John Moriarty

Viktor Zobernig, Richard A. Saldanha, Jinke He et al.

The RangL project hosted by The Alan Turing Institute aims to encourage the wider uptake of reinforcement learning by supporting competitions relating to real-world dynamic decision problems. This article describes the reusable code repository developed by the RangL team and deployed for the 2022 Pathways to Net Zero Challenge, supported by the UK Net Zero Technology Centre. The winning solutions to this particular Challenge seek to optimize the UK's energy transition policy to net zero carbon emissions by 2050. The RangL repository includes an OpenAI Gym reinforcement learning environment and code that supports both submission to, and evaluation in, a remote instance of the open source EvalAI platform as well as all winning learning agent strategies. The repository is an illustrative example of RangL's capability to provide a reusable structure for future challenges.

Randall Martyr, John Moriarty, Christian Beck

This paper studies the optimal control of a commercial building's thermostatic load during off-peak hours as an ancillary service to the transmission system operator of a power grid. It provides an algorithmic framework which commercial buildings can implement to cost-effectively increase their electricity demand at night while they are unoccupied, instead of using standard inflexible setpoint control. Consequently, there is minimal or no impact on user comfort, while the building manager gains an additional income stream from providing the ancillary service, and can benefit further by pre-conditioning the building for later periods. The framework helps determine the amount of flexibility that should be offered for the service, and cost optimized profiles for electricity usage when delivering the service. Numerical results show that there can be an economic incentive to participate even if the payment rate for the ancillary service is less than the price of electricity.

John Moriarty, Jure Vogrinc, Alessandro Zocca

The frequency stability of power systems is increasingly challenged by various types of disturbances. In particular, the increasing penetration of renewable energy sources is increasing the variability of power generation and at the same time reducing system inertia against disturbances. In this paper we are particularly interested in understanding how rate of change of frequency (RoCoF) violations could arise from unusually large power disturbances. We devise a novel specialization, named ghost sampling, of the Metropolis-Hastings Markov Chain Monte Carlo method that is tailored to efficiently sample rare power disturbances leading to nodal frequency violations. Generating a representative random sample addresses important statistical questions such as "which generator is most likely to be disconnected due to a RoCoF violation?" or "what is the probability of having simultaneous RoCoF violations, given that a violation occurs?" Our method can perform conditional sampling from any joint distribution of power disturbances including, for instance, correlated and non-Gaussian disturbances, features which have both been recently shown to be significant in security analyses.

Pantelis Z. Hadjipantelis, Nick S. Jones, John Moriarty et al.

Many biological characteristics of evolutionary interest are not scalar variables but continuous functions. Here we use phylogenetic Gaussian process regression to model the evolution of simulated function-valued traits. Given function-valued data only from the tips of an evolutionary tree and utilising independent principal component analysis (IPCA) as a method for dimension reduction, we construct distributional estimates of ancestral function-valued traits, and estimate parameters describing their evolutionary dynamics.