Short-Term Occupancy Forecasting for a Smart Home Using Optimized Weight Updates Based on GA and PSO Algorithms for an LSTM Network

In this work, we provide a smart home occupancy prediction technique based on environmental variables such as CO2, noise, and relative temperature via our machine learning method and forecasting strategy. The proposed algorithms enhance the energy management system through the optimal use of the electric heating system. The Long Short-Term Memory (LSTM) neural network is a special deep learning strategy for processing time series prediction that has shown promising prediction results in recent years. To improve the performance of the LSTM algorithm, particularly for autocorrelation prediction, we will focus on optimizing weight updates using various approaches such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The performances of the proposed methods are evaluated using real available datasets. Test results reveal that the GA and the PSO can forecast the parameters with higher prediction fidelity compared to the LSTM networks. Indeed, all experimental predictions reached a range in their correlation coefficients between 99.16% and 99.97%, which proves the efficiency of the proposed approaches.

[1]  Narinder Singh,et al.  An Overview of Variants and Advancements of PSO Algorithm , 2022, Applied Sciences.

[2]  G. Fujita,et al.  Estimation of Unmeasured Room Temperature, Relative Humidity, and CO2 Concentrations for a Smart Building Using Machine Learning and Exploratory Data Analysis , 2022, Energies.

[3]  L. Chrifi-Alaoui,et al.  Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks , 2022, Sensors.

[4]  Mohamed Benbouzid,et al.  Building Thermal-Network Models: A Comparative Analysis, Recommendations, and Perspectives , 2022, Energies.

[5]  Benoit Delinchant,et al.  Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model , 2021 .

[6]  Hussain Shareef,et al.  Neural Network Approach for Global Solar Irradiance Prediction at Extremely Short-Time-Intervals Using Particle Swarm Optimization Algorithm , 2021, Energies.

[7]  Yuteng Xiao,et al.  A dual‐stage attention‐based Conv‐LSTM network for spatio‐temporal correlation and multivariate time series prediction , 2021, Int. J. Intell. Syst..

[8]  Luis Hernández-Callejo,et al.  A Review of Energy Consumption Forecasting in Smart Buildings: Methods, Input Variables, Forecasting Horizon and Metrics , 2020, Applied Sciences.

[9]  Gregor P. Henze,et al.  Development and Evaluation of Occupancy-Aware HVAC Control for Residential Building Energy Efficiency and Occupant Comfort , 2020, Energies.

[10]  Xin Zhang,et al.  A review of studies applying machine learning models to predict occupancy and window-opening behaviours in smart buildings , 2020 .

[11]  Shahaboddin Shamshirband,et al.  Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting , 2020, Water.

[12]  Xueqi Zhang,et al.  Time-Series Prediction of Environmental Noise for Urban IoT Based on Long Short-Term Memory Recurrent Neural Network , 2020, Applied Sciences.

[13]  Kenneth N. Brown,et al.  Using Domain Knowledge for Interpretable and Competitive Multi-Class Human Activity Recognition , 2020, Sensors.

[14]  Paul Davidsson,et al.  A comparison of machine learning algorithms for forecasting indoor temperature in smart buildings , 2020, Energy Systems.

[15]  Ming Hu,et al.  Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation , 2020, Computational Materials Science.

[16]  Mohammad Ahsan Chishti,et al.  Data Analytics in the Internet of Things: A Survey , 2019, Scalable Computing: Practice and Experience.

[17]  Zlatan Car,et al.  Genetic Algorithm Approach to Design of Multi-Layer Perceptron for Combined Cycle Power Plant Electrical Power Output Estimation , 2019, Energies.

[18]  Enrico Macii,et al.  A Non-Linear Autoregressive Model for Indoor Air-Temperature Predictions in Smart Buildings , 2019, Electronics.

[19]  Zhile Yang,et al.  Electric Vehicle Charging Load Forecasting: A Comparative Study of Deep Learning Approaches , 2019, Energies.

[20]  Polat Hançer,et al.  A Comparative Study of Traditional and Contemporary Building Envelope Construction Techniques in terms of Thermal Comfort and Energy Efficiency in Hot and Humid Climates , 2019, Sustainability.

[21]  Jun Gao,et al.  Accuracy analyses and model comparison of machine learning adopted in building energy consumption prediction , 2019, Energy Exploration & Exploitation.

[22]  Vasudevan Lakshminarayanan,et al.  Genetic algorithms for lens design: a review , 2018, Journal of Optics.

[23]  Jing Zhao,et al.  A hybrid method of dynamic cooling and heating load forecasting for office buildings based on artificial intelligence and regression analysis , 2018, Energy and Buildings.

[24]  Ali Ouni,et al.  Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches † , 2018, Energies.

[25]  Antonio F. Gómez-Skarmeta,et al.  Providing Personalized Energy Management and Awareness Services for Energy Efficiency in Smart Buildings , 2017, Sensors.

[26]  B. Dong,et al.  A survey on energy consumption and energy usage behavior of households and residential building in urban China , 2017 .

[27]  Joaquim Melendez,et al.  Short-term load forecasting for non-residential buildings contrasting artificial occupancy attributes , 2016 .

[28]  Alina A. von Davier,et al.  Cross-Validation , 2014 .

[29]  Lei Liu,et al.  Particle swarm optimization algorithm: an overview , 2017, Soft Computing.