Short Term Load Forecasting OF 132/33Kv Maiduguri Transmission Substation Using Artificial Neural Network (ANN)
Journal Title: International Journal of Research in Computer and Communication Technology - Year 2015, Vol 4, Issue 5
Abstract
This paper presents a novel approach for 1 to 24 hours ahead load forecasting using multilayer perceptron (MLP) also referred to as multilayer feed forward artificial neural network (ANN) of a utility company located in the North Eastern part of Nigeria. The inputs to the ANN model are; hourly load of the day, daily average minimum temperature, daily average maximum temperature, daily average minimum humidity and daily average maximum humidity. The output to the model is 24hours forecast load. The model was trained and tested on data of year 2010 using the Levenberg- marquadt optimization technique using MATLAB R2012b. A mean square error (MSE) of 5.3902e-06 was obtained. The result obtained shows that the MLP artificial neural network can be considered as a good method to model the Short term load forecast systems.
Authors and Affiliations
Idakwo Harrison, Peter Dibal, Ishaku Bello
After BI: What’s the Future Intelligence?
Traditional Business Intelligence (BI) approaches have fallen short in delivering the expected value and return on investment. High costs, lengthy implementations and increasing complexity have led to frustration and...
A survey – Energy Efficient Routing protocol for Homogenous & Heterogeneous Networks
The wireless sensor networks have gained a lot of grasp in the previous years due to various encroachments in this field. One of the major challenges faced by WSNs is the problem of energy efficiency. Various routing...
Efficient Data Coordination Technique for Data Verification and Integration in Multi-Cloud Systems
Cloud computing is a new and fast growing technology that offers an innovative, efficient and scalable business model for organizations to adopt various information technology (IT) resources i.e. software, hardware,...
Multimodal Biometric Face and Fingerprint Recognition Using Adaptive principal Component Analysis and Multilayer Perception
A multimodal biometric face and fingerprint recognition using neural network system based on adaptive principal component analysis and multilayer perception.To improve accuracy and performance, Reliable method for se...
A Specialized Learning Framework for Aggregate Performance
Aggregate Performance is study of behaviour of a person who’s registered in a social network. More number of individuals are connection each other in this networks. The media is facing a major problem for finding the...