Multi-objective optimisation for tuning building heating and cooling loads forecasting models

Saleh Seyedzadeh, Farzad Pour Rahimian, Parag Rastogi, Stephen Oliver, Ivan Glesk, Bimal Kumar

Research output: Contribution to conferencePaperpeer-review

18 Downloads (Pure)


Machine learning (ML) has been recognised as a powerful method for modelling building energy consumption. The capability of ML to provide a fast and accurate prediction of energy loads makes it an ideal tool for decision-making tasks related to sustainable design and retrofit planning. However, the accuracy of these ML models is much dependant on the selection of the right hyper-parameters for specific building dataset. This paper proposes a method for optimising ML model for forecasting both heating and cooling loads. The technique employs multi-objective optimisation with evolutionary algorithms to search the space of possible parameters. The proposed approach not only tune one model to precisely predict building energy loads but also accelerates the process of model optimisation. The study utilises a simulated building energy data generated in EnergyPlus to demonstrate the efficiency of the proposed method, and compares the outcomes with the regular ML tuning procedure (i.e. grid search). The optimised model provides a reliable tool for building designers and engineers to explore a large space of the available building materials and technologies.
Original languageEnglish
Number of pages10
Publication statusPublished - 18 Sept 2019
Event36th CIB W78 2019 Conference - Northumbria University, Newcastle, United Kingdom
Duration: 18 Sept 201920 Sept 2019
Conference number: 36


Conference36th CIB W78 2019 Conference
Abbreviated titleCIB W78
Country/TerritoryUnited Kingdom


  • building energy loads
  • building energy prediction
  • machine learning
  • model optimisation


Dive into the research topics of 'Multi-objective optimisation for tuning building heating and cooling loads forecasting models'. Together they form a unique fingerprint.

Cite this