Automated prediction system of household energy consumption in cities using web crawler and optimized artificial intelligence

Abstract

The supply of electrical energy is critical to convenient and comfortable living. However, people consume a large amount of energy, contributing to an energy crisis and global warming, and damaging some ecological cycles. Residential electricity consumption has greater elasticity than industrial and business consumption; it therefore has high energy-saving potential. This work establishes an automated platform, which provides information about residential electricity consumption in each city in Taiwan. Machine learning was used to forecast future residential electricity demand. A nature-inspired optimization method was applied to enhance the accuracy of the best machine learner, yielding an even better hybrid ensemble model. Performance measures indicate that the resulting model is accurate and provides effective information for reference. An automatic webbased system based on the model was combined with a web crawler and scheduled to run automatically to provide information on monthly residential electricity consumption in each county and city. By providing energy consumption information across the country, power providers and government can discuss policy and set different goals for energy use. The results of this study can facilitate the early implementation of energy-saving and carbon emission-reducing in cities and aid utility companies in establishing energy conservation guidelines.

Metaheuristics‐optimized deep learning to predict generation of sustainable energy from rooftop plant microbial fuel cells

“…MAPE is the mean of the absolute errors between measured and predicted values divided by the measured values 39 : …”

“…However, this method is time‐consuming 38 . Bio‐inspired optimization algorithms look to the physical meanings of natural biological systems, human activities, and the group behaviors of animals to develop mathematical algorithms to simplify search procedures 39 …”

“…38 Bioinspired optimization algorithms look to the physical meanings of natural biological systems, human activities, and the group behaviors of animals to develop mathematical algorithms to simplify search procedures. 39 Rere et al 40 developed the ant colony optimization (ACO) CNN, which increases the time of training a CNN model and substantially improves its accuracy. Nevertheless, a prediction model that is integrated with an effective and efficient optimization algorithm for automatically tuning its hyperparameters would require less computation time to yield accurate results than would the manual adjustment of hyperparameters as required by deep learning techniques, supporting the development of an optimal hybrid model that is based on a metaheuristic algorithm and deep learning for power generation forecasting.…”

“…• Mean absolute percentage error (MAPE) MAPE is the mean of the absolute errors between measured and predicted values divided by the measured values 39 :…”

Application Analysis of Artificial Intelligence Technology in Electrical Engineering Teaching

“…The decentralized process control mainly completes data collection and distributed control in the production process to avoid the control failure of the centralized control system. The monitoring level mainly monitors and executes operations on production process data, and provides data to directly intervene in the system (Chou & Hsu, 2022). As the center of the entire control system, the management level provides production tasks, compiles system work reports, reviews control plans, establishes mathematical models, and formulates optimal control (Clark et al, 2020).…”