Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dynamic Rolling Horizon Optimization for Network-Constrained V2X Value Stacking of Electric Vehicles Under Uncertainties

Canchen Jiang, Ariel Liebman, Bo Jie, Hao Wang

TL;DR

The paper tackles coordinating EVs for V2X value stacking under distribution-network constraints using a dynamic rolling-horizon optimization. It combines V2B, V2G, and local energy trading with a Transformer-based GRU-EN-TFD forecasting model to handle uncertainties in building load, PV generation, and EV arrivals, solving a shrinking-horizon MIQP to minimize total cost. Experiments on real market data reveal that V2B typically yields the largest cost savings, EV-arrival forecast errors have the largest impact on performance, and GRU-EN-TFD outperforms LSTM forecasts. The work also discusses privacy and scalability limitations of centralized rolling-horizon optimization and points toward decentralized, privacy-preserving solutions for scalability.

Abstract

Electric vehicle (EV) coordination can provide significant benefits through vehicle-to-everything (V2X) by interacting with the grid, buildings, and other EVs. This work aims to develop a V2X value-stacking framework, including vehicle-to-building (V2B), vehicle-to-grid (V2G), and energy trading, to maximize economic benefits for residential communities while maintaining distribution voltage. This work also seeks to quantify the impact of prediction errors related to building load, renewable energy, and EV arrivals. A dynamic rolling-horizon optimization (RHO) method is employed to leverage multiple revenue streams and maximize the potential of EV coordination. To address energy uncertainties, including hourly local building load, local photovoltaic (PV) generation, and EV arrivals, this work develops a Transformer-based forecasting model named Gated Recurrent Units-Encoder-Temporal Fusion Decoder (GRU-EN-TFD). The simulation results, using real data from Australia's National Electricity Market, and the Independent System Operators in New England and New York in the US, reveal that V2X value stacking can significantly reduce energy costs. The proposed GRU-EN-TFD model outperforms the benchmark forecast model. Uncertainties in EV arrivals have a more substantial impact on value-stacking performance, highlighting the significance of its accurate forecast. This work provides new insights into the dynamic interactions among residential communities, unlocking the full potential of EV batteries.

Dynamic Rolling Horizon Optimization for Network-Constrained V2X Value Stacking of Electric Vehicles Under Uncertainties

TL;DR

The paper tackles coordinating EVs for V2X value stacking under distribution-network constraints using a dynamic rolling-horizon optimization. It combines V2B, V2G, and local energy trading with a Transformer-based GRU-EN-TFD forecasting model to handle uncertainties in building load, PV generation, and EV arrivals, solving a shrinking-horizon MIQP to minimize total cost. Experiments on real market data reveal that V2B typically yields the largest cost savings, EV-arrival forecast errors have the largest impact on performance, and GRU-EN-TFD outperforms LSTM forecasts. The work also discusses privacy and scalability limitations of centralized rolling-horizon optimization and points toward decentralized, privacy-preserving solutions for scalability.

Abstract

Electric vehicle (EV) coordination can provide significant benefits through vehicle-to-everything (V2X) by interacting with the grid, buildings, and other EVs. This work aims to develop a V2X value-stacking framework, including vehicle-to-building (V2B), vehicle-to-grid (V2G), and energy trading, to maximize economic benefits for residential communities while maintaining distribution voltage. This work also seeks to quantify the impact of prediction errors related to building load, renewable energy, and EV arrivals. A dynamic rolling-horizon optimization (RHO) method is employed to leverage multiple revenue streams and maximize the potential of EV coordination. To address energy uncertainties, including hourly local building load, local photovoltaic (PV) generation, and EV arrivals, this work develops a Transformer-based forecasting model named Gated Recurrent Units-Encoder-Temporal Fusion Decoder (GRU-EN-TFD). The simulation results, using real data from Australia's National Electricity Market, and the Independent System Operators in New England and New York in the US, reveal that V2X value stacking can significantly reduce energy costs. The proposed GRU-EN-TFD model outperforms the benchmark forecast model. Uncertainties in EV arrivals have a more substantial impact on value-stacking performance, highlighting the significance of its accurate forecast. This work provides new insights into the dynamic interactions among residential communities, unlocking the full potential of EV batteries.

Paper Structure

This paper contains 34 sections, 23 equations, 21 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Literature Review
  3. System Model
  4. Residential Community Model
  5. EVPL Model
  6. Residential Building Load Model
  7. Power Supply
  8. Power Export and Import of Residential Community
  9. Distribution Network Model
  10. V2X Value-Stacking Optimization Problem
  11. Value-Stacking Model
  12. Value Stream of V2B
  13. Value Stream of V2G
  14. Value Stream of Energy Trading in Local Market
  15. Multiple Value Streams of V2X
  16. ...and 19 more sections

Figures (21)

  • Figure 1: Illustration of EV coordination across multiple residential communities in distribution network.
  • Figure 2: The framework of the proposed V2X value-stacking, including V2B, V2G, and energy trading.
  • Figure 3: Framework of the GRU-EN-TFD model for forecasting building demand, PV generation, and EV arrivals.
  • Figure 4: Shrinking time window for the dynamic rolling-horizon EV value-stacking optimization.
  • Figure 5: Modified IEEE 33-bus distribution test system with six residential communities.
  • ...and 16 more figures