Litcius/Paper detail

Modelling energy demand response using long short-term memory neural networks

José Joaquín Mesa-Jiménez, Lee Stokes, C. Moss, Qingping Yang, Valerie Livina

2020Energy Efficiency23 citationsDOIOpen Access PDF

Abstract

Abstract We propose a method for detecting and forecasting events of high energy demand, which are managed at the national level in demand side response programmes, such as the UK Triads. The methodology consists of two stages: load forecasting with long short-term memory neural network and dynamic filtering of the potential highest electricity demand peaks by using the exponential moving average. The methodology is validated on real data of a UK building management system case study. We demonstrate successful forecasts of Triad events with R R M S E ≈ 2.2 % and M A P E ≈ 1.6 % and general applicability of the methodology for demand side response programme management, with reduction of energy consumption and indirect carbon emissions.

Topics & Concepts

Demand responseTerm (time)Artificial neural networkDemand forecastingTriad (sociology)Computer scienceOperations researchEnergy demandElectricityDemand sideDemand reductionSustainable developmentEnergy managementEnvironmental economicsEconometricsEnergy (signal processing)EconomicsEngineeringArtificial intelligenceStatisticsMathematicsPsychologyLawPolitical scienceMedicineElectrical engineeringPathologyQuantum mechanicsPsychoanalysisPhysicsEnergy Load and Power ForecastingBuilding Energy and Comfort OptimizationWind and Air Flow Studies
Modelling energy demand response using long short-term memory neural networks | Litcius