EV Bidirectional Charging Scheduling for Market Arbitrage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for managing bidirectional charging at electric vehicle (EV) charging stations face challenges in optimizing energy transactions between day-ahead and intra-day markets due to limited charging and trading flexibility, computation complexity, and electricity price volatility, making it difficult to capitalize on price differences and ensure timely vehicle operations.
Innovation Solution
A method and system that utilize a day-ahead planning module and an intra-day planning module, employing a learning agent and Graph Neural Network to optimize vehicle-charger allocation and prioritize energy trading, allowing for dynamic scheduling and arbitrage opportunities based on market prices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the fleet uses more charging points to increase charging capacity, then the charging speed and vehicle availability improve, but the capital expenditure and infrastructure cost increase
Solution Approach 1:
The system dynamically adjusts charging allocation based on real-time electricity prices, vehicle state of charge, and delivery requirements. The optimization algorithm continuously reconfigures which vehicles charge at which points and when, allowing the limited charging infrastructure to serve more vehicles effectively without physical expansion
Solution Approach 2:
The system performs day-ahead planning that pre-schedules charging sessions based on forecasted electricity prices and predicted vehicle availability. By preparing charge schedules in advance, the system ensures vehicles are charged during optimal price periods while meeting delivery deadlines, maximizing the utility of existing charging capacity
2Loss of energy
If the system prioritizes day-ahead market trading to secure energy commitments, then the energy cost is reduced, but the trading flexibility and ability to capitalize on intra-day price volatility decreases
Solution Approach 1:
The energy procurement strategy is segmented into two distinct time horizons: day-ahead market transactions for baseline energy needs and intra-day market transactions for optimization and arbitrage. This segmentation allows the system to secure energy commitments in advance while retaining flexibility to adjust purchases based on real-time price signals and actual vehicle charging requirements
Solution Approach 2:
The system dynamically adjusts the mix of day-ahead and intra-day purchasing based on market conditions, vehicle state of charge levels, and delivery requirements. When intra-day prices are favorable or vehicle availability is uncertain, the system increases intra-day procurement; when day-ahead prices are low and vehicle schedules are stable, it relies more on pre-scheduled purchases
3Reliability
If the system makes detailed charging schedules for all vehicles in advance, then the vehicle operation reliability improves, but the computation complexity and planning time increases
Solution Approach 1:
The planning problem is segmented into day-ahead strategic planning and real-time operational adjustment. The day-ahead phase creates high-level charge schedules and market procurement plans, while the real-time phase handles dynamic re-scheduling based on actual vehicle arrivals, departures, and price changes. This segmentation reduces computational burden by separating strategic decisions from tactical adjustments
Solution Approach 2:
The system performs preliminary optimization by pre-calculating charging schedules based on forecasted parameters before actual vehicle operations begin. These pre-computed schedules provide a reliable baseline that ensures vehicle availability while avoiding the need to solve the full complex optimization problem in real-time
4Loss of energy
If the system charges vehicles during low-price periods to reduce costs, then the energy cost decreases, but the vehicle availability for on-demand deliveries may be compromised
Solution Approach 1:
The system dynamically adjusts charging schedules based on real-time vehicle availability data, delivery requests, and electricity prices. When a vehicle is needed for an urgent delivery or arrives earlier than expected, the system can interrupt or reschedule charging sessions. Conversely, when vehicles are idle and prices are low, charging is prioritized. This dynamic adjustment ensures cost-effective charging while maintaining service reliability
Solution Approach 2:
The system performs preliminary checks of vehicle delivery requirements and schedules before committing to charging sessions. By knowing in advance which vehicles need to be available for specific deliveries, the system can plan charging to occur during appropriate time windows that satisfy both cost optimization and availability requirements
Data Source
AI summary
This disclosure relates generally to a bidirectional charging at an electric vehicle (EV) charging station by an energy model that uses electricity bought from the day-ahead market for charging the fleet of electric vehicles (EVs) and uses the intra-day market for arbitrage. The competitive pricing of wholesale electricity markets and distributed energy resource capability of EV fleets (in addition) provide a revenue channel through energy arbitrage. To effectively handle electricity price variations and the energy demand of the EV fleet, the present disclosure utilizes a graph representation-based learning agent (LA3_D) with two-stage encoding for day-ahead charge planning; and a priority order based greedy heuristic (GH_I) for intra-day arbitrage planning. Because the agent learns the planning policy of mapping EVs to charging operations over several problem instances, it is able to solve a given instance with limited sub-optimality when put to test at different levels of scale.