Enhancing residential demand response through dynamic pricing forecasting

This study rigorously investigates the impact of demand response mechanisms in daily household operations, leveraging smart devices driven by dynamic pricing. It introduces a machine learning framework tailored for real-time predictive capabilities. The main objective is to enhance user convenience,...

Full description

Saved in:

Bibliographic Details
Published in:	2023 Second IEEE International Conference on Measurement, Instrumentation, Control and Automation (ICMICA) pp. 1 - 6
Main Authors:	Sanjana, V S, Maheswar Reddy, Y, Kumar, M Rakesh, Amrutha Raju, B
Format:	Conference Proceeding
Language:	English
Published:	IEEE 03-05-2024
Subjects:	Biological system modeling Demand response Dynamic pricing Forecasting Hardware Heuristic algorithms Long short term memory Machine Learning Monitoring Predictive models Pricing Real-time systems Residential Community
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	This study rigorously investigates the impact of demand response mechanisms in daily household operations, leveraging smart devices driven by dynamic pricing. It introduces a machine learning framework tailored for real-time predictive capabilities. The main objective is to enhance user convenience, optimize appliance management, and reduce electricity expenses by analyzing market prices. The focal point lies in monitoring and utilizing essential and non-essential devices, responsive to real-time fluctuations in grid prices throughout the day. This approach involves systematic data collection for training sophisticated models, particularly using Long Short-Term Memory (LSTM) networks. The performance of the adopted machine learning model is validated and evaluated for its ability to regulate device usage in dynamic grid pricing scenarios. Eventually, this study aims to establish a responsive and energy-efficient residential ecosystem, aligning with contemporary demands for sustainable living through cost analysis.
DOI:	10.1109/ICMICA61068.2024.10732813