Affiliations: [a] School of Business, Guangdong University of Foreign Studies, Guangzhou, China
Correspondence:
[*]
Corresponding author. Wen-Tsao Pan, School of Business, Guangdong University of Foreign Studies, Guangzhou 510006, China. E-mail: teacherp0162@yahoo.com.tw.
Abstract: With the progress in science and technology, many types of electrical equipment have been invented, making the use of electricity more extensive, and living environment more comfortable. However, in modern times, every country stresses the need to promote green energy in order to reduce environmental damage, while the Taiwanese government made an attempt to adjust electricity price as a means to make Taiwan people to reduce carbon emissions and pollution on the planet. Therefore, the paper takes electricity price on the power consumption of Taiwan people as the research object, observes tariff adjustment trends of relevant government departments, and builds Taiwan’s average electricity consumption and the average price forecast model to provide references to government and researchers. Firstly, we gather data of electricity consumption and price from Taiwan Power Company’s website, and draw a trend chart to explore the relationship between the two; and respectively work out technical indicators of average electric quantity and electricity prices by referring to stock technical indicators; finally, we compare Neural Network parameters optimized by Grey Fruit Fly Optimization Algorithm (GFOA) to build average power consumption and average electricity price forecasting models, and compare the best prediction model with other three algorithms. The study results demonstrate that the electricity consumption and electricity price trends have different characteristics; it is found out that the prediction model of smoothing parameter σ of General Regression Neural Network optimized by GFOA has better predictive ability compared to prediction models constructed by other three algorithms.
Keywords: Grey Fruit Fly Optimization Algorithm, Artificial Fish Swarm Algorithm, Artificial Bee Colony, General Regression Neural Network, Swarm Intelligence
