Energy consumption forecasting using genetic fuzzy rule-based systems based on MOGUL learning methodology

Jozi, Aria; Pinto, Tiago; Praça, Isabel; Silva, Francisco; Teixeira, Brígida; Vale, Zita

http://hdl.handle.net/10400.22/17335

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
COM_GECAD_Powertech_2017_Aria.pdf		420.86 KB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

One of the most challenging tasks for energy domain stakeholders is to have a better preview of the electricity consumption. Having a more trustable expectation of electricity consumption can help minimizing the cost of electricity and also enable a better control on the electricity tariff. This paper presents a study using a Methodology to Obtain Genetic fuzzy rule-based systems Under the iterative rule Learning approach (MOGUL) methodology in order to have a better profile of the electricity consumption of the following hours. The proposed approach uses the electricity consumption of the past hours to forecast the consumption value for the following hours. Results from this study are compared to those of previous approaches, namely two fuzzy based systems: and several different approaches based on artificial neural networks. The comparison of the achieved results with those achieved by the previous approaches shows that this approach can calculate a more reliable value for the electricity consumption in the following hours, as it is able to achieve lower forecasting errors, and a less standard deviation of the forecasting error results