A Computing Model of Artificial Intelligent Approaches to Mid-term Load Forecasting: a state-of-the-art- survey for the researcher

Abstract

Abstract-This article presents the review of the computing models applied for solving problems of midterm load forecasting. The load forecasting results can be used in electricity generation such as energy reservation and maintenance scheduling. Principle, strategy and results of short term, midterm, and long term load forecasting using statistic methods and artificial intelligence technology (AI) are summaried, Which, comparison between each method and the articles have difference feature input and strategy. The last, will get the idea or literature review conclusion to solve the problem of mid term load forecasting (MTLF).

Energy Time Series Forecasting

“…Statistical models distinguish classical approaches such as Box-Jenkins models (e.g., ARIMA) [25] and exponential smoothing [229] as well as approaches from machine learning such as most importantly artificial neural networks [40]. Depending on the task and on the horizon different forecast models are employed.…”

“…The general forecast models can be divided into three large classes namely: models with autoregressive structures [25], exponential smoothing [127,246] and approaches from machine learning [40]. For this purpose mathematical models-called forecast models-are used.…”

A hybrid dynamic and fuzzy time series model for mid-term power load forecasting

“…In particular, mid-term load forecasting concerns power requirements for up to a few months ahead and focuses on predicting the peak monthly power load or monthly variations. Mid-term load forecasting is important in the scheduling of power plant maintenance, energy conservation and hydrothermal regulation and has been studied extensively for improving our forecasting skills [e.g., [1][2][3][4][5][7][8][9]. The prediction of loads over this timescale is particularly vital in fast growing mega-cities, where the rate of increase in the demand for power exceeds that of the power supply because of a population explosion and fast economic growth, thus endangering their sustainability.…”

Forecasting the load of electrical power systems in mid‐ and long‐term horizons: a review

“…It quoted "When you flick that switch, you expect the lights to go on -but the business of keeping them on is not nearly as straightforward". Till date, few of the prominent survey studies in load forecasting are Matthewman and Nicholson [17] in 1968, Abu El-Magd and Sinha [18] in 1982, Gross and Galiana [19] in 1987, Moghram and Rahman [20] in 1989, Srinivasan and Lee [21] in 1995, Hippert et al [22] in 2001, Alfares and Nazeeruddin [23] in 2002, Bunoon et al [24] in 2010 and Ghods and Kalantar [25] in 2011. Out of these review articles, either most of them are for STLF or the reviews are more than a decade old.…”

“…Also, it can be seen that the review articles did not explicitly review the methodologies for MTLF and LTLF, apart from refs. [24][25]. Thus, the paper aims at quantifying the recent methodologies as well as tries to gather the concept of MTLF and LTLF into one article that can be referenced for future use.…”