Constance Crozier

Constance Crozier, Dimitra Apostolopoulou, Malcolm McCulloch

Accurately predicting the future power demand of electric vehicles is important for developing policy and industrial strategy. Here we propose a method to create a representative set of electricity demand profiles using survey data from conventional vehicles. This is achieved by developing a model which maps journey and vehicle parameters to an energy consumption, and applying it individually to the entire data set. As a case study the National Travel Survey was used to create a set of profiles representing an entirely electric UK fleet of vehicles. This allowed prediction of the required electricity demand and sizing of the necessary vehicle batteries. Also, by inferring location information from the data, the effectiveness of various charging strategies was assessed. These results will be useful in both National planning, and as the inputs to further research on the impact of electric vehicles.

Yiru Ji, Constance Crozier, Matthew Liska

The rapid growth of GPU-heavy data centers has significantly increased electricity demand and creating challenges for grid stability. Our paper investigates the extent to which an energy-aware job scheduling algorithm can provide flexibility in GPU-heavy data centers. Compared with the traditional first-in first-out (FIFO) baseline, we show that more efficient job scheduling not only increases profit, but also brings latent power flexibility during peak price period. This flexibility is achieved by moving lower energy jobs, preferentially executing jobs with lower GPU utilization and smaller node requirements, when the electricity price is high. We demonstrate that data centers with lower queue length and higher variance in job characteristics such as job GPU utilization and job size, offer the greatest flexibility potential. Finally we show that data center flexibility is highly price sensitive, a 7% demand reduction is achieved with a small incentive, but unrealistically high prices are required to achieve a 33% reduction.

Enrico Marchesini, Benjamin Donnot, Constance Crozier et al.

Reinforcement learning (RL) can provide adaptive and scalable controllers essential for power grid decarbonization. However, RL methods struggle with power grids' complex dynamics, long-horizon goals, and hard physical constraints. For these reasons, we present RL2Grid, a benchmark designed in collaboration with power system operators to accelerate progress in grid control and foster RL maturity. Built on RTE France's power simulation framework, RL2Grid standardizes tasks, state and action spaces, and reward structures for a systematic evaluation and comparison of RL algorithms. Moreover, we integrate operational heuristics and design safety constraints based on human expertise to ensure alignment with physical requirements. By establishing reference performance metrics for classic RL baselines on RL2Grid's tasks, we highlight the need for novel methods capable of handling real systems and discuss future directions for RL-based grid control.

Caleb Ju, Constance Crozier

Variable renewable generation increases the challenge of balancing power supply and demand. Grid-scale batteries co-located with generation can help mitigate this misalignment. This paper explores the use of reinforcement learning (RL) for operating grid-scale batteries co-located with solar power. Our results show RL achieves an average of 61% (and up to 96%) of the approximate theoretical optimal (non-causal) operation, outperforming advanced control methods on average. Our findings suggest RL may be preferred when future signals are hard to predict. Moreover, RL has two significant advantages compared to simpler rules-based control: (1) that solar energy is more effectively shifted towards high demand periods, and (2) increased diversity of battery dispatch across different locations, reducing potential ramping issues caused by super-position of many similar actions.

Aisling Pigott, Constance Crozier, Kyri Baker et al.

Increasing amounts of distributed generation in distribution networks can provide both challenges and opportunities for voltage regulation across the network. Intelligent control of smart inverters and other smart building energy management systems can be leveraged to alleviate these issues. GridLearn is a multiagent reinforcement learning platform that incorporates both building energy models and power flow models to achieve grid level goals, by controlling behind-the-meter resources. This study demonstrates how multi-agent reinforcement learning can preserve building owner privacy and comfort while pursuing grid-level objectives. Building upon the CityLearn framework which considers RL for building-level goals, this work expands the framework to a network setting where grid-level goals are additionally considered. As a case study, we consider voltage regulation on the IEEE-33 bus network using controllable building loads, energy storage, and smart inverters. The results show that the RL agents nominally reduce instances of undervoltages and reduce instances of overvoltages by 34%.

Liyang Han, Thomas Morstyn, Constance Crozier et al.

Among the various market structures under peer-to-peer energy sharing, one model based on cooperative game theory provides clear incentives for prosumers to collaboratively schedule their energy resources. The computational complexity of this model, however, increases exponentially with the number of participants. To address this issue, this paper proposes the application of K-means clustering to the energy profiles following the grand coalition optimization. The cooperative model is run with the "clustered players" to compute their payoff allocations, which are then further distributed among the prosumers within each cluster. Case studies show that the proposed method can significantly improve the scalability of the cooperative scheme while maintaining a high level of financial incentives for the prosumers.