Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Real-time Multi-scale Smart Energy Management and Optimisation (REMO) for buildings and their district

Jayan, Bejay 2016. Real-time Multi-scale Smart Energy Management and Optimisation (REMO) for buildings and their district. PhD Thesis, Cardiff University.
Item availability restricted.

[img]
Preview
PDF - Accepted Post-Print Version
Download (15MB) | Preview
[img] PDF - Supplemental Material
Restricted to Repository staff only

Download (162kB)

Abstract

Energy management systems in buildings and their district today use automation systems and artificial intelligence (AI) solutions for smart energy management, but they fail to achieve the desired results due to the lack of holistic and optimised decision-making. A reason for this is the silo-oriented approach to the decision-making failing to consider cross-domain data. Ontologies, as a new way of processing domain knowledge, have been increasingly applied to different domains using formal and explicit knowledge representation to conduct smart decision-making. In this PhD research, Real-time Multiscale Smart Energy Management and Optimisation (REMO) ontology was developed, as a cross-domain knowledge-base, which consequently can be used to support holistic real-time energy management in districts considering both demand and supply side optimisation. The ontology here, is also presented as the core of a proposed framework which facilitates the running of AI solutions and automation systems, aiming to minimise energy use, emissions, and costs, while maintaining comfort for users. The state of the art AI solutions for prediction and optimisation were concluded through authors involvement in European Union research projects. The AI techniques were independently validated through action research and achieved about 30 - 40 % reduction in energy demand of the buildings, and 36% reduction in carbon emissions through optimisation of the generation mix in the district. The research here also concludes a smart way to capture the generic knowledge behind AI models in ontologies through rule axiom features, which also meant this knowledge can be used to replicate these AI models in future sites. Both semantic and syntactic validation were performed on the ontology before demonstrating how the ontology supports the various use cases of the framework for holistic energy management. Further development of the framework is recommended for the future which is needed for it to facilitate real-time energy management and optimisation in buildings and their district.

Item Type: Thesis (PhD)
Status: Unpublished
Schools: Engineering
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Uncontrolled Keywords: Ontology; Multi-Objective Optimisation; Artificial Intelligence; Energy Management; Real-Time.
Date of First Compliant Deposit: 30 March 2017
Last Modified: 04 Jun 2017 09:46
URI: http://orca.cf.ac.uk/id/eprint/99480

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics