It is well known that short-term load forecasting (STLF) plays a key role in the formulation of economic, reliable, and secure operating strategies for power systems (planning, scheduling, maintenance, and control processes, among others), and this topic has been an important issue for several decades. However, there is still much progress to be made in this field. The deployment of enabling technologies (e.g., smart meters and sub-metering) has made high granular data available for many customer segments and many tasks—for instance, it has made load forecasting tasks feasible at several demand aggregation levels. The first challenge in this area is the improvement of STLF models and their performance at new demand aggregation levels. Specifically, individual level demand forecasting, which is more challenging than aggregated demand, should be addressed in a comprehensive manner, helping customers in decision making. Moreover, the increasing inclusion of renewable energies (wind and solar power) in the power system, and the necessity of including more flexibility through demand response initiatives, have introduced greater uncertainties, creating new challenges for STLF in future power systems. Other relevant issues are net demand forecasting in “prosumers” (i.e., the integrated or disaggregated forecast of demand and renewable generation), and demand forecasting by end-uses in large or aggregated customers.

Many techniques have been proposed for STLF, including traditional statistical models (such as SARIMA, ARMAX, exponential smoothing, linear and non-linear models, etc.) and artificial intelligence techniques (such as fuzzy regression, artificial neural networks, support vector regression, tree-based regression, ensemble methods, stacked methods, etc.). In the case of individual loads, the techniques for peak detection and extreme values are of great importance. Furthermore, distribution planning needs, as well as grid modernization, have initiated the development of hierarchical load forecasting. Analogously, the need to face new uncertainty sources in the power system has given more importance to probabilistic load forecasting in recent years.

This Topic is concerned with both fundamental research on STLF methodologies and its practical application to power systems, aiming at exploring the challenges that will be faced by a more distributed power system in the future.

All submitted contributions must be based on the rigorous examination of the mentioned approaches and demonstrate a theoretically sound framework; submissions lacking such a scientific approach are discouraged. It is recommended that existing/presented approaches are validated using real practical applications.

Prof. Dr. Antonio Gabaldón
Prof. Dr. María Carmen Ruiz-Abellón
Prof. Dr. Luis Alfredo Fernández-Jiménez
Topic Editors

Keywords

short-term load forecasting and distributed energy resources
short-term load forecasting and demand aggregation levels
statistical forecasting models (SARIMA, ARMAX, exponential smoothing, linear and non-linear regression, etc.)
artificial neural networks (ANNs)
fuzzy regression models
tree-based regression methods
stacked and ensemble methods
evolutionary algorithms
deep learning architectures
support vector regression (SVR)
robust load forecasting
hierarchical and probabilistic forecasting
hybrid and combined models
renewable generation forecasting
short-term net demand forecasting
inference on extreme and rare events
end-use demand forecasting

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Algorithms algorithms	-	3.3	2008	17.6 Days	1600 CHF	Submit
Applied Sciences applsci	2.838	3.7	2011	14.9 Days	2300 CHF	Submit
Energies energies	3.252	5.0	2008	15.5 Days	2200 CHF	Submit
Forecasting forecasting	-	-	2019	15 Days	1400 CHF	Submit
Sustainability sustainability	3.889	5.0	2009	17.7 Days	2200 CHF	Submit

Preprints is a platform dedicated to making early versions of research outputs permanently available and citable. MDPI journals allow posting on preprint servers such as Preprints.org prior to publication. For more details about reprints, please visit https://www.preprints.org.

Published Papers (5 papers)

Download All Papers

Order results

Result details

Journals

Show export options Show export options

Select all

Export citation of selected articles as:

Open AccessArticle

Point-Interval Forecasting for Electricity Load Based on Regular Fluctuation Component Extraction

Bilin Shao

Zixuan Yao

and

Yifan Qiang

Energies 2023, 16(4), 1988; https://doi.org/10.3390/en16041988 - 17 Feb 2023

Viewed by 531

Abstract

The fluctuation and uncertainty of the electricity load bring challenges to load forecasting. Traditional point forecasting struggles to avoid errors, and pure interval forecasting may cause the problem of too wide an interval. In this paper, we combine point forecasting and interval forecasting and propose a point-interval forecasting model for electricity load based on regular fluctuation component extraction. Firstly, the variational modal decomposition is combined with the sample entropy to decompose the original load series into a strong regular fluctuation component and a weak regular fluctuation component. Then, the gate recurrent unit neural network is used for point forecasting of the strong regular fluctuation component, and the support vector quantile regression model is used for interval forecasting of the weak regular fluctuation component, and the results are accumulated to obtain the final forecasting intervals. Finally, experiments were conducted using electricity load data from two regional electricity grids in Shaanxi Province, China. The results show that combining the idea of point interval, point forecasting, and interval forecasting for components with different fluctuation regularity can effectively reduce the forecasting interval width while having high accuracy. The proposed model has higher forecasting accuracy and smaller mean interval width at various confidence levels compared to the commonly used models. Full article

(This article belongs to the Topic Short-Term Load Forecasting)

