediction curve has higher fluctuation frequency and higher fitting precision in a single data point, but the prediction curve is more oscillating and has certain hysteresis. The model prediction curve fluctuation can fit the true practical power trend, the approach fitting effect can be realized on a single data point, and the accuracy of the charging station load prediction result is improved.
In some embodiments, the present application evaluates the final prediction result, including:
And calculating the root mean square error according to the real charging load result and the final prediction result.
Root mean square error is expressed as:
And calculating an average absolute percentage error according to the real charging load result and the final prediction result.
The mean absolute percentage error is expressed as:
Wherein T represents a predicted start time, h represents a charging day of the charging station, T represents a predicted initial day, Representing the final predicted result, y t represents the actual charging station load result.
And determining the accuracy of the final prediction result according to the root mean square error and the average absolute percentage error.
And if the accuracy of the final prediction result is determined to be within the error range, the prediction result is sorted and visualized, and decision service is provided for planning and management of the charging station.
It should be noted that, the method of the embodiment of the present application may be performed by a single device, for example, a computer or a server. The method of the embodiment can also be applied to a distributed scene, and is completed by mutually matching a plurality of devices. In the case of such a distributed scenario, one of the devices may perform only one or more steps of the method of an embodiment of the present application, the devices interacting with each other to accomplish the method.
It should be noted that the foregoing describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Based on the same technical conception, the application also provides a charging station load prediction device corresponding to the method in any embodiment.
Referring to fig. 4, the charging station load prediction apparatus includes:
An acquisition module 41, configured to acquire historical charging load data and historical meteorological factor data of a charging station;
the first prediction module 42 is configured to input historical charging load data into a first prediction model, determine a change trend and periodicity of a charging station load, and output a first prediction result;
A second prediction module 43, configured to input the historical charging load data and the historical weather factor data into a second prediction model, determine a long-term relationship between the historical charging load data and the historical weather factor data, and output a second prediction result;
The final prediction module 44 is configured to determine weights of the first prediction result and the second prediction result, and determine a final prediction result according to the first prediction result, the second prediction result, the weights of the first prediction result, and the weights of the second prediction result.
For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, the functions of each module may be implemented in the same piece or pieces of software and/or hardware when implementing the present application.
The device of the foregoing embodiment is configured to implement the corresponding charging station load prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same technical concept, the application also provides an electronic device corresponding to the method in any embodiment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the charging station load prediction method in any embodiment when executing the program.
Fig. 5 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 implement communication connections therebetween within the device via a bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit ), a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits, etc. for executing related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage, dynamic storage, etc. Memory 1020 may store an operating system and other application programs, and when the embodiments of the present specification are implemented in software or firmware, the associated program code is stored in memory 1020 and executed by processor 1010.
The input/output interface 1030 is used to connect with an input/output module for inputting and outputting information. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
Communication interface 1040 is used to connect communication modules (not shown) to enable communication interactions of the present device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 1050 includes a path for transferring information between components of the device (e.g., processor 1010, memory 1020, input/output interface 1030, and communication interface 1040).
It should be noted that although the above-described device only shows processor 1010, memory 1020, input/output interface 1030, communication interface 1040, and bus 1050, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
The electronic device of the foregoing embodiment is configured to implement the corresponding charging station load prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which is not described herein.
Based on the same technical concept, the present application also provides a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the charging station load prediction method according to any of the above embodiments, corresponding to the method according to any of the above embodiments.
The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
The storage medium of the above embodiment stores computer instructions for causing the computer to execute the charging station load prediction method according to any one of the above embodiments, and has the advantages of the corresponding method embodiments, which are not described herein.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the application (including the claims) is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the application, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the application as described above, which are not provided in detail for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the embodiments of the present application. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the embodiments of the present application, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the present application are to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, and the like, which are within the spirit and principles of the embodiments of the application, are intended to be included within the scope of the application.
Claims (10)
1. A charging station load prediction method, comprising:
Acquiring historical charging load data and historical meteorological factor data of a charging station;
Inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load, and outputting a first prediction result;
Inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term dependence of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result;
And determining weights of the first predicted result and the second predicted result, and determining a final predicted result according to the first predicted result, the second predicted result, the weights of the first predicted result and the weights of the second predicted result.
2. The method according to claim 1, wherein the historical charge load data includes a charge date and a charge amount corresponding to the charge date;
inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load, and outputting a first prediction result, wherein the method comprises the following steps:
capturing a periodic variation of the charge amount with the charge date in the historical charge load data;
capturing holiday variation of the charge amount with the charge date in the historical charge load data;
And according to the periodic change and the holiday change, determining a linear function of the charge quantity along with the charging date, and determining the change trend of the charge quantity along with the charging date.
3. The method of claim 1, wherein the second predictive model includes at least a long-short term memory network layer and a fully connected layer;
inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term dependence relationship of the historical charging load data and the historical meteorological factor data, and outputting a second prediction result, wherein the method comprises the following steps of:
establishing a connection relationship for the historical charging load data and the historical meteorological data based on the full connection layer;
And processing the connection relation based on the long-short-term memory network layer to obtain the long-term dependency relation of the historical charging data and the historical meteorological data.
