Electricity Load Forecasting using Hybrid Datasets with Linear Interpolation and Synthetic Data DOI Open Access

Karma P. Dorji,

Sorawut Jittanon,

Prapita Thanarak

et al.

Engineering Technology & Applied Science Research, Journal Year: 2024, Volume and Issue: 14(6), P. 17931 - 17938

Published: Dec. 2, 2024

Electricity load forecasting is an important aspect of power system management. Improving accuracy ensures reliable electricity supply, grid operations, and cost savings. Often, collected data consist Missing Values (MVs), anomalies, outliers, or other inconsistencies caused by failures, metering errors, collection hardware network unexpected events. This study uses real-world to investigate the possibility using synthetically generated as alternative filling in MVs. Three datasets were created from original one based on different imputation methods. The methods employed linear interpolation, synthetic data, a proposed hybrid method interpolation data. performance three was compared deep learning, machine statistical models verified improvements. findings demonstrate that dataset outperformed models.

Language: Английский

Impact of Artificial Intelligence on the Planning and Operation of Distributed Energy Systems in Smart Grids DOI Creative Commons
Paúl Arévalo, Francisco Jurado

Energies, Journal Year: 2024, Volume and Issue: 17(17), P. 4501 - 4501

Published: Sept. 8, 2024

This review paper thoroughly explores the impact of artificial intelligence on planning and operation distributed energy systems in smart grids. With rapid advancement techniques such as machine learning, optimization, cognitive computing, new opportunities are emerging to enhance efficiency reliability electrical From demand generation prediction flow optimization load management, is playing a pivotal role transformation infrastructure. delves deeply into latest advancements specific applications within context systems, including coordination resources, integration intermittent renewable energies, enhancement response. Furthermore, it discusses technical, economic, regulatory challenges associated with implementation intelligence-based solutions, well ethical considerations related automation autonomous decision-making sector. comprehensive analysis provides detailed insight how reshaping grids highlights future research development areas that crucial for achieving more efficient, sustainable, resilient system.

Language: Английский

Citations

15

Guiding Urban Decision-Making: A Study on Recommender Systems in Smart Cities DOI Open Access
Andra Sandu, Liviu‐Adrian Cotfas, Aurelia Stănescu

et al.

Electronics, Journal Year: 2024, Volume and Issue: 13(11), P. 2151 - 2151

Published: May 31, 2024

In recent years, the research community has increasingly embraced topics related to smart cities, recognizing their potential enhance residents’ quality of life and create sustainable, efficient urban environments through integration diverse systems services. Concurrently, recommender have demonstrated continued improvement in accuracy, delivering more precise recommendations for items or content aiding users decision-making processes. This paper explores utilization context cities by analyzing a dataset comprised papers indexed ISI Web Science database. Through bibliometric analysis, key themes, trends, prominent authors institutions, preferred journals, collaboration networks among were extracted. The findings revealed an average annual scientific production growth 25.85%. Additionally, n-gram analysis across keywords, abstracts, titles, keywords plus, along with review selected papers, enriched analysis. insights gained from these efforts offer valuable perspectives, contribute identifying pertinent issues, provide guidance on trends this evolving field. importance lies ability living providing personalized recommendations, optimizing resource utilization, improving processes, ultimately contributing sustainable intelligent environment.

Language: Английский

Citations

10

The application of collective intelligence in the construction industry: a review of the current state, challenges, and opportunities DOI
Shitao Jin

Architectural Engineering and Design Management, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 26

Published: March 11, 2025

Language: Английский

Citations

1

Explainable hybrid forecasting model for a 4-node smart grid stability DOI
Taher M. Ghazal, Mohammad Kamrul Hasan, Rosilah Hassan

et al.

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 4948 - 4961

Published: April 24, 2025

Language: Английский

Citations

0

Security and Privacy in Networks and Multimedia DOI Open Access
Tomasz Rak, Dariusz Rzońca

Electronics, Journal Year: 2024, Volume and Issue: 13(15), P. 2887 - 2887

Published: July 23, 2024

The digital era has significantly transformed the dissemination of information and business operations, creating an intricate web interconnected systems [...]

Language: Английский

Citations

0

Radian Scaling and Its Application to Enhance Electricity Load Forecasting in Smart Cities Against Concept Drift DOI Creative Commons
Mohd Hafizuddin Bin Kamilin, Shingo Yamaguchi, Mohd Anuaruddin Bin Ahmadon

et al.

Smart Cities, Journal Year: 2024, Volume and Issue: 7(6), P. 3412 - 3436

Published: Nov. 8, 2024

In a real-world implementation, machine learning models frequently experience concept drift when forecasting the electricity load. This is due to seasonal changes influencing scale, mean, and median values found in input data, changing their distribution. Several methods have been proposed solve this, such as implementing automated model retraining, feature engineering, ensemble learning. The biggest drawback, however, that they are too complex for simple implementation existing projects. Since drifted data follow same pattern training dataset terms of having different values, radian scaling was new way scale without relying on these values. It works by converting difference between two sequential into compute, removing bounding, allowing forecast beyond scale. experiment, not only does constrained gated recurrent unit with shorter average epochs, but it also lowers root mean square error from 158.63 43.375, outperforming best normalization method 72.657%.

Language: Английский

Citations

0

Electricity Load Forecasting using Hybrid Datasets with Linear Interpolation and Synthetic Data DOI Open Access

Karma P. Dorji,

Sorawut Jittanon,

Prapita Thanarak

et al.

Engineering Technology & Applied Science Research, Journal Year: 2024, Volume and Issue: 14(6), P. 17931 - 17938

Published: Dec. 2, 2024

Electricity load forecasting is an important aspect of power system management. Improving accuracy ensures reliable electricity supply, grid operations, and cost savings. Often, collected data consist Missing Values (MVs), anomalies, outliers, or other inconsistencies caused by failures, metering errors, collection hardware network unexpected events. This study uses real-world to investigate the possibility using synthetically generated as alternative filling in MVs. Three datasets were created from original one based on different imputation methods. The methods employed linear interpolation, synthetic data, a proposed hybrid method interpolation data. performance three was compared deep learning, machine statistical models verified improvements. findings demonstrate that dataset outperformed models.

Language: Английский

Citations

0