► Show Figures

Figure 1

Open AccessArticle

Forecasting Short-Term Electricity Load Using Validated Ensemble Learning

Chatum Sankalpa

Somsak Kittipiyakul

and

Seksan Laitrakun

Energies 2022, 15(22), 8567; https://doi.org/10.3390/en15228567 - 16 Nov 2022

Cited by 1 | Viewed by 850

Abstract

As short-term load forecasting is essential for the day-to-day operation planning of power systems, we built an ensemble learning model to perform such forecasting for Thai data. The proposed model uses voting regression (VR), producing forecasts with weighted averages of forecasts from five individual models: three parametric multiple linear regressors and two non-parametric machine-learning models. The regressors are linear regression models with gradient-descent (LR), ordinary least-squares (OLS) estimators, and generalized least-squares auto-regression (GLSAR) models. In contrast, the machine-learning models are decision trees (DT) and random forests (RF). To select the best model variables and hyper-parameters, we used cross-validation (CV) performance instead of the test data performance, which yielded overly good test performance. We compared various validation schemes and found that the Blocked-CV scheme gives the validation error closest to the test error. Using Blocked-CV, the test results show that the VR model outperforms all its individual predictors. Full article

(This article belongs to the Topic Short-Term Load Forecasting)

► Show Figures

Graphical abstract

Open AccessArticle

Automatic Selection of Temperature Variables for Short-Term Load Forecasting

Alfredo Candela Esclapez

Miguel López García

Sergio Valero Verdú

and

Carolina Senabre Blanes

Sustainability 2022, 14(20), 13339; https://doi.org/10.3390/su142013339 - 17 Oct 2022

Viewed by 511

Abstract

Due to the infeasibility of large-scale electrical energy storage, electricity is generated and consumed simultaneously. Therefore, electricity entities need consumption forecasting systems to plan operations and manage supplies. In addition, accurate predictions allow renewable energies on electrical grids to be managed, thereby reducing greenhouse gas emissions. Temperature affects electricity consumption through air conditioning and heating equipment, although it is the consumer’s behavior that determines specifically to what extent. This work proposes an automatic method of processing and selecting variables, with a two-fold objective: improving both the accuracy and the interpretability of the overall forecasting system. The procedure has been tested by the predictive system of the Spanish electricity operator (Red Eléctrica de España) with regard to peninsular demand. During the test period, the forecasting error was consistently reduced for the forecasting horizon, with an improvement of 0.16% in MAPE and 59.71 MWh in RMSE. The new way of working with temperatures is interpretable, since they separate the effect of temperature according to location and time. It has been observed that heat has a greater influence than the cold. In addition, on hot days, the temperature of the second previous day has a greater influence than the previous one, while the opposite occurs on cold days. Full article

(This article belongs to the Topic Short-Term Load Forecasting)

► Show Figures

Figure 1

Open AccessArticle

A Novel Interval Energy-Forecasting Method for Sustainable Building Management Based on Deep Learning

Yun Duan

Sustainability 2022, 14(14), 8584; https://doi.org/10.3390/su14148584 - 13 Jul 2022

Cited by 3 | Viewed by 902

Abstract

Energy conservation in buildings has increasingly become a hot issue for the Chinese government. Compared to deterministic load prediction, probabilistic load forecasting is more suitable for long-term planning and management of building energy consumption. In this study, we propose a probabilistic load-forecasting method for daily and weekly indoor load. The methodology is based on the long short-term memory (LSTM) model and penalized quantile regression (PQR). A comprehensive analysis for a time period of a year is conducted using the proposed method, and back propagation neural networks (BPNN), support vector machine (SVM), and random forest are applied as reference models. Point prediction as well as interval prediction are adopted to roundly test the prediction performance of the proposed model. Results show that LSTM-PQR has superior performance over the other three models and has improvements ranging from 6.4% to 20.9% for PICP compared with other models. This work indicates that the proposed method fits well with probabilistic load forecasting, which could promise to guide the management of building sustainability in a future carbon neutral scenario. Full article

(This article belongs to the Topic Short-Term Load Forecasting)

► Show Figures

Figure 1

Open AccessArticle

Self-Attention-Based Short-Term Load Forecasting Considering Demand-Side Management

and

Energies 2022, 15(12), 4198; https://doi.org/10.3390/en15124198 - 07 Jun 2022

Cited by 2 | Viewed by 1049

Abstract

Accurate and rapid forecasting of short-term loads facilitates demand-side management by electricity retailers. The complexity of customer demand makes traditional forecasting methods incapable of meeting the accuracy requirements, so a self-attention based short-term load forecasting (STLF) considering demand-side management is proposed. In the data preprocessing stage, non-parametric kernel density estimation is used to construct customer electricity consumption feature curves, and then historical load data are used to delineate the feasible domain range for outlier detection. In the feature selection stage, the feature data are selected using variational modal decomposition and a maximum information coefficient to enhance the model prediction accuracy. In the model prediction stage, the decomposed intrinsic mode function components are independently predicted and reconstructed using an Informer based on improved self-attention. Additionally, the novel AdaBlief optimizer is used to optimize the model parameters. Cross-sectional and longitudinal experiments are conducted on a regional-level load dataset set in Spain. The experimental results prove that the proposed method is superior to other methods in STLF. Full article

(This article belongs to the Topic Short-Term Load Forecasting)

► Show Figures

Figure 1

Submit your Abstract

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Algorithms algorithms	-	3.3	2008	17.6 Days	1600 CHF	Submit
Applied Sciences applsci	2.838	3.7	2011	14.9 Days	2300 CHF	Submit
Energies energies	3.252	5.0	2008	15.5 Days	2200 CHF	Submit
Forecasting forecasting	-	-	2019	15 Days	1400 CHF	Submit
Sustainability sustainability	3.889	5.0	2009	17.7 Days	2200 CHF	Submit

Topic Menu

Topic Editors

Short-Term Load Forecasting

Topic Information

Keywords

Participating Journals

Published Papers (5 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI