scholarly journals Forecasting Electricity Consumption Using Fuzzy Time Series

2018 ◽  
Vol 7 (4.30) ◽  
pp. 342
Author(s):  
K.G. Tay ◽  
Y.Y. Choy ◽  
C.C. Chew
Keyword(s):  
Time Series ◽  
Membership Function ◽  
Electricity Consumption ◽  
Fuzzy Time Series ◽  
Infrastructure Development ◽  
Power Load ◽  
Increasing Demand ◽  
Facility Expansion ◽  
Electric Power Load ◽  
Monthly Electricity Consumption

Electricity consumption forecasting is important for effective operation, planning and facility expansion of power system.  Accurate forecasts can save operating and maintenance costs, increased the reliability of power supply and delivery system, and correct decisions for future development.  There is a great development of Universiti Tun Hussein Onn Malaysia (UTHM) infrastructure since its formation in 1993. The development will be accompanied with the increasing demand of electricity.  Hence, there is a need to forecast the UTHM electricity consumption for future decisions on generating electric power, load switching, and infrastructure development. Therefore, in this study, the Fuzzy time series (FTS) with trapezoidal membership function was implemented on the UTHM monthly electricity consumption from January 2011 to December 2017 to forecast January to December 2018 monthly electricity consumption.  The procedure of the FTS and trapezoidal membership function was described together with January data.  FTS is able to forecast UTHM electricity consumption quite well.

scholarly journals Research and Application of a Novel Hybrid Model Based on a Deep Neural Network Combined with Fuzzy Time Series for Energy Forecasting

Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3588 ◽  
Author(s):  
Wei ◽  
Wang ◽  
Ni ◽  
Tang
Keyword(s):  
Time Series ◽  
Wind Speed ◽  
Short Term Memory ◽  
Electrical Power ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Grey Wolf Optimizer ◽  
Power Load ◽  
Hybrid Forecasting ◽  
Forecasting System

In recent years, although deep learning algorithms have been widely applied to various fields, ranging from translation to time series forecasting, researchers paid limited attention to modelling parameter optimization and the combination of the fuzzy time series. In this paper, a novel hybrid forecasting system, named CFML (complementary ensemble empirical mode decomposition (CEEMD)-fuzzy time series (FTS)-multi-objective grey wolf optimizer (MOGWO)-long short-term memory (LSTM)), is proposed and tested. This model is based on the LSTM model with parameters optimized by MOGWO, before which a fuzzy time series method involving the LEM2 (learning from examples module version two) algorithm is adopted to generate the final input data of the optimized LSTM model. In addition, the CEEMD algorithm is also used to de-noise and decompose the raw data. The CFML model successfully overcomes the nonstationary and irregular features of wind speed data and electrical power load series. Several experimental results covering four wind speed datasets and two electrical power load datasets indicate that our hybrid forecasting system achieves average improvements of 49% and 70% in wind speed and electrical power load, respectively, under the metric MAPE (mean absolute percentage error).

Sign in / Sign up

Export Citation Format

Share Document