Seminars

Abstract: Local energy communities (LECs) are viewed as key actors in the future clean energy system where groups of citizens collaborate to use renewable energy to serve their community’s energy needs. However, LECs need decision support and optimisation tools. In this talk I will describe some optimisation models to support LECs to decide where to locate Photovoltaic arrays, and how to understand uncertainty between renewable energy generation and electricity demand, with computational experiments based on empirical data from a university campus. I will also highlight some ongoing research of the EURO WISDOM Forum to uncover gender dimensions in traditional OR applications such as Disaster Management, Healthcare, and Transport.

Abstract: Despite some negative press, deep neural networks are a useful tool for statistical risk modelling. We present deep extremal regression models - neural networks designed to target descriptions of the conditional tails, such as extreme quantiles or tail indices. By combining deep neural networks with asymptotically-justified models from extreme value theory, we create grey box models which permit high-dimensional inference on extremes while retaining some of the interpretability of traditional statistical models. This talk covers a few examples of deep extremal regression models, which we use for extreme quantile regression, full (semi-parametric) conditional density estimation, and modelling of multivariate extremes via an angular-radial approach. Real data applications include US and Mediterranean wildfire extremes, and UK Metocean storms.