Quantum-Enhanced Hybrid Models for Ultra-Short-Term Electricity Price Forecasting in Decentralized Smart Grids

Paper ID: EIJTEM_2025_12_2_67-73

Author's Name: Jaya Shukla, Dr. Rajnish Bhasker

Volume: 12

Issue: 2

Year: 2025

Page No: 67-73

Abstract:

This research investigates the integration of quantum-enhanced hybrid models for ultra-short-term electricity price forecasting within decentralized smart grids. The increasing complexity of electricity markets and the rise of renewable energy resources necessitate advanced forecasting techniques that can adapt to volatile price dynamics. This study proposes a hybrid model that leverages quantum computing capabilities alongside classical machine learning algorithms to improve prediction accuracy in ultra-short-term time frames. By utilizing real-time data from decentralized systems, the model captures the intricate relationships between supply and demand, facilitating optimal price forecasting. Performance evaluations against traditional forecasting models demonstrate significant improvements in accuracy and response time. The findings underscore the potential of quantum-enhanced models to revolutionize electricity price forecasting by providing stakeholders with reliable, timely information for market decision-making. This research contributes to the ongoing discourse on the integration of quantum technology in energy systems and highlights the importance of innovative modeling approaches to address the challenges posed by decentralized smart grids, ultimately paving the way for more resilient energy infrastructures.

Keywords: Power consumption analysis, Digital logic circuits, Ultra-low power, Subthreshold operation, Static CMOS gates

View PDF