Title: Intelligent infrastructures using deep learning-based applications for energy optimisation
Authors: P. Monica; Kriti Srivastava; A. Chitra; S. Malathi; D. Kerana Hanirex; S. Silvia Priscila
Addresses: Department of Electrical and Electronics Engineering, Sri Venkateswara College of Engineering and Technology, RVS Nagar, Chittoor, Andhra Pradesh, India ' Department of Computer Science and Engineering (Data Science), D.J. Sanghvi College of Engineering, Mumbai, India ' Department of Computer Applications, DRBCCC Hindu College, Pattabiram, Chennai, Tamil Nadu, India ' Department of Computer Science, St. Thomas College of Arts and Science, Koyembedu, Chennai, Tamil Nadu, India ' Department of Computer Science, Bharath Institute of Higher Education and Research, Tamil Nadu, India ' Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, 600126, Tamil Nadu, India
Abstract: Renewable energy could boost electricity and wave power. Increased electricity consumption necessitates hydropower integration. Wind energy is cost-effective and promising. This study examines wind farm viability in windy areas. This study summarises deep learning models, methods, and wind and wave energy conditions. Comparing approaches for similar applications. A computation technique can substitute a comprehensive computer model, with a 94% accuracy rate compared to model simulations and 84% compared to other data. The study found great promise in deep learning-based energy optimisation, storage, monitoring, forecasting, and behaviour inquiry and detection. Energy regulators and utility management could evaluate sustainable electricity diversification using the study's findings. This study summarises deep learning models, methods, and wind and wave energy conditions. Comparing equivalent application approaches. A computing technique can replace a complex computer model with 94% accuracy compared to model simulations and 84% to other data. Deep learning applications for energy optimisation, storage, monitoring, forecasting, and behaviour identification and investigation were promising. The project would give energy regulators and utility management impartial advice on sustainable electricity diversification.
Keywords: renewable energy; deep learning; wind turbine blade; electricity generation; wind energy; power management; wave energy; extended short-term memory; thermal sensation; indoor climate; machine learning; presence recognition.
DOI: 10.1504/IJCIS.2024.141440
International Journal of Critical Infrastructures, 2024 Vol.20 No.5, pp.391 - 415
Received: 01 Jan 2023
Accepted: 05 Feb 2023
Published online: 13 Sep 2024 *