Load forecasting (LF) is a technique used by energy-providing companies to predict the power needed. LF is of great importance for ensuring sufficient capacity and manipulating the deregulation of the power industry in many countries, such as Arab gulf countries. Moreover, reduction of load forecasting error leads to lower costs and could save billions of dollars. Recently, further improvement has been introduced using more complex models that take into account dependencies among hidden layers. Also, many approach based model are presented, but all of them have limitations prediction capabilities. The purpose of this work is to demonstrate the load forecasting classes and factors impacting its performance, especially in Kuwaiti region in Arab Gulf. This work presents a novel deep leaning model that involves generating more accurate predictions for the electric load based on hierarchal learning architecture. It is integrates the features of data in discovering most influent factors affecting electrical load usage. The dataset used is the actual data from Ministry of Electrical in Kuwait, the data for load is in mega-watt long-term for the years 2006 to year 2015, which is trained using ARIMA and neural networks models. The load forecasting is done for the year 2016 and is validated for the accuracy and less for error rate. Results indicate that this architecture performs quite well when compared to traditional approaches and deep neural network.
展开▼
