Hybrid model for predicting energy behaviour of Prosumers

Chittazhi, Sreelakshmi (2024) Hybrid model for predicting energy behaviour of Prosumers. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The current study seeks to contribute to the solution of the problem related to the determination of imbalance in prosumer networks, as this is critical for increasing the efficiency of energy management, and therefore, for decreasing the reliance on traditional power supply. This problem is relevant because the appropriate energy management contributes to improvement of energy systems, the reduction of carbon emissions, and the availability and stability of energy supply. To address this, developed a hybrid model that integrates the weather data and market price data with advanced machine learning techniques to enhance the predictions of energy imbalance. Even though the base model LightGBM model(18.15) and hybrid model with meta models linear regression and ridge regression had similar MAE value (18.20) which suggest its effectiveness in managing energy imbalances in prosumer networks. The paper’s contribution to the existing knowledge is in showing that using multiple data sources and implementing contemporary machine learning techniques improve accuracy of prediction. This work contributes to the existing knowledge on how the hybrid models can help manage the fluctuations of renewable energy production and prosumers’ actions. The issues of the applicability of the model to other geographical areas and various patterns of prosumer activity are left unsolved. Further investigations of the presented framework are required to enhance and expand its usage for different contexts.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Makki, Ahmed UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Energy industries Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HC Economic History and Conditions > Natural resources > Power resources
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	14 Aug 2025 15:48
Last Modified:	14 Aug 2025 15:48
URI:	https://norma.ncirl.ie/id/eprint/8545

Actions (login required)

View Item