Rainfall prediction using fuzzy inference system for preliminary micro-hydro power plant planning

Suprapty, Bedi; Malani, Rheo; Minardi, Joko

doi:10.1088/1755-1315/144/1/012005

Cited by 2 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Eleven years of monthly rainfall data from the year 2006 to 2016 was used in [17] to predict the next two years of rainfall rate in the east of Kalimantan using autoregressive (AR) with FIS. However, it is unclear how they fuzzified the monthly rainfall data using the second-order AR.…”

Section: Electricity Consumption Forecasting Usingmentioning

confidence: 99%

Electricity Consumption Forecasting Using Fuzzy Inference System

2020

IJATCSE

View full text Add to dashboard Cite

Electricity consumption in Universiti Tun Hussein Onn Malaysia (UTHM) has previously been forecasted using a time series model, fuzzy time series (FTS) and multiple linear regression (MLR). Even though FTS gives the best prediction among these methods, the manual implementation of FTS can be a time consuming and laborious process. Like FTS, Fuzzy inference system (FIS) is an alternative system that utilizes fuzzy logic concept. The prediction using FIS, however, required multivariate data such as day, time, temperature, humidity and historical consumption data as its input. In this study, monthly univariate data of UTHM electricity consumption from January 2009 to December 2018 was employed for the forecasting of electricity consumption for the year 2019. FIS was chosen to be compared with the FTS method. Historical univariate data were fuzzified using trapezoidal rule following the FTS method before Sugeno type FIS was chosen to give constant output. A simple fuzzy rule was applied to map the input to output. 2.3173% of mean absolute percentage error (MAPE) was obtained in FIS which is considerably low if compared to the time series model (11.14%), MLR (10.62%), and FTS (5.74%).

show abstract

Section: Electricity Consumption Forecasting Usingmentioning

confidence: 99%