【 中文摘要 】本发明公开了考虑突发事件特征的电动汽车充电负荷预测方法及装置，包括：对常规影响因素进行特征筛选，得到最优常规特征集；对考虑突发事件的特征进行筛选，得到考虑突发事件的最优特征集；建立考虑突发事件的电动汽车负荷预测模型，结合最优常规特征集、考虑突发事件的最优特征集及历史负荷数据对电动汽车充电负荷进行预测。通过构建常规影响因素特征集以及突发事件最优特征集，通过SSA‑BiGRU‑CNN神经网络模型进行预测，同时考虑由突发事件所引起的负荷变化，从而能够准确预测突发事件下的电动汽车负荷，积极响应突发事件带来的负荷波动，有利于电力公司合理制定发电计划，削减电网成本，提高充电用户满意度及提高充电站的经济效益。
【 英文摘要 】The invention discloses a method and a device for predicting charging load of an electric vehicle in consideration of emergency characteristics. The method comprises the following steps of : performing characteristic screening on conventional influencing factors to obtain an optimal conventional characteristic set; Screening the features of the emergencies to obtain an optimal feature set of the emergencies; An electric vehicle load prediction model considering emergencies is established, and the charging load of the electric vehicle is predicted by combining the optimal conventional feature set and considering the optimal feature set of the emergencies and historical load data. The method comprises the following steps of : establishing a load prediction model of the electric vehicle considering the emergencies; and predicting the charging load of the electric vehicle by combining the optimal conventional feature set and considering the optimal feature set of the emergencies and historical load data. By constructing a feature set of conventional influencing factors and an optimal feature set of emergencies, Predicting by SSA-BiGRU-CNN neural network model, Meanwhile, the load change caused by the emergency is considered, so that the load of the electric automobile under the emergency can be accurately predicted, the load fluctuation caused by the emergency is actively responded, a power company can reasonably formulate a power generation plan, the cost of a power grid is reduced, the satisfaction degree of charging users is improved, and the economic benefit of a charging station is improved.
