Short Term Load Forecasting using SVM Models

Khan, Rizwan Ahmed; Dewangan, Chaman Lal; Srivastava, Suresh C.; Chakrabarti, Saikat

doi:10.1109/poweri.2018.8704366

Cited by 12 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the SVM model excels in addressing various challenges (e.g., local minima, high minima, and smaller sample sizes). Figure 6 illustrates the essential structure for the SVM method [67]: The nonlinear regression function expression is given as Equation ( 1):…”

Section: Supervised ML Modelmentioning

confidence: 99%

A Comprehensive Review of Behind-the-Meter Distributed Energy Resources Load Forecasting: Models, Challenges, and Emerging Technologies

Zaboli,

Kasimalla,

Park

et al. 2024

Energies

View full text Add to dashboard Cite

Behind the meter (BTM) distributed energy resources (DERs), such as photovoltaic (PV) systems, battery energy storage systems (BESSs), and electric vehicle (EV) charging infrastructures, have experienced significant growth in residential locations. Accurate load forecasting is crucial for the efficient operation and management of these resources. This paper presents a comprehensive survey of the state-of-the-art technologies and models employed in the load forecasting process of BTM DERs in recent years. The review covers a wide range of models, from traditional approaches to machine learning (ML) algorithms, discussing their applicability. A rigorous validation process is essential to ensure the model’s precision and reliability. Cross-validation techniques can be utilized to reduce overfitting risks, while using multiple evaluation metrics offers a comprehensive assessment of the model’s predictive capabilities. Comparing the model’s predictions with real-world data helps identify areas for improvement and further refinement. Additionally, the U.S. Energy Information Administration (EIA) has recently announced its plan to collect electricity consumption data from identified U.S.-based crypto mining companies, which can exhibit abnormal energy consumption patterns due to rapid fluctuations. Hence, some real-world case studies have been presented that focus on irregular energy consumption patterns in residential buildings equipped with BTM DERs. These abnormal activities underscore the importance of implementing robust anomaly detection techniques to identify and address such deviations from typical energy usage profiles. Thus, our proposed framework, presented in residential buildings equipped with BTM DERs, considering smart meters (SMs). Finally, a thorough exploration of potential challenges and emerging models based on artificial intelligence (AI) and large language models (LLMs) is suggested as a promising approach.

show abstract

Section: Supervised ML Modelmentioning

confidence: 99%

A Comprehensive Review of Behind-the-Meter Distributed Energy Resources Load Forecasting: Models, Challenges, and Emerging Technologies

Zaboli,

Kasimalla,

Park

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…We and 4) Coefficient of the determinant (R 2 ). The mathematical representations these metrics are shown in equations (8,9,10,11).…”

Section: Evaluation Criteriamentioning

confidence: 99%

“…The AI methods, on the other hand, use a variety of algorithms to learn non-linear patterns and relationships in historical data and use them to make predictions about future load demand. Machine Learning (ML) models such as Artificial Neural Network (ANN) [10], Support Vector Machine (SVM) [11], Fuzzy model [12], and Ensemble models [13] can overcome the shortcoming of the time series models due to their ability to handle complex and dynamic load patterns. They also trained very fast, albeit with the requirement of handcrafted features.…”

Section: Introductionmentioning

confidence: 99%

P-ConvLSTM: An Effective Parallel ConvLSTM-based model for Short-term Electricity Load Forecasting

Kshetrimayum,

Singh,

Hoque

2023

Preprint

View full text Add to dashboard Cite

Short-term Load Forecasting (STLF) is a challenging task for an Energy Management System (EMS) that depends on highly unpredictable and volatile factors, making it difficult to predict the electricity load demand accurately. Despite the challenges, it is an essential component, as it helps to ensure energy demand-supply equilibrium, prevents blackouts, reduces the need for expensive peak power generation, and improves the efficiency and reliability of the EMS. Motivated by these factors, we have proposed a novel STLF framework using a multi-input parallel ConvLSTM model. The effectiveness of the proposed model is verified using two publicly available load-series datasets. On the Malaysia dataset, the proposed model yields 998.12, 2.59%, 1590.34, and 0.987 for MAE, MAPE, RMSE, and R2, respectively. Similarly, on the Tetouan dataset, this model yields 1737.32, 2.49%, 2254.91, and 0.976 for MAE, MAPE, RMSE, and R2, respectively. These outperforming results found in the comparative experiments are further statistically verified using Friedman's test. The presenting framework of STLF can help EMS to make informed decisions about resource allocation and system operations.

show abstract

“…Over the last two decades, several approaches have been developed to attempt to predict an accurate forecasting for immediate and short-term load forecasting (STLF). Prediction approaches can be categorised into physical approaches, statistical methods, artificial intelligent models and hybrid power production forecasters [8][9][10][11][12][13][14][15][16][17][18][19][20][21]. The main approaches for STLF can be split into three categories: neural networks (NN) [8,[13][14][15][16][17][18][19][20][21] and support vector machines (SVM) [9][10][11][12][22][23][24] or a combination of several NN or SVM or both [12,16,19,[25][26][27][28].…”

Section: Introductionmentioning

confidence: 99%

“…Prediction approaches can be categorised into physical approaches, statistical methods, artificial intelligent models and hybrid power production forecasters [8][9][10][11][12][13][14][15][16][17][18][19][20][21]. The main approaches for STLF can be split into three categories: neural networks (NN) [8,[13][14][15][16][17][18][19][20][21] and support vector machines (SVM) [9][10][11][12][22][23][24] or a combination of several NN or SVM or both [12,16,19,[25][26][27][28]. Important to know is that no matter which models and algorithms are adopted into the STLF, the main focus of all research efforts is aimed at providing assurances that the forecasted loads matches the actual loads as much as possible.…”

Section: Introductionmentioning

confidence: 99%

A post‐forecast weighing algorithm to improve wind power forecasting capabilities

Pijnenburg

Cao

Chang

et al. 2022

IET Renewable Power Gen

View full text Add to dashboard Cite

Wind power generation has had a profound impact on both the green power and traditional power sectors. As a result, wind power forecasting plays an immense role in effectively predicting and providing wind power generated for effective power dispatching for system operators. However, wind power forecasting is a challenging topic with accuracy issues between the predicted power and actual power generation at the point of common coupling. Furthermore, due to the variation of wind, effective dispatching through the utilisation of wind power production forecasting becomes a challenge. This issue is further compounded by the vast amount of data required to train and verify of these forecasting algorithms. This paper presents a fast acting post forecast weighing algorithm designed to evaluate the forecasted power output of a previously developed wind power forecasting package. The developed method is designed to gauge and improve the estimated output forecaster's approach in order to observe performance changes in the algorithm while using minimal data without changing the internal workings of the evaluated forecasting algorithm.

show abstract

Short Term Load Forecasting using SVM Models

Cited by 12 publications

References 14 publications

A Comprehensive Review of Behind-the-Meter Distributed Energy Resources Load Forecasting: Models, Challenges, and Emerging Technologies

A Comprehensive Review of Behind-the-Meter Distributed Energy Resources Load Forecasting: Models, Challenges, and Emerging Technologies

P-ConvLSTM: An Effective Parallel ConvLSTM-based model for Short-term Electricity Load Forecasting

A post‐forecast weighing algorithm to improve wind power forecasting capabilities

Contact Info

Product

Resources

About