Short-Term Load Forecasting

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Algorithms algorithms	1.8	4.1	2008	18.9 Days	CHF 1600
Applied Sciences applsci	2.5	5.3	2011	18.4 Days	CHF 2400
Energies energies	3.0	6.2	2008	16.8 Days	CHF 2600
Forecasting forecasting	2.3	5.8	2019	18.5 Days	CHF 1800
Sustainability sustainability	3.3	6.8	2009	19.7 Days	CHF 2400

20 pages, 5551 KiB

Open AccessArticle

Multi-Level Decomposition and Interpretability-Enhanced Air Conditioning Load Forecasting Study

by Xinting Yang, Ling Zhang, Hong Zhao, Wenhua Zhang, Chuan Long, Gang Wu, Junhao Zhao and Xiaodong Shen

Energies 2024, 17(23), 5881; https://doi.org/10.3390/en17235881 - 23 Nov 2024

Cited by 1 | Viewed by 616

Abstract

This study seeks to improve the accuracy of air conditioning load forecasting to address the challenges of load management in power systems during high-temperature periods in the summer. Given the limitations of traditional forecasting models in capturing different frequency components and noise within [...] Read more.

This study seeks to improve the accuracy of air conditioning load forecasting to address the challenges of load management in power systems during high-temperature periods in the summer. Given the limitations of traditional forecasting models in capturing different frequency components and noise within complex load sequences, this paper proposes a multi-level decomposition forecasting model using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), sample entropy (SE), variational mode decomposition (VMD), and long short-term memory (LSTM). First, CEEMDAN is used for the preliminary decomposition of the raw air-conditioning load series, with modal components aggregated by sample entropy to generate high-, medium-, and low-frequency subsequences. VMD then performs a secondary decomposition on the high-frequency subsequence to reduce its complexity, while LSTM is applied to each subsequence for prediction. The final prediction result of the air-conditioning load is obtained through reconstruction. To validate model performance, this paper uses air-conditioning load data from Nanchong City and Sichuan Province, for experimental analysis. Results show that the proposed method significantly outperforms the LSTM model without decomposition and other benchmark models in prediction accuracy, with the Root Mean Square Error (RMSE) reductions ranging from 40.26% to 74.18% and the Modified Mean Absolute Percentage Error (MMAPE) reductions from 37.75% to 73.41%. By employing the SHAP (Shapley additive explanations) method for both global and local interpretability, the model reveals the influence of key factors, such as historical load and temperature, on load forecasting. The decomposition and aggregation approach introduced in this paper substantially enhances forecasting accuracy, providing a scientific foundation for power system load management and dispatch. Full article

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

► Show Figures

Figure 1

28 pages, 5112 KiB

Open AccessArticle

Applications of Probabilistic Forecasting in Demand Response

by María Carmen Ruiz-Abellón, Luis Alfredo Fernández-Jiménez, Antonio Guillamón and Antonio Gabaldón

Appl. Sci. 2024, 14(21), 9716; https://doi.org/10.3390/app14219716 - 24 Oct 2024

Viewed by 977

Abstract

Studies on probabilistic demand forecasting remain relatively limited compared with point forecasting, despite it being especially valuable for operational and planning purposes. This paper demonstrates different applications of probabilistic forecasting in demand response, together with Physical-Based Load Models. The first application shows how [...] Read more.

Studies on probabilistic demand forecasting remain relatively limited compared with point forecasting, despite it being especially valuable for operational and planning purposes. This paper demonstrates different applications of probabilistic forecasting in demand response, together with Physical-Based Load Models. The first application shows how to determine the percentage of uncertainty potentially covered by demand response throughout a day, whereas the second application deals with obtaining the number of consumers that would be needed in demand response actions for a desired percentage of coverage. Finally, in the third application, a specific hourly strategy is proposed for demand response policies. These applications facilitate the aggregator’s energy purchasing in the market and the planning of subsequent consumption adjustments through demand response to minimize deviations from the purchased energy. The approach is illustrated using hourly demand data from a small Spanish city, and two machine learning methods were used to produce a set of probabilistic forecasts and compare results: Linear Quantile Regression and a Quantile Regression Forest. Main results show a significant reduction in deviations from the purchased energy after applying the proposed strategy, especially in the case of the forecasting method being less accurate (40.95% and 33.62% of reduction, respectively). Full article

