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

• Published in: Energy (Oxford) Vol. 151; pp. 729 - 739
• Main Authors: Reynolds, Jonathan, Rezgui, Yacine, Kwan, Alan, Piriou, Solène
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 15.05.2018; Elsevier BV
• Subjects: Algorithms; Artificial neural network; Artificial neural networks; Building energy management; buildings; controllers; Emissions; energy; Energy consumption; energy costs; Genetic algorithm; Genetic algorithms; Greenhouse effect; greenhouse gas emissions; Greenhouse gases; Heating; Heating set point scheduler; HVAC control; Mathematical models; Model predictive control; Neural networks; Optimization; Predictive control; prices; Schedules; Smart sensors; Strategy; Tariffs; temperature; Time of use; United Kingdom; weather; United Kingdom; Model predictive control; Artificial neural network; HVAC control; Heating set point scheduler; Building energy management; Genetic algorithm
• ISSN: 0360-5442; 1873-6785; 1873-6785
• DOI: 10.1016/j.energy.2018.03.113

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. •This paper develops zone-level, surrogate, ANN models to predict heating energy demand and zone temperature.•The ANN are combined with a GA to minimise energy consumption or energy cost.•The effect of day-ahead controls or model predictive control is assessed.•The control framework was shown to be adaptive to dynamic energy pricing.•A total energy saving of 25% was shown over a February test week.