A short-term electric vehicle charging load prediction method, system, terminal and medium

Abstract

This invention discloses a short-term electric vehicle charging load prediction method, system, terminal, and medium, relating to the field of electric vehicle charging load prediction technology. The key technical points are: a short-term electric vehicle charging load prediction method that constructs a Holt-Winter model for electric vehicle charging load prediction based on historical charging load data of electric vehicles, and optimizes the Holt-Winter model using a charging load data sequence composed of charging load data from the previous few cycles in the historical charging load data of electric vehicles, obtaining an electric vehicle charging load prediction model for short-term electric vehicle charging load prediction. This achieves the goal of using the electric vehicle charging load prediction model to predict the load of electric vehicles in real time over a future period, thereby improving the real-time performance of electric vehicle load prediction.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging load prediction technology, and more specifically, to a short-term electric vehicle charging load prediction method, system, terminal, and medium. Background Technology

[0002] Electric vehicle (EV) charging and discharging load forecasting is fundamental for conducting research on the impact of EV integration on the power grid, distribution network planning and control operation, two-way interaction between EVs and the power grid, and coordination between EVs and other energy and transportation systems. Short-term EV load forecasting refers to predicting the charging load curve for the next few hours. It can be applied to the planning, configuration, and real-time scheduling of EV charging stations, reducing adverse impacts on the power grid and providing further power supply support. It is of great significance to the development of EVs and the safe and stable operation of the distribution network.

[0003] Currently, research on electric vehicle charging load prediction mainly focuses on probabilistic statistical Monte Carlo simulation methods and some artificial intelligence methods, which have a certain lag in the prediction process. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, terminal, and medium for short-term electric vehicle charging load forecasting. Based on historical charging load data of electric vehicles, a Holt-Winter model for electric vehicle charging load forecasting is constructed. The Holt-Winter model is then optimized using a charging load data sequence composed of charging load data from the previous few cycles in the historical charging load data of electric vehicles, resulting in an electric vehicle charging load forecasting model for short-term electric vehicle charging load forecasting. This achieves the goal of using the electric vehicle charging load forecasting model to predict the load of electric vehicles in real time over a future period, thereby improving the real-time performance of electric vehicle load forecasting.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0006] A short-term electric vehicle charging load forecasting method includes the following steps:

[0007] Based on the historical charging load data of the target object, a Holt-Winter model for predicting the charging load of the target object is constructed;

[0008] The charging load data of the first n periods are selected from the historical charging load data to form a charging load data sequence;

[0009] Based on the charging load data sequence, the Holt-Winter model is optimized to obtain the charging load prediction model for the target object;

[0010] The charging load of the target object is predicted using a target object charging load prediction model.

[0011] Furthermore, the process of constructing the Holt-Winter model for predicting the charging load of the target object is as follows:

[0012] Obtain the model parameters for constructing the Holt-Winter model from the historical charging load data of the target object;

[0013] Based on the model parameters of the Holt-Winter model, a Holt-Winter model for predicting the charging load of the target object is constructed.

[0014] The model parameters include the stable component, trend component, and seasonal component of the target object's historical charging load data.

[0015] Furthermore, the model parameters of the Holt-Winter model are optimized using the mean absolute percentage error.

[0016] Furthermore, the Holt-Winter model is... In the formula, a t b is the stable component in the historical charging load data of electric vehicles at time t. t S represents the trend component in the historical charging load data of electric vehicles at time t. t-l-k The seasonal component in the historical charging load data of electric vehicles at time tlk. Let t+k be the predicted electric vehicle charging load, k be the time to be predicted, and l be the length of the season.

[0017] Furthermore, the optimization of the Holt-Winter model includes:

[0018] The first optimization process includes...

[0019] The charging load data of the first period and the charging load data of the second period in the charging load data sequence are selected as feature data.

[0020] Based on the feature data, the initial stable component, trend component, and seasonal component of the charging load data sequence are obtained;

[0021] Based on the initial stable component, trend component, and seasonal component of the charging load data sequence, the model parameters of the Holt-Winter model are optimized for the first time using an optimization algorithm, resulting in the Holt-Winter model after the first optimization.

[0022] Furthermore, the optimization of the Holt-Winter model also includes:

[0023] The second optimization process includes...

[0024] Select charging load data from any period in the charging load data sequence;

[0025] Based on the charging load data of any period in the charging load data sequence, the stable component, trend component and seasonal component of any period in the charging load data sequence are obtained.

[0026] Based on the stable component, trend component, and seasonal component of any period in the charging load data sequence, the model parameters of the Holt-Winter model are optimized a second time using an optimization algorithm to obtain the charging load prediction model for the target object.

[0027] Furthermore, the particle swarm optimization algorithm is used to optimize the model parameters of the Holt-Winter model.

[0028] A short-term electric vehicle charging load prediction system includes: a construction module for constructing a Holt-Winter model for predicting the charging load of a target object based on historical charging load data of the target object; an extraction module for selecting charging load data from the previous n periods from the historical charging load data to form a charging load data sequence; an optimization module for optimizing the Holt-Winter model based on the charging load data sequence to obtain a charging load prediction model for the target object; and a prediction module for predicting the charging load of the target object using the charging load prediction model for the target object.

[0029] An electronic terminal includes: a memory for storing a computer program; and a processor for executing the computer program stored in the memory to enable the electronic terminal to perform the aforementioned short-term electric vehicle charging load prediction method.

[0030] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned short-term electric vehicle charging load prediction method.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] ① A short-term electric vehicle charging load forecasting method is proposed. Based on historical charging load data of electric vehicles, a Holt-Winter model for electric vehicle charging load forecasting is constructed. The Holt-Winter model is then optimized using a charging load data sequence composed of charging load data from the previous few cycles in the historical charging load data of electric vehicles. This results in an electric vehicle charging load forecasting model for short-term electric vehicle charging load forecasting, thereby improving the real-time performance of electric vehicle load forecasting.

[0033] ② Based on the Holt-Winter model after the first optimization, the stable component, trend component, and seasonal component used in the second optimization of the Holt-Winter model are calculated to improve the accuracy of the initial components of the Holt-Winter model, thereby reducing the impact of the initial value of electric vehicle charging load on the objective function of parameter optimization and improving the accuracy of prediction results.

[0034] ③ A Holt-Winter parameter model is established based on the minimum mean absolute percentage error. The optimal parameters obtained by solving the Holt-Winter model are solved by an optimization algorithm. When implementing short-term electric vehicle load forecasting, the parameter optimization process can be simple, easy to implement, and converge quickly. Attached Figure Description

[0035] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0036] Figure 1 This is a schematic diagram of a short-term electric vehicle charging load prediction method in this embodiment;

[0037] Figure 2 This is the original charging load curve of the electric vehicle in this embodiment;

[0038] Figure 3 This is the electric vehicle charging load curve predicted by a short-term electric vehicle charging load prediction method in this embodiment. Detailed Implementation

[0039] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0040] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0041] Example: Figures 1-3 As shown, a method, system, terminal and medium for predicting short-term electric vehicle charging load are presented.

[0042] like Figure 1As shown, a short-term electric vehicle charging load forecasting method includes the following steps: constructing a Holt-Winter model for forecasting the charging load of the target object based on historical charging load data of the target object; selecting charging load data from the first n periods of the historical charging load data to form a charging load data sequence; optimizing the Holt-Winter model based on the charging load data sequence to obtain a charging load forecasting model for the target object; and using the charging load forecasting model for the target object to forecast the charging load of the target object. Specifically, the process of constructing the Holt-Winter model for forecasting the charging load of the target object involves: obtaining model parameters for constructing the Holt-Winter model from the historical charging load data of the target object; constructing the Holt-Winter model for forecasting the charging load of the target object based on the model parameters of the Holt-Winter model; wherein the model parameters include stable components, trend components, and seasonal components in the historical charging load data of the target object.

[0043] The target object mentioned above is electric vehicles, and the historical charging load data of the target object is the historical charging load data Y of electric vehicles. Based on the historical charging load data Y of electric vehicles, the estimation formula for the model parameters of the Holt-Winter model is as follows: b t =β(a t -a t-1 )+(1-β)b t-1 ; In the formula, a t b is the stable component in the historical charging load data of electric vehicles at time t. t S represents the trend component in the historical charging load data of electric vehicles at time t. t Y represents the seasonal component of the historical charging load data of electric vehicles at time t. t For time t, the historical charging load data of electric vehicles is given, and α,β,γ∈[0,1] are smoothing parameters;

[0044] The Holt-Winter model is In the formula, a t b is the stable component in the historical charging load data of electric vehicles at time t. t S represents the trend component in the historical charging load data of electric vehicles at time t. t-l-k The seasonal component in the historical charging load data of electric vehicles at time tlk. Let t+k be the predicted electric vehicle charging load, k be the time to be predicted, and l be the length of the season.

[0045] The model parameters of the Holt-Winter model are optimized using the mean absolute percentage error.

[0046] Specifically: the objective function for parameter optimization is the mean absolute percentage error. In the formula, N is the total number of charging load moments.

[0047] The optimization of the Holt-Winter model includes: a first optimization process, which includes selecting charging load data from the first period and the second period of the charging load data sequence as feature data; obtaining the initial stable component, trend component, and seasonal component of the charging load data sequence based on the feature data; and using an optimization algorithm to perform a first optimization of the model parameters of the Holt-Winter model based on the initial stable component, trend component, and seasonal component of the charging load data sequence, thereby obtaining the Holt-Winter model after the first optimization.

[0048] Specifically: Select the charging load data of the first n periods of the historical charging load data Y of electric vehicles to form the charging load data sequence y = Y. nl-t (t = 1, 2, ..., nl);

[0049] Select the first two periods of the charging load data sequence y, and calculate the charging load data sequence y.

[0050] Initial stable components

[0051] Initial trend components

[0052] Seasonal ingredients:

[0053] The seasonal components at each moment in the first cycle are:

[0054] The seasonal components at each moment in the second cycle are:

[0055] The initial formula for calculating seasonal components is:

[0056] Among them, y i The i-th component of the charging load data sequence y, y j The j-th component of the charging load data sequence y is S. j ′ represents the seasonal component at time j within the first period, S j "" represents the seasonal component at time j within the second cycle.

[0057] Using the particle swarm optimization algorithm, the model parameters of the Holt-Winter model are optimized by taking advantage of the initial stable, trend, and seasonal components of the charging load data sequence y, combined with the parameter optimization objective function, to obtain the Holt-Winter model after the first optimization.

[0058] The optimization of the Holt-Winter model further includes: a second optimization process, which includes selecting charging load data for any period in the charging load data sequence; obtaining the stable component, trend component, and seasonal component of the charging load data for any period in the charging load data sequence based on the charging load data for any period in the charging load data sequence; and using an optimization algorithm to perform a second optimization of the model parameters of the Holt-Winter model based on the stable component, trend component, and seasonal component of the charging load data sequence to obtain the target charging load prediction model. The model parameters of the Holt-Winter model are further optimized using a particle swarm optimization algorithm.

[0059] like Figure 2 The image shows the original charging load curve of the electric vehicle. Figure 3 The electric vehicle charging load curve is predicted using a short-term electric vehicle charging load prediction method in this embodiment.

[0060] Depend on Figure 2 and Figure 3 The comparison shows that the short-term electric vehicle charging load prediction method provided in this embodiment does not eliminate data with regularity when filtering out random fluctuation components, and can track the changing trend of the load curve well. Its average absolute percentage error is 7.13%, which shows good prediction effect.

[0061] In summary, the short-term electric vehicle charging load forecasting method provided in this embodiment has the following beneficial effects: ① Based on historical charging load data of electric vehicles, a Holt-Winter model for electric vehicle charging load forecasting is constructed. The Holt-Winter model is then optimized using a charging load data sequence composed of charging load data from the previous few cycles in the historical charging load data, resulting in an electric vehicle charging load forecasting model for short-term electric vehicle charging load forecasting. This achieves the goal of real-time forecasting of electric vehicle load over a future period using the electric vehicle charging load forecasting model, thereby improving the real-time performance of electric vehicle load forecasting. ② Based on the first optimized Holt-Winter model, the stable component, trend component, and seasonal component used in the second optimized Holt-Winter model are calculated. This improves the accuracy of the initial components of the Holt-Winter model, thereby reducing the impact of the initial value of the electric vehicle charging load on the parameter optimization objective function, and thus improving the accuracy of the forecast results. ③ A Holt-Winter parameter model is established based on the minimum mean absolute percentage error. The optimal parameters obtained by solving the Holt-Winter model through an optimization algorithm are then used. This makes the parameter optimization process simple, easy to implement, and fast in converging when implementing short-term electric vehicle load forecasting.

[0062] This embodiment also provides a short-term electric vehicle charging load prediction system. This short-term electric vehicle charging load prediction system and the optimization method of the above embodiment belong to the same inventive concept. Therefore, the principle of the optimization system in this embodiment in solving the problem is the same. Figure 1 The method shown is similar to a short-term electric vehicle charging load forecasting method; therefore, the implementation of these optimization systems can be found in [reference needed]. Figure 1 An embodiment of a short-term electric vehicle charging load forecasting method is shown. This short-term electric vehicle charging load forecasting system includes: a construction module for constructing a Holt-Winter model for forecasting the charging load of a target object based on historical charging load data; an extraction module for selecting charging load data from the previous n periods from the historical charging load data to form a charging load data sequence; an optimization module for optimizing the Holt-Winter model based on the charging load data sequence to obtain a target object charging load forecasting model; and a forecasting module for predicting the charging load of the target object using the target object charging load forecasting model.

[0063] This embodiment also provides an electronic terminal, including: a memory for storing a computer program; and a processor for executing the computer program stored in the memory, so that the electronic terminal executes the aforementioned short-term electric vehicle charging load prediction method.

[0064] Specifically, the electronic terminal includes one or more processors, and a memory coupled to the processors for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the steps of the power system structure optimization method described in the above embodiments. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions in a computer storage medium to realize the corresponding method flow or corresponding function. The processor described in the embodiments of the present invention can be used to execute the operation of a power system structure optimization method.

[0065] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned short-term electric vehicle charging load prediction method.

[0066] Specifically, the computer-readable storage medium is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor; these instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the power system structure optimization method in the above embodiments. Those skilled in the art should understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A short-term electric vehicle charging load prediction method characterized by, Includes the following steps: Based on the historical charging load data of the target object, a Holt-Winter model for predicting the charging load of the target object is constructed; The charging load data of the first n periods are selected from the historical charging load data to form a charging load data sequence; Based on the charging load data sequence, the Holt-Winter model is optimized to obtain the charging load prediction model for the target object; Predict the charging load of the target object using a target object charging load prediction model; The process of constructing the Holt-Winter model for predicting the charging load of the target object is as follows: Obtain the model parameters for constructing the Holt-Winter model from the historical charging load data of the target object; Based on the model parameters of the Holt-Winter model, a Holt-Winter model for predicting the charging load of the target object is constructed. The model parameters include the stable component, trend component, and seasonal component of the historical charging load data of the target object; The optimization of the Holt-Winter model includes: The first optimization process includes... The charging load data of the first period and the charging load data of the second period in the charging load data sequence are selected as feature data. Based on the feature data, the initial stable component, trend component, and seasonal component of the charging load data sequence are obtained; Based on the initial stable component, trend component and seasonal component of the charging load data sequence, the model parameters of the Holt-Winter model are optimized for the first time using an optimization algorithm, resulting in the Holt-Winter model after the first optimization. The optimization of the Holt-Winter model also includes: The second optimization process includes... Select charging load data from any period in the charging load data sequence; Based on the charging load data of any period in the charging load data sequence, the stable component, trend component and seasonal component of any period in the charging load data sequence are obtained. Based on the stable component, trend component, and seasonal component of any period in the charging load data sequence, the model parameters of the Holt-Winter model are optimized a second time using an optimization algorithm to obtain the charging load prediction model for the target object.

2. The short-term electric vehicle charging load forecasting method according to claim 1, characterized in that: The model parameters of the Holt-Winter model are optimized using the mean absolute percentage error.

3. The short-term electric vehicle charging load prediction method according to claim 1, characterized in that: The Holt-Winter model is In the formula, For a moment The stable component in historical charging load data of electric vehicles For a moment Trend components in historical charging load data for electric vehicles For a moment Seasonal component in historical charging load data for electric vehicles for Forecast values ​​of electric vehicle charging load at any time For the time that needs to be predicted, The length of a season.

4. The short-term electric vehicle charging load forecasting method according to claim 1, characterized in that: The model parameters of the Holt-Winter model are optimized using the particle swarm optimization algorithm.

5. A short-term electric vehicle charging load forecasting system, characterized by, A method for predicting short-term electric vehicle charging load as described in any one of claims 1-4 includes: The building module is used to construct a Holt-Winter model for predicting the charging load of the target object based on its historical charging load data. The extraction module is used to select the charging load data of the first n cycles from the historical charging load data to form a charging load data sequence. The optimization module is used to optimize the Holt-Winter model based on the charging load data sequence to obtain the charging load prediction model for the target object. The prediction module is used to predict the charging load of the target object using the target object charging load prediction model.

6. An electronic terminal, characterized in that include: The memory is used to store computer programs; A processor for executing a computer program stored in the memory to cause an electronic terminal to perform a short-term electric vehicle charging load prediction method according to any one of claims 1-4.

7. A computer readable storage medium having stored thereon a computer program, characterized in that: When the program is executed by the processor, it implements a short-term electric vehicle charging load prediction method according to any one of claims 1-4.

Images