Learning capacity: predicting user decisions for vehicle-to-grid services

Abstract

The electric vehicles (EV) market is projected to continue its rapid growth, which will profoundly impact the demand on the electricity network requiring costly network reinforcements unless EV charging is properly managed. However, as well as importing electricity from the grid, EVs also have the potential to export electricity through vehicle-togrid (V2G) technology, which can help balance supply and demand and stabilise the grid through participation in flexibility markets. Such a scenario requires a population of EVs to be pooled to provide a larger storage resource. Key to doing so effectively however is knowledge of the users, as they ultimately determine the availability of a vehicle. In this paper we introduce a machine learning model that aims to learn both a) the criteria influencing users when they decided whether to make their vehicle available and b) their reliability in following through on those decisions, with a view to more accurately predicting total available capacity from the pool of vehicles at a given time. Using a series of simplified simulations, we demonstrate that the learning model is able to adapt to both these factors, which allows the required capacity of a market event to be satisfied more reliably and using a smaller number of vehicles than would otherwise be the case. This in turn has the potential to support participation in larger and more numerous market events for the same user base and use of the technology for smaller groups of users such as individual communities.

Online Machine Learning of Available Capacity for Vehicle-to-Grid Services during the Coronavirus Pandemic

“…Quantifying and adapting to individual users is of particular importance when a V2G aggregator targets individual vehicle owners rather than fleets, which are more likely to have well defined patterns of activity. An early example of such work was developed in [12], in which a learning algorithm was introduced to adapt to changes in factors influencing a user's decision making and a user's reliability in making their vehicle available to the service. A methodology was also developed in [28] using behavioural analysis to assess the potential of a fleet to transition to electric vehicles and V2G.…”

“…Such prediction is required at multiple levels. For example, a machine learning framework was introduced in [12] that predicted available capacity from a vehicle fleet based on the learned behaviour of simulated user types, their willingness to participate in proposed V2G events and their reliability in making their vehicles available at agreed times. In [13], an automated machine learning was used to predict the parking locations of a fleet of vehicles and their proximity to V2G charging locations.…”

Where Will You Park? Predicting Vehicle Locations for Vehicle-to-Grid

“…Knowledge of individual vehicles is also important during the operation of a V2G service. It may not be possible to assume the use of a vehicle even if it is plugged in and available as it may be necessary for individuals to receive and accept offers to participate in a given V2G opportunity [28], an issue that may be particularly pertinent for non-fleet users. For non-homogeneous populations of vehicles and batteries, it may also be necessary to target users based on the specific capabilities of their vehicles, such as battery capacity.…”

Behavior-Neutral Smart Charging of Plugin Electric Vehicles: Reinforcement Learning Approach

“…The emergence of massive datasets has enabled data-driven approaches, which allow evaluating the system design directly on actual usage data [19][20][21][22] [23]. A large proportion of works using real datasets focused on characterisation of demand [21], studying charging behavior [24], prediction [25] and other [26][27] aspects.…”