4. The method of claim 1, wherein determining weights for the first predictor and the second predictor comprises:
randomly generating an initial population of weights for the first predictor;
Utilizing the error of the final prediction result as a fitness function of individuals in the initial population;
according to the fitness function, carrying out iterative computation on individuals in an initial population of the weight of the first prediction result by utilizing a genetic algorithm until the preset iteration times are reached, and determining that the individual with the minimum fitness function in the current population is the weight of the first prediction result;
And obtaining the weight of the second predicted result through the weight of the first predicted result.
5. The method of claim 4, wherein the fitness function is expressed as:
Where h represents the charging days of the charging station, y t represents the true charging station load result, Representing the final prediction result.
6. The method as recited in claim 1, further comprising:
calculating root mean square error according to the real charging load result and the final prediction result;
calculating an average absolute percentage error according to the real charging load result and the final prediction result;
and determining the accuracy of the final prediction result according to the root mean square error and the average absolute percentage error.
7. The method of claim 6, wherein the root mean square error is expressed as:
the mean absolute percentage error is expressed as:
Wherein RMSE represents root mean square error, MAPE represents mean absolute percentage error, T represents predicted start time, h represents charging days of the charging station, T represents predicted initial days, Representing the final predicted result, y t represents the actual charging station load result.
8. A charging station load prediction apparatus, comprising:
the acquisition module is used for acquiring historical charging load data and historical meteorological factor data of the charging station;
the first prediction module is used for inputting the historical charging load data into a first prediction model, determining the change trend and periodicity of the charging station load and outputting a first prediction result;
The second prediction module is used for inputting the historical charging load data and the historical meteorological factor data into a second prediction model, determining the long-term relation between the historical charging load data and the historical meteorological factor data and outputting a second prediction result;
And the final prediction module is used for determining the weights of the first prediction result and the second prediction result, and determining a final prediction result according to the first prediction result, the second prediction result, the weights of the first prediction result and the weights of the second prediction result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 7 when the program is executed by the processor.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410145362.3A CN118195056A (en) | 2024-02-01 | 2024-02-01 | Charging station load prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410145362.3A CN118195056A (en) | 2024-02-01 | 2024-02-01 | Charging station load prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118195056A true CN118195056A (en) | 2024-06-14 |
Family
ID=91395515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410145362.3A Pending CN118195056A (en) | 2024-02-01 | 2024-02-01 | Charging station load prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118195056A (en) |
-
2024
- 2024-02-01 CN CN202410145362.3A patent/CN118195056A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107506868B (en) | Method and device for predicting short-time power load | |
| CN110517479B (en) | Urban road traffic prediction method and device and electronic equipment | |
| CN109214436A (en) | A kind of prediction model training method and device for target scene | |
| CN111091196B (en) | Passenger flow data determination method and device, computer equipment and storage medium | |
| CN114493050B (en) | Multi-dimensional fusion new energy power parallel prediction method and device | |
| CN112396231B (en) | Modeling method and device for space-time data, electronic equipment and readable medium | |
| CN113918884A (en) | Traffic prediction model construction method and traffic prediction method | |
| Hawelka et al. | Collective prediction of individual mobility traces for users with short data history | |
| CN112668238A (en) | Rainfall processing method, device, equipment and storage medium | |
| CN116091118A (en) | Electricity price prediction method, device, equipment, medium and product | |
| CN113253336B (en) | Earthquake prediction method and system based on deep learning | |
| Anh et al. | Effect of gradient descent optimizers and dropout technique on deep learning LSTM performance in rainfall-runoff modeling | |
| Ghassemi et al. | Optimal surrogate and neural network modeling for day-ahead forecasting of the hourly energy consumption of university buildings | |
| CN117350336A (en) | Charging load prediction and model training method, device, equipment and storage medium | |
| CN116960962A (en) | Mid-long term area load prediction method for cross-area data fusion | |
| CN118195056A (en) | Charging station load prediction method and device, electronic equipment and storage medium | |
| CN113723712B (en) | Wind power prediction method, system, equipment and medium | |
| CN111931994A (en) | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof | |
| CN117435870B (en) | Load data real-time filling method, system, equipment and medium | |
| CN116227249B (en) | New energy long-term electric quantity prediction method and system for intelligent migration of power meteorological data | |
| CN116646923A (en) | Method, device, terminal and storage medium for predicting medium and long term power load | |
| CN116128566A (en) | Price prediction method, price prediction device, electronic equipment and storage medium | |
| CN116029447A (en) | Predictive model training method and device, medium and computer equipment | |
| CN118153737A (en) | Method and device for predicting line loss of power distribution network | |
| Tang et al. | Forecasting individual bids in real electricity markets through machine learning framework |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |