With the globally increasing electricity demand, its related uncertainties are on the rise as well. Therefore, a deeper insight of load forecasting techniques for projecting future electricity demands becomes imperative for business entities and policy makers. The electricity demand is governed by a set of different variables or “electricity demand determinants”. These demand determinants depend on forecasting horizons (long term, medium term, and short term), the load aggregation level, climate, and socio-economic activities. In this paper, a review of different electricity demand forecasting methodologies is provided in the context of a group of low and middle income countries. The article presents a comprehensive literature review by tabulating the different demand determinants used in different countries and forecasting the trends and techniques used in these countries. A comparative review of these forecasting methodologies over different time horizons reveals that the time series modeling approach has been extensively used while forecasting for long and medium terms. For short term forecasts, artificial intelligence-based techniques remain prevalent in the literature. Furthermore, a comparative analysis of the demand determinants in these countries indicates a frequent use of determinants like the population, GDP, weather, and load data over different time horizons. Following the analysis, potential research gaps are identified, and recommendations are provided, accordingly.

Load forecasts are fundamental inputs for the reliable and resilient operation of a power system. Globally, researchers endeavor to improve the resulting forecast accuracies. However, the lack of studies detailing a standardized model development process remains a major issue. In this regard, this paper advances the knowledge of the systematic development of a short-term load forecast (STLF) model for electric utilities. The proposed model has been developed by using hourly load (time series) of five years of an electric power utility in Pakistan. Following the investigation of previously developed forecast models, this study addresses the challenges of STLF by utilizing multiple linear regression, bootstrap aggregated decision trees, and artificial neural networks (ANNs) as mutually competitive forecasting techniques. The study also highlights both rudimentary and advanced elements of data extraction, synthetic weather station development, and the use of elastic nets for feature space development to upscale its reproducibility at the global level. Simulations showed the superior forecasting prowess of ANNs over other techniques in terms of mean absolute percentage error (MAPE), root mean squared error (RMSE) and R 2 score. Furthermore, an empirical approach has been taken to underline the effects of data recency, climatic events, power cuts, human activities, and public holidays on the model's overall performance.

With the emergence of advanced computational technologies, the capacity to process data for developing machine learning-based predictive models has increased multifold. However, reliance on the model’s mere accuracy has swiftly shifted attention away from its interpretability. Resultantly, a need has emerged amongst forecasters and academics to have predictive models that are not only accurate but also interpretable as well. Therefore, to facilitate energy forecasters, this paper advances the knowledge of short-term load forecasting through generalized regression analysis using high degree polynomials and cross terms. To predict the irregularly changing energy demand at the consumer level, the proposed model uses a time series of an hourly load of three years of an electricity distribution company in Pakistan. Two variants of regression analysis are used: (a) generalized linear regression model (GLRM), and (b) generalized linear regression model with polynomials and cross-terms (GLRM-PCT) for comparative reasons. Experiments revealed that GLRM-PCT showed higher forecasting accuracy across a variety of performance metrics such as mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE), and r-squared values. Moreover, the enhanced interpretability of GLRM-PCT also explained a wide range of combinations of weather variables, public holidays, as well as lagged load and climatic variables.

No abstract