Short-Term Electricity Demand Forecasting: Impact Analysis of Temperature for Thailand

Abstract

Accurate electricity demand forecasting for a short horizon is very important for day-to-day control, scheduling, operation, planning, and stability of the power system. The main factors that affect the forecasting accuracy are deterministic variables and weather variables such as types of days and temperature. Due to the tropical climate of Thailand, the marginal impact of weather variables on electricity demand is worth analyzing. Therefore, this paper primarily focuses on the impact of temperature and other deterministic variables on Thai electricity demand. Accuracy improvement is also considered during model design. Based on the characteristics of demand, the overall dataset is divided into four different subgroups and models are developed for each subgroup. The regression models are estimated using Ordinary Least Square (OLS) methods for uncorrelated errors, and General Least Square (GLS) methods for correlated errors, respectively. While Feed Forward Artificial Neural Network (FF-ANN) as a simple Deep Neural Network (DNN) is estimated to compare the accuracy with regression methods, several experiments conducted for determination of training length, selection of variables, and the number of neurons show some major findings. The first finding is that regression methods can have better forecasting accuracy than FF-ANN for Thailand’s dataset. Unlike much existing literature, the temperature effect on Thai electricity demand is very interesting because of their linear relationship. The marginal impacts of temperature on electricity demand are also maximal at night hours. The maximum impact of temperature during night hours happens at 11 p.m., is 300 MW/ ° C, about 4 % rise in demand while during day hours, the temperature impact is only 10 MW/ ° C to 200 MW/ ° C about 1.4 % to 2.6 % rise.

Impact Study of Temperature on the Time Series Electricity Demand of Urban Nepal for Short-Term Load Forecasting

“…The complex behavior and fluctuating nature of electricity demand is a major challenge when developing a robust model. Fluctuation in the consumption of electricity is due to the random behaviors of the consumers, but within all the randomness, a few predictable patterns can be separated, such as seasonal, weekly and daily variation [7]. As human behaviors and requirements change with various factors such as the time of day or the day of the week, holidays tend to follow similar demand patterns, which make them easier to track [8].…”

“…As such events result in people traveling, most people travel away from major cities largely during long holidays or religious holidays. Local festivals and major events such as the new year have a huge impact on the load consumed [7]. This effect can be observed in various locations, which affects the consumption pattern [9,10].…”

“…Likewise, stochastic variables such as environmental factors and human behaviors toward the change in the environment also provide information on changing electricity demand. Among all factors, the outdoor temperature shows an important influence that explains the variation in demand [7,11,12]. The influence can be linked to the use of electric cooling and heating appliances used within the households.…”

“…The literature shows that a change in the outdoor temperature results in an increase or decrease in the use of appliances, resulting in a change in electricity demand. As multiple examples of research show that heating and cooling appliances are responsible for more than half the energy consumption in the residential load [7], implementing the impact of temperature as an input to the forecasting model can improve the accuracy of the load forecasting model.…”

A Fuzzy Logic Model for Hourly Electrical Power Demand Modeling

“…In References [19][20][21], the authors used recurrent neural models. In References [22][23][24][25], the authors used deep neural models. In References [26][27][28][29], the authors compared neural and fuzzy logic models.…”