Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Coherent Hierarchical Probabilistic Forecasting of Electric Vehicle Charging Demand

Kedi Zheng, Hanwei Xu, Zeyang Long, Yi Wang, Qixin Chen

TL;DR

This article studies the forecasting problem of multiple EVCS in a hierarchical probabilistic manner and 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.

Abstract

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.

Coherent Hierarchical Probabilistic Forecasting of Electric Vehicle Charging Demand

TL;DR

This article studies the forecasting problem of multiple EVCS in a hierarchical probabilistic manner and 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.

Abstract

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.

Paper Structure

This paper contains 24 sections, 14 equations, 10 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work in Hierarchical Forecasting
  3. Related Work in EV Demand Forecasting
  4. Contribution
  5. Paper Structure
  6. Preliminaries
  7. Probabilistic Forecasting and Quantile Regression
  8. Hierarchical Coherency
  9. Framework
  10. Methodology
  11. Feature Engineering
  12. LSTM Module
  13. Probabilistic Modeling with PICNN
  14. Principle of DCL
  15. Trainable Hierarchical Reconciling with DCL
  16. ...and 9 more sections

Figures (10)

  • Figure 1: Relationship of observations in multi-horizon forecasting.
  • Figure 2: The proposed hierarchical probabilistic forecasting framework.
  • Figure 3: The structure of an LSTM module.
  • Figure 4: The structure of a multi-layer PICNN.
  • Figure 5: Training and data partitioning of hierarchical reconciling.
  • ...and 5 more figures

Theorems & Definitions (1)

  • proof