Power Consumption Forecasting with AI and IOT

Title

Power Consumption Forecasting with AI and IOT

Creator

Murugesan, G.; Radha, B.; Nithya, A.S.; Gunavathi, R.

Description

Electricity plays a fundamental and indispensable role in modern society, driving progress, development, and the overall quality of life. Electricity is profoundly ingrained in daily life. It powers homes, providing lighting, heating, cooling, and appliances that support, comfort, and convenience. From cooking meals to powering electronic devices and entertainment systems, electricity is vital for modern living, enhancing our quality of life and enabling various activities. Power forecasting is critical to the effective management and optimization of power generation, consumption, and distribution. Power consumption forecasting has evolved significantly with the introduction of advanced technologies such as Artificial Intelligence (AI) and the Internet of Things (IoT). AI techniques, such as machine learning and deep learning, make use of the massive amounts of data produced by IoT devices like smart meters and energy monitoring devices. These devices continuously gather real-time data on power consumption, weather conditions, grid performance, and other relevant factors. AI algorithms can find patterns and correlations and provide accurate forecasts and important insights for power forecasting by processing and analyzing data. Machine learning algorithms, such as regression models, neural networks, and ensemble approaches, are trained using historical power consumption data and the features that have been chosen. The models discover the underlying patterns and correlations between input features and power consumption. These forecasts can be used for short-term load balancing, energy procurement planning, demand response management, and optimizing energy distribution. AI and IoT power usage projections give valuable data for decision-making and energy optimization techniques. These projections can be used by energy suppliers, grid operators, building managers, and consumers to plan energy usage, distribute resources efficiently, optimize demand response programs, and discover possibilities for energy saving. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Source

Power Systems;Volume;Part F914;pp.57-78

Date

01-01-2025

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Data fusion; Distributed energy resources; Grid resilience; Load forecasting; Machine learning algorithms; Optimization algorithms; Renewable energy integration; Time series forecasting

Coverage

Murugesan G., Department of Artificial Intelligence and Machine Learning, Sree Saraswathi Thyagaraja College, Tamil Nadu, Pollachi, India; Radha B., Department of Computer Technology and Data Science, Sri Krishna Arts and Science College, Tamil Nadu, Coimbatore, India; Nithya A.S., Department of Artificial Intelligence and Machine Learning, Sree Saraswathi Thyagaraja College, Tamil Nadu, Pollachi, India; Gunavathi R., Data Science Department, Christ (Deemed to be University), Maharashtra, Pune, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 16121287;

Format

online

Language

English

Type

Book chapter

Identifier

https://doi.org/10.1007/978-3-031-89459-6_4

https://www.scopus.com/pages/publications/105018052264?origin=resultslist