Coherent Hierarchical Probabilistic Forecasting of Electric Vehicle Charging Demand
This work addresses the need for accurate and coherent demand forecasts in smart grids to manage increasing volatility from fast EV charging, though it is incremental as it builds on existing hierarchical forecasting techniques.
The paper tackles probabilistic forecasting of electric vehicle charging demand across multiple stations by combining a deep learning model to predict distributions and differentiable convex optimization layers to ensure hierarchical coherence, achieving improved accuracy over traditional methods as shown in real-world data experiments.
The growing penetration of electric vehicles (EVs) significantly changes typical load curves in smart grids. With the development of fast charging technology, the volatility of EV charging demand is increasing, which requires additional flexibility for real-time power balance. The forecasting of EV charging demand involves probabilistic modeling of high dimensional time series dynamics across diverse electric vehicle charging stations (EVCSs). This paper studies the forecasting problem of multiple EVCS in a hierarchical probabilistic manner. For each charging station, a deep learning model based on a partial input convex neural network (PICNN) is trained to predict the day-ahead charging demand's conditional distribution, preventing the common quantile crossing problem in traditional quantile regression models. Then, differentiable convex optimization layers (DCLs) are used to reconcile the scenarios sampled from the distributions to yield coherent scenarios that satisfy the hierarchical constraint. It learns a better weight matrix for adjusting the forecasting results of different targets in a machine-learning approach compared to traditional optimization-based hierarchical reconciling methods. Numerical experiments based on real-world EV charging data are conducted to demonstrate the efficacy of the proposed method.