Household appliance usage recommendation based on demand forecasting and multi­objective optimization

Accelerated population growth in the 21st century and increased demand for energy sources, associated with climate change, have resulted two main challenges: search sustainable sources need to find more efficient ways use extant sources. The forecasting module provides an estimate of future usage these appliances it is source recommended module’s suggestion. Time Series Forecasting techniques, such as Autoregressive Integrated Moving Average, Long­Short Term Memory (LSTM), Gated Recurrent Units, Echo State Networks (ESN), Support Vector Regression, were tested predictive module. Multi­objective optimization techniques Non­Sorted Genetic Algorithm II (NSGA II), Multi­Objective Particle Swarm Optimization (MOPSO), Speed constrained Multi-­objective (SMOPSO), Strength Pareto Evolutionary (SPEA2), example, Recommendation Module. experiments performed independently. In Module, results statistical tests revealed LSTM best­ suited technique loads majority (in this case seven) terms root mean square error. recommendation module, NSGA showed a higher overall performance compared other metrics hyper volume Front generated. This work presents potential using both Predictive Models Techniques combined reduce household environments.