Equipping Seasonal Exponential Smoothing Models with Particle Swarm Optimization Algorithm for Electricity Consumption Forecasting

Abstract

Electricity consumption forecasting plays an important role in investment planning of electricity infrastructure, and in electricity production/generation and distribution. Accurate electricity consumption prediction over the mid/long term is of great interest to both practitioners and academics. Considering that monthly electricity consumption series usually show an obvious seasonal variation due to their inherent nature subject to temperature during the year, in this paper, seasonal exponential smoothing (SES) models were employed as the modeling technique, and the particle swarm optimization (PSO) algorithm was applied to find a set of near-optimal smoothing parameters. Quantitative and comprehensive assessments were performed with two real-world electricity consumption datasets on the basis of prediction accuracy and computational cost. The experimental results indicated that (1) whether the accuracy measure or the elapsed time was considered, the PSO performed better than grid search (GS) or genetic algorithm (GA); (2) the proposed PSO-based SES model with a non-trend component and additive seasonality term significantly outperformed other competitors for the majority of prediction horizons, which indicates that the model could be a promising alternative for electricity consumption forecasting.

XGB and SHAP credit scoring model based on Bayesian optimization

“…In the experimental study, we carried out parameter optimization comparative experiments on four algorithms: Grid search , Random search , Particle Swarm Optimization (PSO) [18], and Bayesian Optimization (BO) . For the optimization performance, first of all, the effect of Grid search and Random search is average, second of all, the optimization efficiency of the Patch Swarm Optimization algorithm is not particularly high, and needs enough initial sample points.…”

Event-Based Under-Frequency Load Shedding Scheme in a Standalone Power System

“…PSO involves a population of individuals (particles) that represent possible solutions and move in an Ω-dimensional search space. The velocity V t p and position X t p of particle p are updated using Equations ( 10) and ( 11), respectively [34,35]:…”

Multivariate empirical mode decomposition based hybrid model for day-ahead peak load forecasting

“…A variety of models were developed in an attempt to predict the amount of electricity peak load. For example, traditional statistics methods, such as linear regression [19,20], gray forecasting [21], fuzzy logic [22,23], exponential smoothing (ES) [24,25], and autoregressive integrated moving average [26], are useful in forecasting linear trends. However, these approaches can't predict the non-linear signals and time series accurately due to the defect of capturing the significant fluctuation of electricity demand and they can only discuss the physical properties of the substances [27].…”