Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.574547
Title: Smart grid framework analysis and artificial neutral network in load forecast
Author: Xu, Fang Yuan
Awarding Body: City University
Current Institution: City, University of London
Date of Award: 2011
Availability of Full Text:
Access through EThOS:
Abstract:
Power system is the one of the most critical parts of the whole energy utilization around the world. Recently people pay more attention to the energy utilization, new types of generations, storages and power utilization need to increase energy efficiency and reduce carbon emission. Due to the power grid currently is still mainly under the old-designed approach, it is increasingly exposed limitation on efficiency enhancement, security and reliability improvement, new technologies compatibility and meeting larger power capacity requirements. Thus, Smart Grid is 'born' to improve power grid for these requirements. It is an overlapping area between power system and digital technology, intelligent technology, communication technology and so on. Smart Grid can provide updates for nearly all sections of traditional power grid. It is a systematic framework that new technologies integration, system development strategy and planning, customers' awareness improvements and supports from." all relevant areas. The areas must be operated in coordination and parallel. Firstly, this thesis introduces Smart Grid and Smart Metering on its definition, characteristics and deployment. Secondly, this thesis describes a load forecasting system for macro-grid. Artificial Neural Network (ANN) was introduced to achieve this work for its excellent mapping approximation ability. In the third section, thesis focuses on load forecasting for micro-grid. Back- . Propagation method is used to train the Multi-layer Perceptron (MLP) ANN and its results were compared to that from Radial Basis Function (RBF) ANN. Analysis was focused not only on the two networks but also ANN generalization problems and differences between micro-grid load and macro-grid load prediction.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.574547  DOI: Not available
Share: