Towards energy‐efficient smart homes via precise nonintrusive load disaggregation based on hybrid ANN–PSO

• Published in: Energy science & engineering Vol. 11; no. 7; pp. 2535 - 2551
• Main Authors: Ramadan, R., Huang, Qi, Bamisile, Olusola, Zalhaf, Amr S., Mahmoud, Karar, Lehtonen, Matti, Darwish, Mohamed M. F.
• Format: Journal Article
• Language: English
• Published: London John Wiley & Sons, Inc 01.07.2023; Wiley
• Subjects: Algorithms; artificial neural network; Artificial neural networks; Datasets; Electric appliances; Electrical loads; Energy consumption; Energy costs; Energy efficiency; energy efficiency behavior; Energy management; Household appliances; Monitoring; Neural networks; nonintrusive load monitoring; Particle swarm optimization; Power consumption; REDD; Residential energy; Smart buildings; Smart houses; United Kingdom > UK
• ISSN: 2050-0505; 2050-0505
• DOI: 10.1002/ese3.1472

Nowadays, the load monitoring system is an important element in smart buildings to reduce energy consumption. Nonintrusive load monitoring (NILM) is utilized to determine the power consumption of each appliance in smart homes. The main problem of NILM is how to separate each appliance's power from the signal of aggregated consumption. In this regard, this paper presents a combination between particle swarm optimization (PSO) and artificial neural networks (ANNs) to identify electrical appliances for demand‐side management. ANN is applied in NILM as a load identification task, and PSO is used to train the ANN algorithm. This combination enhances the NILM technique's accuracy, which is further verified by experiments on different datasets like Reference Energy Disaggregation Dataset, UK Domestic Appliance‐Level ElectricityUK‐DALE, and Indian data for Ambient Water and electricity Sensing. The high accuracy of the proposed algorithm is verified by comparisons with state of the art methods. Compared with other approaches, the total mean absolute error has decreased from 39.3566 to 18.607. Also, the normalized root mean square error (NRMSE) method has been used to compare the measured and predicted results. The NRMSE is in the range of 1.719%–16.514%, which means perfect consistency. This demonstrates the effectiveness of the proposed approach for home energy management. Furthermore, customer behavior has been studied, considering energy costs during day hours. The main contribution of this work can be summarized as follows: (1) The nonintrusive load monitoring (NILM) technique is used to improve the energy efficiency in smart homes due to the flexibility, simplicity, and efficiency of its parameter estimation algorithm. (2) The particle swarm optimization (PSO) with the artificial neural network is used as a hybrid algorithm to disaggregate the loads, whereas the PSO algorithm is used to train neural network architecture to improve the accuracy of the NILM technique. (3) The algorithm is applied to different datasets such as Reference Energy Disaggregation Dataset, UK Domestic Appliance‐Level Electricity, and Indian data for Ambient Water and electricity Sensing. (4) In addition, a comparison is performed between predicted and actual values of power consumption of the appliances. Moreover, the results are compared with the state of the art methods. (5) Furthermore, customer behavior has been studied, taking into account the cost of energy during day hours.