Special Issue "Short-Term, Medium-Term and Long-Term Load Forecasting: Methods and Applications"

A special issue of Forecasting (ISSN 2571-9394). This special issue belongs to the section "Power and Energy Forecasting".

Deadline for manuscript submissions: 31 December 2020.

Special Issue Editor

Asst. Prof. Dr. Ioannis Panapakidis
Website
Guest Editor
School of Technology, University of Thessaly, 41110, Larissa, Greece
Interests: demand side management; energy policy; load forecasting; load profiling; optimization

Special Issue Information

Dear Colleagues,

Power system operation and planning rely on forecasting of demand variables such as hourly load, peak load, and total energy. Based on the time horizon, forecasting is categorized as short-term, medium-term, and long-term. Short-term load forecasting (STLF) is the foundation where power system operation is built upon on an intraday and day-ahead basis. Paradigms of applications are unit commitment, hydrothermal coordination, optimal load flow, demand response, and others. Medium-term load forecasting (MTLF) is mostly concerned with fuel import decisions and power unit maintenance scheduling. Long-term load forecasting (LTLF) is exploitable in power system planning.

Until recently, the system operator was responsible for providing the official predictions for the national system level. However, due to the deregulation and increase of competition of modern-day power markets, the strategic actions of various entities such as generation companies, retailers, aggregators, and others rely on accurate load predictions. Moreover, a robust forecasting model for a prosumer would lead to the optimal management of the resources, i.e., energy management, generation, and storage.

Further, the power system gradually transforms into a smart grid where the focus is mostly in small scale instead of system wide level loads such as loads of residences, buildings, distribution buses, and others. Another aspect of smart grid is smart metering, where the data are recorded in low time resolution, resulting in the collection of large amounts of data.

Load forecasting models can be, in general, classified into time series models and computational intelligence models. Time series models such as ARMA and ARIMA demand a priori the definition of the structure of the model. On the other hand, computational intelligence models such as neural networks, support vector machines, neurofuzzy systems, bio-inspired algorithms, and others are trained by the data, and the structure is determined after training. To overcome the drawbacks of each model, hybrid models have been proposed that combine models of a different type or a model and a data preprocessing technique. In addition, deep learning is a new and promising trend in machine learning that has not sufficiently been tested in load forecasting studies.

In the context of these challenges, the main scope of this Special Issue is to develop new methods applicable in short-, medium-, and long-term load forecasting. State-of-the-art papers together with innovative case studies are invited. Multidisciplinary research and cutting-edge approaches are welcomed in order to address the challenges that are raised by modern power systems, smart grids, and competitive power markets.

Asst. Prof. Dr. Ioannis Panapakidis
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Forecasting is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Time series and computational intelligence models for short-, medium-, and long-term forecasting
  • Application of time series processing techniques for load forecasting: Wavelets, empirical mode decomposition, principal component analysis, and others
  • Deep learning methods
  • Short-term load forecasting exploitation in power systems operations
  • Medium- and long-term forecasting exploitation in power systems planning
  • Load forecasting and deregulated power markets
  • Load forecasting for smart homes and smart buildings
  • Load forecasting for distribution systems and buses
  • Big data analytics application in load forecasting
  • Spatial and temporal load forecasting

Published Papers (2 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Open AccessArticle
Modeling and Forecasting Medium-Term Electricity Consumption Using Component Estimation Technique
Forecasting 2020, 2(2), 163-179; https://doi.org/10.3390/forecast2020009 - 23 May 2020
Abstract
The increasing shortage of electricity in Pakistan disturbs almost all sectors of its economy. As, for accurate policy formulation, precise and efficient forecasts of electricity consumption are vital, this paper implements a forecasting procedure based on components estimation technique to forecast medium-term electricity [...] Read more.
The increasing shortage of electricity in Pakistan disturbs almost all sectors of its economy. As, for accurate policy formulation, precise and efficient forecasts of electricity consumption are vital, this paper implements a forecasting procedure based on components estimation technique to forecast medium-term electricity consumption. To this end, the electricity consumption series is divided into two major components: deterministic and stochastic. For the estimation of deterministic component, we use parametric and nonparametric models. The stochastic component is modeled by using four different univariate time series models including parametric AutoRegressive (AR), nonparametric AutoRegressive (NPAR), Smooth Transition AutoRegressive (STAR), and Autoregressive Moving Average (ARMA) models. The proposed methodology was applied to Pakistan electricity consumption data ranging from January 1990 to December 2015. To assess one month ahead post-sample forecasting accuracy, three standard error measures, namely Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE), were calculated. The results show that the proposed component-based estimation procedure is very effective at predicting electricity consumption. Moreover, ARMA models outperform the other models, while NPAR model is competitive. Finally, our forecasting results are comparatively batter then those cited in other works. Full article
Show Figures

Figure 1

Open AccessArticle
X-Model: Further Development and Possible Modifications
Forecasting 2020, 2(1), 20-35; https://doi.org/10.3390/forecast2010002 - 03 Feb 2020
Cited by 1
Abstract
The main goal of the present paper is to improve the X-model used for day-ahead electricity price and volume forecasting. The key feature of the X-model is that it makes a day-ahead forecast for the entire wholesale supply and demand curves. The intersection [...] Read more.
The main goal of the present paper is to improve the X-model used for day-ahead electricity price and volume forecasting. The key feature of the X-model is that it makes a day-ahead forecast for the entire wholesale supply and demand curves. The intersection of the predicted curves yields the forecast for equilibrium day-ahead prices and volumes. We take advantage of a technique for auction curves’ transformation to improve the original X-model. Instead of using actual wholesale supply and demand curves, we rely on transformed versions of these curves with perfectly inelastic demand. As a result, the computational requirements of our X-model are reduced and its forecasting power increases. Moreover, our X-model is more robust towards outliers present in the initial auction curves’ data. Full article
Show Figures

Figure 1

Back to TopTop