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

► Show Figures

Figure 1

27 pages, 12347 KiB

Open AccessArticle

A Deep Learning Approach for Short-Term Electricity Demand Forecasting: Analysis of Thailand Data

by Ranju Kumari Shiwakoti, Chalie Charoenlarpnopparut and Kamal Chapagain

Appl. Sci. 2024, 14(10), 3971; https://doi.org/10.3390/app14103971 - 7 May 2024

Cited by 2 | Viewed by 2112

Abstract

Accurate electricity demand forecasting serves as a vital planning tool, enhancing the reliability of management decisions. Apart from that, achieving these aims, particularly in managing peak demand, faces challenges due to the industry’s volatility and the ongoing increase in residential energy use. Our [...] Read more.

Accurate electricity demand forecasting serves as a vital planning tool, enhancing the reliability of management decisions. Apart from that, achieving these aims, particularly in managing peak demand, faces challenges due to the industry’s volatility and the ongoing increase in residential energy use. Our research suggests that employing deep learning algorithms, such as recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), holds promise for the accurate forecasting of electrical energy demand in time series data. This paper presents the construction and testing of three deep learning models across three separate scenarios. Scenario 1 involves utilizing data from all-day demand. In Scenario 2, only weekday data are considered. Scenario 3 uses data from non-working days (Saturdays, Sundays, and holidays). The models underwent training and testing across a wide range of alternative hyperparameters to determine the optimal configuration. The proposed model’s validation involved utilizing a dataset comprising half-hourly electrical energy demand data spanning seven years from the Electricity Generating Authority of Thailand (EGAT). In terms of model performance, we determined that the RNN-GRU model performed better when the dataset was substantial, especially in scenarios 1 and 2. On the other hand, the RNN-LSTM model is excellent in Scenario 3. Specifically, the RNN-GRU model achieved an MAE (mean absolute error) of 214.79 MW and an MAPE (mean absolute percentage error) of 2.08% for Scenario 1, and an MAE of 181.63 MW and MAPE of 1.89% for Scenario 2. Conversely, the RNN-LSTM model obtained an MAE of 226.76 MW and an MAPE of 2.13% for Scenario 3. Furthermore, given the expanded dataset in Scenario 3, we can anticipate even higher precision in the results. Full article

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

► Show Figures

Figure 1

21 pages, 8324 KiB

Open AccessArticle

Short-Term Load Forecasting Based on Optimized Random Forest and Optimal Feature Selection

by Bianca Magalhães, Pedro Bento, José Pombo, Maria do Rosário Calado and Sílvio Mariano

Energies 2024, 17(8), 1926; https://doi.org/10.3390/en17081926 - 18 Apr 2024

Cited by 7 | Viewed by 1928

Abstract

Short-term load forecasting (STLF) plays a vital role in ensuring the safe, efficient, and economical operation of power systems. Accurate load forecasting provides numerous benefits for power suppliers, such as cost reduction, increased reliability, and informed decision-making. However, STLF is a complex task [...] Read more.

Short-term load forecasting (STLF) plays a vital role in ensuring the safe, efficient, and economical operation of power systems. Accurate load forecasting provides numerous benefits for power suppliers, such as cost reduction, increased reliability, and informed decision-making. However, STLF is a complex task due to various factors, including non-linear trends, multiple seasonality, variable variance, and significant random interruptions in electricity demand time series. To address these challenges, advanced techniques and models are required. This study focuses on the development of an efficient short-term power load forecasting model using the random forest (RF) algorithm. RF combines regression trees through bagging and random subspace techniques to improve prediction accuracy and reduce model variability. The algorithm constructs a forest of trees using bootstrap samples and selects random feature subsets at each node to enhance diversity. Hyperparameters such as the number of trees, minimum sample leaf size, and maximum features for each split are tuned to optimize forecasting results. The proposed model was tested using historical hourly load data from four transformer substations supplying different campus areas of the University of Beira Interior, Portugal. The training data were from January 2018 to December 2021, while the data from 2022 were used for testing. The results demonstrate the effectiveness of the RF model in forecasting short-term hourly and one day ahead load and its potential to enhance decision-making processes in smart grid operations. Full article

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

► Show Figures

Figure 1

27 pages, 10172 KiB

Open AccessArticle

Combined K-Means Clustering with Neural Networks Methods for PV Short-Term Generation Load Forecasting in Electric Utilities

by Alex Sleiman and Wencong Su

Energies 2024, 17(6), 1433; https://doi.org/10.3390/en17061433 - 16 Mar 2024

Cited by 3 | Viewed by 1916

Abstract

The power system has undergone significant growth and faced considerable challenges in recent decades, marked by the surge in energy demand and advancements in smart grid technologies, including solar and wind energies, as well as the widespread adoption of electric vehicles. These developments [...] Read more.

The power system has undergone significant growth and faced considerable challenges in recent decades, marked by the surge in energy demand and advancements in smart grid technologies, including solar and wind energies, as well as the widespread adoption of electric vehicles. These developments have introduced a level of complexity for utilities, compounded by the rapid expansion of behind-the-meter (BTM) photovoltaic (PV) systems, each with its own unique design and characteristics, thereby impacting power grid stability and reliability. In response to these intricate challenges, this research focused on the development of a robust forecasting model for load generation. This precision forecasting is crucial for optimal planning, mitigating the adverse effects of PV systems, and reducing operational and maintenance costs. By addressing these key aspects, the goal is to enhance the overall resilience and efficiency of the power grid amidst the evolving landscape of energy and technological advancements. The authors propose a solution leveraging LSTM (long short-term memory) model for a forecasting horizon up to 168 hours. This approach incorporates combinations of K-means clustering, automated meter infrastructure (AMI) real-world PV load generation, weather data, and calculated solar positions to forecast the generation load at customer locations to achieve a 5.7% mean absolute error between the actual and the predicted generation load. Full article

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

► Show Figures

Figure 1

18 pages, 628 KiB

Open AccessArticle

Short-Term Load Forecasting Using an LSTM Neural Network for a Grid Operator

by Joan Sebastian Caicedo-Vivas and Wilfredo Alfonso-Morales

Energies 2023, 16(23), 7878; https://doi.org/10.3390/en16237878 - 1 Dec 2023

Cited by 18 | Viewed by 3103

Abstract

Electricity is crucial for daily life due to the number of activities that depend on it. To forecast future electric load, which changes over time and depends on various factors, grid operators (GOs) must create forecasting models for various time horizons with a [...] Read more.

Electricity is crucial for daily life due to the number of activities that depend on it. To forecast future electric load, which changes over time and depends on various factors, grid operators (GOs) must create forecasting models for various time horizons with a high degree of accuracy because the results have a huge impact on their decision-making regarding, for example, the scheduling of power units to supply user consumption in the short or long term or the installation of new power plants. This has led to the exploration of multiple techniques like statistical models and Artificial Intelligence (AI), with Machine-Learning and Deep-Learning algorithms being the most popular in this latter field. This paper proposes a neural network-based model to forecast short-term load for a Colombian grid operator, considering a seven-day time horizon and using an LSTM recurrent neural network with historical load values from a region in Colombia and calendar features such as holidays and the current month corresponding to the target week. Unlike other LSTM implementations found in the literature, in this work, the LSTM cells read multiple load measurements at once, and the additional information (holidays and current month) is concatenated to the output of the LSTM. The result is used to feed a fully connected neural network to obtain the desired forecast. Due to social problems in the country, the load data presents a strange behavior, which, in principle, affects the prediction capacity of the model. Still, it is eventually able to adjust its forecasts accordingly. The regression metric MAPE measures the model performance, with the best predicted week having an error of 1.65% and the worst week having an error of 26.22%. Additionally, prediction intervals are estimated using bootstrapping. Full article

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

► Show Figures

Figure 1

17 pages, 3127 KiB

Open AccessArticle

Short-Term Net Load Forecasting for Regions with Distributed Photovoltaic Systems Based on Feature Reconstruction

by Xudong Zheng, Ming Yang, Yixiao Yu and Chuanqi Wang

Appl. Sci. 2023, 13(16), 9064; https://doi.org/10.3390/app13169064 - 8 Aug 2023

Cited by 3 | Viewed by 1499

Abstract

Short-term load forecasting is the guarantee for the safe, stable, and economical operation of power systems. Deep learning methods have been proven effective in obtaining accurate forecasting results. However, in recent years, the large-scale integration of distributed photovoltaic systems (DPVS) has caused changes [...] Read more.

