WSEAS Transactions on Systems
Print ISSN: 1109-2777, E-ISSN: 2224-2678
Volume 13, 2014
Electricity Consumption Prediction System for the Public Transportation
Authors: ,
Abstract: A system for prediction of the electricity consumption of public transport in a city is presented in the paper. A multilayer neural network with back propagation learning method is the basic part of the system. In transport hauler the Power Engineer has to declare the necessary electricity consumption for every hour of the following week. The incorrect request affects the price of the electricity. Electricity consumption is a random process which depends on many factors. Dialogue system requires information for the month, type of day, time and temperature. The system provides information for the distributions of temperature, kilometers run and their joint distribution for the different periods. The system searches the kilometers run with similar parameters in the database and offers an average value. The Power Engineer compares this value with the planed kilometers run and decides the value for the request. Thereby formed query is the input vector to the neural network, which returns a value of electricity consumption. The neural network is previously trained with 26230 items for the past period. The neural network has one input with five neurons, one hidden and one output layer with one neuron. The output is the electricity consumption.
Search Articles
Keywords: Dialogue system, neural network, electricity consumption, prediction, back propagation learning method, copula, histogram, database
Pages: 638-643
WSEAS Transactions on Systems, ISSN / E-ISSN: 1109-2777 / 2224-2678, Volume 13, 2014, Art. #63