Bus charging management based on AI prediction and MILP optimization

Abstract

The emergence of new energy optimisation and control technologies with the concept of power system flexibility is a promising way to achieve the desired optimum, secure management within the smart grid and green energy transition. In this context, demand response is available through flexible demand management, taking into account various technical and time constraints. Accordingly, the aim of this paper is to address existing constraints in the field of electric mobility, in particular the operation of the charging infrastructure of bus depots, in order to actively and effectively participate in demand response events by forecasting day-ahead charging costs and load profiles of public transport infrastructure. In line with the development of a methodology for forecasting more accurately, this paper develops a prediction model based on machine learning (ML). A charging schedule is then produced based on Mixed-Integer Linear Programming (MILP) with various objective function scenarios, taking into consideration the electricity price forecast and load distribution. As a result, calculating new provisional load profiles involves assessing the flexibility potential of the bus fleet and preparing solutions in advance based on the electricity market situation.