Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems

TL;DR

This paper addresses online decision-making for vehicle-to-building (V2B) energy management under uncertainty by formulating it as a Markov decision process and solving it with a domain-knowledge guided Monte Carlo Tree Search (DG-MCTS). The approach combines online sampling, LLF-based action pruning, and horizon decomposition to compute near-optimal charging/discharging actions, with a decentralized variant for scalability. Experimental results on real NATC-SV data show DG-MCTS outperforms state-of-the-art baselines in total cost and peak shaving while maintaining acceptable SoC levels, though performance can depend on prediction accuracy. The work advances practical V2B control by integrating stochastic planning, domain knowledge, and scalable multi-agent search, enabling more resilient and cost-effective energy management for smart buildings.

Abstract

Vehicle-to-building (V2B) systems integrate physical infrastructures, such as smart buildings and electric vehicles (EVs) connected to chargers at the building, with digital control mechanisms to manage energy use. By utilizing EVs as flexible energy reservoirs, buildings can dynamically charge and discharge them to optimize energy use and cut costs under time-variable pricing and demand charge policies. This setup leads to the V2B optimization problem, where buildings coordinate EV charging and discharging to minimize total electricity costs while meeting users' charging requirements. However, the V2B optimization problem is challenging because of: (1) fluctuating electricity pricing, which includes both energy charges ($/kWh) and demand charges ($/kW); (2) long planning horizons (typically over 30 days); (3) heterogeneous chargers with varying charging rates, controllability, and directionality (i.e., unidirectional or bidirectional); and (4) user-specific battery levels at departure to ensure user requirements are met. In contrast to existing approaches that often model this setting as a single-shot combinatorial optimization problem, we highlight critical limitations in prior work and instead model the V2B optimization problem as a Markov decision process (MDP), i.e., a stochastic control process. Solving the resulting MDP is challenging due to the large state and action spaces. To address the challenges of the large state space, we leverage online search, and we counter the action space by using domain-specific heuristics to prune unpromising actions. We validate our approach in collaboration with Nissan Advanced Technology Center - Silicon Valley. Using data from their EV testbed, we show that the proposed framework significantly outperforms state-of-the-art methods.

Figures (2)

• Figure 1: (Top) EV arrival and departure hours vs. arrival and required SoC over 8 months. (Bottom) Peak building power draw vs. time of day and TOU rates.
• Figure 2: Importance of each factor in hyperparameter exploration