Short-term load forecasting is the guarantee for the safe, stable, and economical operation of power systems. Deep learning methods have been proven effective in obtaining accurate forecasting results. However, in recent years, the large-scale integration of distributed photovoltaic systems (DPVS) has caused changes in load curve fluctuations. Current deep learning models generally train with historical load series and load-related meteorological data series as input features, which limits the model’s ability to recognize the load fluctuations caused by DPVS. In order to further improve the accuracy of load forecasting models, this paper proposes an input feature reconstruction method based on the maximum information coefficient (MIC). Firstly, the load curves with DPVS are classified by Gaussian mixture model (GMM) clustering. Then, considering the coupling relationship between the load and input features at different times, the load data and input features are reordered. Finally, the MIC between different features and loads at different times is calculated to select the relevant features at those different times and construct new input features. The case analysis shows that the feature reconstruction strategy proposed in this paper effectively improves the prediction performance of deep neural networks. Full article

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

► Show Figures

Figure 1

22 pages, 3857 KiB

Open AccessArticle

TS2ARCformer: A Multi-Dimensional Time Series Forecasting Framework for Short-Term Load Prediction

by Songjiang Li, Wenxin Zhang and Peng Wang

Energies 2023, 16(15), 5825; https://doi.org/10.3390/en16155825 - 5 Aug 2023

Cited by 2 | Viewed by 2892

Abstract

Accurately predicting power load is a pressing concern that requires immediate attention. Short-term load prediction plays a crucial role in ensuring the secure operation and analysis of power systems. However, existing research studies have limited capability in extracting the mutual relationships of multivariate [...] Read more.

Accurately predicting power load is a pressing concern that requires immediate attention. Short-term load prediction plays a crucial role in ensuring the secure operation and analysis of power systems. However, existing research studies have limited capability in extracting the mutual relationships of multivariate features in multivariate time series data. To address these limitations, we propose a multi-dimensional time series forecasting framework called TS2ARCformer. The TS2ARCformer framework incorporates the TS2Vec layer for contextual encoding and utilizes the Transformer model for prediction. This combination effectively captures the multi-dimensional features of the data. Additionally, TS2ARCformer introduces a Cross-Dimensional-Self-Attention module, which leverages interactions across channels and temporal dimensions to enhance the extraction of multivariate features. Furthermore, TS2ARCformer leverage a traditional autoregressive component to overcome the issue of deep learning models being insensitive to input scale. This also enhances the model’s ability to extract linear features. Experimental results on two publicly available power load datasets demonstrate significant improvements in prediction accuracy compared to baseline models, with reductions of 43.2% and 37.8% in the aspect of mean absolute percentage error (MAPE) for dataset area1 and area2, respectively. These findings have important implications for the accurate prediction of power load and the optimization of power system operation and analysis. Full article

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

► Show Figures

Figure 1

16 pages, 10260 KiB

Open AccessArticle

Short-Term Load Forecasting Based on Outlier Correction, Decomposition, and Ensemble Reinforcement Learning

by Jiakang Wang, Hui Liu, Guangji Zheng, Ye Li and Shi Yin

Energies 2023, 16(11), 4401; https://doi.org/10.3390/en16114401 - 30 May 2023

Cited by 8 | Viewed by 1891

Abstract

Short-term load forecasting is critical to ensuring the safe and stable operation of the power system. To this end, this study proposes a load power prediction model that utilizes outlier correction, decomposition, and ensemble reinforcement learning. The novelty of this study is as [...] Read more.

