Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On Electric Vehicle Energy Demand Forecasting and the Effect of Federated Learning

Andreas Tritsarolis, Gil Sampaio, Nikos Pelekis, Yannis Theodoridis

TL;DR

Experimental results demonstrate the superiority of gradient boosted trees (XGBoost) over statistical and NN-based models in both prediction accuracy and energy efficiency and an insight that Federated Learning-enabled models balance these factors, offering a promising direction for decentralized energy demand forecasting.

Abstract

The wide spread of new energy resources, smart devices, and demand side management strategies has motivated several analytics operations, from infrastructure load modeling to user behavior profiling. Energy Demand Forecasting (EDF) of Electric Vehicle Supply Equipments (EVSEs) is one of the most critical operations for ensuring efficient energy management and sustainability, since it enables utility providers to anticipate energy/power demand, optimize resource allocation, and implement proactive measures to improve grid reliability. However, accurate EDF is a challenging problem due to external factors, such as the varying user routines, weather conditions, driving behaviors, unknown state of charge, etc. Furthermore, as concerns and restrictions about privacy and sustainability have grown, training data has become increasingly fragmented, resulting in distributed datasets scattered across different data silos and/or edge devices, calling for federated learning solutions. In this paper, we investigate different well-established time series forecasting methodologies to address the EDF problem, from statistical methods (the ARIMA family) to traditional machine learning models (such as XGBoost) and deep neural networks (GRU and LSTM). We provide an overview of these methods through a performance comparison over four real-world EVSE datasets, evaluated under both centralized and federated learning paradigms, focusing on the trade-offs between forecasting fidelity, privacy preservation, and energy overheads. Our experimental results demonstrate, on the one hand, the superiority of gradient boosted trees (XGBoost) over statistical and NN-based models in both prediction accuracy and energy efficiency and, on the other hand, an insight that Federated Learning-enabled models balance these factors, offering a promising direction for decentralized energy demand forecasting.

On Electric Vehicle Energy Demand Forecasting and the Effect of Federated Learning

TL;DR

Experimental results demonstrate the superiority of gradient boosted trees (XGBoost) over statistical and NN-based models in both prediction accuracy and energy efficiency and an insight that Federated Learning-enabled models balance these factors, offering a promising direction for decentralized energy demand forecasting.

Abstract

The wide spread of new energy resources, smart devices, and demand side management strategies has motivated several analytics operations, from infrastructure load modeling to user behavior profiling. Energy Demand Forecasting (EDF) of Electric Vehicle Supply Equipments (EVSEs) is one of the most critical operations for ensuring efficient energy management and sustainability, since it enables utility providers to anticipate energy/power demand, optimize resource allocation, and implement proactive measures to improve grid reliability. However, accurate EDF is a challenging problem due to external factors, such as the varying user routines, weather conditions, driving behaviors, unknown state of charge, etc. Furthermore, as concerns and restrictions about privacy and sustainability have grown, training data has become increasingly fragmented, resulting in distributed datasets scattered across different data silos and/or edge devices, calling for federated learning solutions. In this paper, we investigate different well-established time series forecasting methodologies to address the EDF problem, from statistical methods (the ARIMA family) to traditional machine learning models (such as XGBoost) and deep neural networks (GRU and LSTM). We provide an overview of these methods through a performance comparison over four real-world EVSE datasets, evaluated under both centralized and federated learning paradigms, focusing on the trade-offs between forecasting fidelity, privacy preservation, and energy overheads. Our experimental results demonstrate, on the one hand, the superiority of gradient boosted trees (XGBoost) over statistical and NN-based models in both prediction accuracy and energy efficiency and, on the other hand, an insight that Federated Learning-enabled models balance these factors, offering a promising direction for decentralized energy demand forecasting.
Paper Structure (15 sections, 7 equations, 6 figures, 6 tables)

This paper contains 15 sections, 7 equations, 6 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Energy Demand Forecasting
  4. Federated Learning
  5. Problem Formulation and Proposed Methodology
  6. Problem Definition
  7. Our Methodology for Training EDF Models
  8. Extending to Federated Learning
  9. Summary of Forecasting Methods
  10. Experimental Study
  11. Experimental Setup, Datasets and Preprocessing
  12. Experimental Results, Part I: Centralized Learning
  13. Experimental Results, Part II: Federated Learning
  14. A Note on the Energy Consumption and Carbon Emission Savings
  15. Conclusion

Figures (6)

  • Figure 1: Overview of our [Fed]EDF forecasting framework.
  • Figure 2: Adapting the EDF experimental comparison workflow for the FL paradigm.
  • Figure 3: Snapshot of the EVSE locations of the (a) Dundee; (b) FEUP; (c) Boulder; and (d) Palo Alto dataset. Each color represents a different cluster / EVSE hub.
  • Figure 4: Snapshots of indicative EVSE energy demand time series (in kW) during March in (a) Dundee; (b) FEUP; (c) Boulder; and (d) Palo Alto dataset, respectively.
  • Figure 5: Energy Demand Forecasting on a randomly selected EVSE from the test set of the Dundee (a, e), FEUP (b, f), Boulder (c, g), and Palo Alto (d, h) Datasets using statistical (a, b, c, d); and ML-based (e, f, g, h) methods, respectively.
  • ...and 1 more figures

Theorems & Definitions (3)

  • Definition 1
  • Definition 2
  • Definition 3