A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control

TLDR

Buildings account for a large share of global energy use and greenhouse gas emissions, and the proliferation of smart devices and sensors offers an opportunity to develop context‑aware building controllers. The authors build zone‑level artificial neural networks that take weather, occupancy, and indoor temperature as inputs, and use them as evaluation engines for a genetic algorithm that generates 24‑hour heating set‑point schedules, which can be run day‑ahead or as model‑predictive control and can be re‑optimised hourly to minimize energy or cost under a time‑of‑use tariff. In a February test week, the optimisation reduced energy consumption by about 25 % compared with a baseline heating strategy, and when a time‑of‑use tariff was applied it shifted load to cheaper periods and cut energy cost by roughly 27 %.

Abstract

Buildings account for a substantial proportion of global energy consumption and global greenhouse gas emissions. Given the growth in smart devices and sensors there is an opportunity to develop a new generation of smarter, more context aware, building controllers. Therefore, in this work, surrogate, zone-level artificial neural networks that take weather, occupancy and indoor temperature as inputs, have been created. These are used as an evaluation engine by a genetic algorithm with the aim of minimising energy consumption. Bespoke 24-h, heating set point schedules are generated for each zone in a small office building in Cardiff, UK. The optimisation strategy can be deployed in two modes, day ahead optimisation or as model predictive control which re-optimises every hour. Over a February test week, the optimisation is shown to reduce energy consumption by around 25% compared to a baseline heating strategy. When a time of use tariff is introduced, the optimisation is altered to minimise cost rather than energy consumption. The optimisation strategy successfully shifts load to cheaper price periods and reduces energy cost by around 27% compared to the baseline strategy.