Short-term load forecasting is critical to ensuring the safe and stable operation of the power system. To this end, this study proposes a load power prediction model that utilizes outlier correction, decomposition, and ensemble reinforcement learning. The novelty of this study is as follows: firstly, the Hampel identifier (HI) is employed to correct outliers in the original data; secondly, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to extract the waveform characteristics of the data fully; and, finally, the temporal convolutional network, extreme learning machine, and gate recurrent unit are selected as the basic learners for forecasting load power data. An ensemble reinforcement learning algorithm based on Q-learning was adopted to generate optimal ensemble weights, and the predictive results of the three basic learners are combined. The experimental results of the models for three real load power datasets show that: (a) the utilization of HI improves the model’s forecasting result; (b) CEEMDAN is superior to other decomposition algorithms in forecasting performance; and (c) the proposed ensemble method, based on the Q-learning algorithm, outperforms three single models in accuracy, and achieves smaller prediction errors. Full article

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

► Show Figures

Figure 1

21 pages, 4310 KiB

Open AccessArticle

Interval Load Forecasting for Individual Households in the Presence of Electric Vehicle Charging

by Raiden Skala, Mohamed Ahmed T. A. Elgalhud, Katarina Grolinger and Syed Mir

Energies 2023, 16(10), 4093; https://doi.org/10.3390/en16104093 - 15 May 2023

Cited by 9 | Viewed by 1876

Abstract

The transition to Electric Vehicles (EV) in place of traditional internal combustion engines is increasing societal demand for electricity. The ability to integrate the additional demand from EV charging into forecasting electricity demand is critical for maintaining the reliability of electricity generation and [...] Read more.

The transition to Electric Vehicles (EV) in place of traditional internal combustion engines is increasing societal demand for electricity. The ability to integrate the additional demand from EV charging into forecasting electricity demand is critical for maintaining the reliability of electricity generation and distribution. Load forecasting studies typically exclude households with home EV charging, focusing on offices, schools, and public charging stations. Moreover, they provide point forecasts which do not offer information about prediction uncertainty. Consequently, this paper proposes the Long Short-Term Memory Bayesian Neural Networks (LSTM-BNNs) for household load forecasting in presence of EV charging. The approach takes advantage of the LSTM model to capture the time dependencies and uses the dropout layer with Bayesian inference to generate prediction intervals. Results show that the proposed LSTM-BNNs achieve accuracy similar to point forecasts with the advantage of prediction intervals. Moreover, the impact of lockdowns related to the COVID-19 pandemic on the load forecasting model is examined, and the analysis shows that there is no major change in the model performance as, for the considered households, the randomness of the EV charging outweighs the change due to pandemic. Full article

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

► Show Figures

Figure 1

20 pages, 5908 KiB

Open AccessArticle

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

by Bilin Shao, Zixuan Yao and Yifan Qiang

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

Cited by 2 | Viewed by 1949

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 [...] Read more.

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

30 pages, 4652 KiB

Open AccessArticle

Forecasting Short-Term Electricity Load Using Validated Ensemble Learning

by Chatum Sankalpa, Somsak Kittipiyakul and Seksan Laitrakun

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

Cited by 9 | Viewed by 2299

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 [...] Read more.

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

22 pages, 4390 KiB

Open AccessArticle

Automatic Selection of Temperature Variables for Short-Term Load Forecasting

by 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

Cited by 4 | Viewed by 1828

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 [...] Read more.

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

18 pages, 2449 KiB

Open AccessArticle

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

by Yun Duan

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

Cited by 9 | Viewed by 2351

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 [...] Read more.

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

19 pages, 7388 KiB

Open AccessArticle

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

by Fan Yu, Lei Wang, Qiaoyong Jiang, Qunmin Yan and Shi Qiao

Energies 2022, 15(12), 4198; https://doi.org/10.3390/en15124198 - 7 Jun 2022

Cited by 7 | Viewed by 2444

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 [...] Read more.

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

Topic Menu

Topic Editors

Short-Term Load Forecasting

Topic Information

Keywords

Participating Journals

Published Papers (15 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Topic Menu

Topic Editors

Short-Term Load Forecasting

Topic Information

Keywords

Participating Journals

Related Topic

Published Papers (15 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI