The invention discloses an electric vehicle charging load prediction method based on IACO-Attention-LSTM. The method comprises the following steps: selecting an electricity price and holidays as input variables; the IACO algorithm adopts an elite ant system and a minimum and maximum ant system, and when the IACO algorithm is used for optimizing the LSTM neural network, the IACO feeds back a prediction error of the LSTM neural network; before load prediction of the IACO-LSTM method, the IACO algorithm trains the LSTM, selects different hyper-parameters to train a data set and predicts an output result, determines hyper-parameters for enabling ants to traverse all targets as soon as possible according to an error between a prediction result and a real load value, outputs an optimal solution after completion of iteration, assigns the optimal solution to an LSTM neural network, and finally performs load prediction. And determining a final LSTM neural network prediction model, and integrating all prediction results by using an Attention mechanism to obtain a prediction result so as to improve prediction accuracy and efficiency.

    一种基于IACO‑Attention‑LSTM的电动汽车充电负荷预测方法,选择电价以及节假日作为输入变量;IACO算法采用精英蚂蚁系统和最小最大蚂蚁系统,使用IACO算法对LSTM神经网络进行优化时,IACO反馈LSTM神经网络的预测误差;进行IACO‑LSTM方法负荷预测前,IACO算法对LSTM进行训练,选择不同的超参数对数据集进行训练并预测输出结果,根据预测结果和真实负荷值的误差确定让蚂蚁最快遍历所有目标的超参数,在迭代次数完成之后输出最优解,赋值给LSTM神经网络,确定最终LSTM神经网络预测模型,运用Attention机制对所有预测结果进行整合,得到预测结果,以提升预测准确性和效率。


    Access

    Download


    Export, share and cite



    Title :

    Electric vehicle charging load prediction method based on IACO-Attention-LSTM


    Additional title:

    基于IACO-Attention-LSTM的电动汽车充电负荷预测方法


    Contributors:
    HUANG LIANG (author) / TUO LIANGYU (author) / CUI YIBO (author) / LING ZAIXUN (author) / SUN CHAOXIA (author) / GU YIMING (author) / XIANG MUCHAO (author) / WU XIAOMIN (author) / LIU MANJIA (author) / DENG GUIPING (author)

    Publication date :

    2024-09-13


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    H02J CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER , Schaltungsanordnungen oder Systeme für die Abgabe oder Verteilung elektrischer Leistung / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES



    Electric vehicle charging load prediction method and terminal

    LIU LIN / YANG SIYU / CHEN YANTAO et al. | European Patent Office | 2024

    Free access

    Electric vehicle charging load prediction method and device

    LEE SEUNG-HAN / LIAO YIPU / SUN KE et al. | European Patent Office | 2023

    Free access

    A Reliable Path Planning Method for Lane Change Based on Hybrid PSO-IACO Algorithm

    Zhou, Zewei / Yu, Zhuoping / Xiong, Lu et al. | IEEE | 2021