Dr Jethro Browell, Research Fellow at the University of Strathclyde, and Dr Matteo Fasiolo, Lecturer at the University of Bristol, ran a regional electricity demand forecasting hackathon for students in the COMPASS Centre for Doctoral Training yesterday.
Visiting Research Fellow Dr Browell gave students an overview of how the Great Britain electricity transmission network has changed during the last decade, with particular focus on the consequences of the increased production from small-scale renewable sources, which appear as “negative demand”.
Dr Fasiolo then introduced a dataset containing electricity demand and weather-related variables, such as wind speed and solar irradiation, from 14 regions covering the whole of Great Britain. He proposed an initial forecasting solution based on a simple Generalized Additive Model (GAM), which he used to forecast the demand in each region.
The hackathon started, with the “Jim” team being the first to propose an improved solution, based on a more sophisticated GAM model, which beat the initial GAM in terms of forecasting accuracy.
The “AGang” team then produced an even more sophisticated GAM, which took them to the top of the ranking. In the meantime, the “D&D” team was struggling to make their random forest work, and submitted a couple of poor forecasts. Toward the end of event, “AGang” produced a couple of improved GAM solutions, which further strengthened their lead.
While Dr Fasiolo and Dr Browell were wrapping up the event and preparing to award the winners, the “D&D” team caught everyone by surprise by submitting a forecast which beat all others by a margin, in terms of forecasting accuracy. Their random forest was far better than the GAMs at predicting demand in Scotland, where wind production is an important factor and the dynamics are quite different relative to the other regions.
Congratulations to the top three teams:
- D&D: Doug Corbin and Dom Owens
- AGang: Andrea Becsek, Alex Modell and Alessio Zakaria
- Jim: Michael Whitehouse, Daniel Williams and Jake Spiteri
Winning team “D&D” said: “Given physical measurements, such as wind speeds and precipitation, as well as calendar data, we first performed a minor amount of feature engineering. Given the complex nature of the interactions between the variables, and large amount of data available, we opted to fit random forest models. These performed feature selection for us and provided some robustness from outlying observations.
“However, the models took a long time to fit. Despite parallelising the model fitting across the regions, we only just got our predictions in before the deadline. Thankfully, our model consistently outperformed the other approaches.
“Everyone taking part had a great time learning about the challenges of energy modelling, and we thrived under the pressure of friendly competition.”
Dr Browell added: “Computational statistics and data science is driving innovation in the energy sector and the technologies they enable will play a huge role in the decarbonisation. I was pleased to be able to expose the COMPASS cohort to this application and hope that they will be inspired to apply their expertise to energy and climate problems in the future.”