Forecasting short-term electric load using extreme learning machine with improved tree seed algorithm based on Lévy flight

Chen, Xuan; Przystupa, Krzysztof; Ye, Zhiwei; Chen, Feng; Wang, Chunzhi; Liu, Jinhang; Gao, Rong; Wei, Ming; Кочан, Орест

doi:10.17531/ein.2022.1.17

Cited by 19 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, considering the sparsity of power load data, KPCA extraction was performed on the input data. The proposed method had superiority compared with other methods [7]. KEMICHE M et al used ELM to recognize handwritten characters in Berber language.…”

Section: Related Workmentioning

confidence: 95%

The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data

Wang,

Li,

Zhang

2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

As one of the core equipment of the power grid, the operation status of transformers directly affects the stability and reliability of the power system. To accurately evaluate the remaining life of power grid transformers, a genetic algorithm is applied to optimize the Extreme Learning Machine based on digital twin technology. Then, considering changes in load rate, a residual life prediction model for power grid transformers is constructed. From the results, the error of the research method was within 2℃, with a maximum error of only 1.76℃. The research model converged with a fitness value of 0.04 at 150 iterations. It showed good predictive performance for hot spot temperatures under different load rates, with an average accuracy of 99.97%. Compared with backpropagation models and extreme learning machine models, the research method improved accuracy by 2.85% and 1.01%, respectively, with small and stable prediction errors. It verified the superiority of the research model, indicating that the research method can improve the accuracy of predicting the remaining life for power grid transformers. By monitoring the operation status of transformers in real-time, potential faults can be detected in a timely manner. The maintenance and replacement can be carried out in advance to avoid power outages caused by equipment damage. In addition, the research can provide reference for the planning and design of power systems, and support the stability and reliability of power systems.

show abstract

Section: Related Workmentioning

confidence: 95%

The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data

Wang,

Li,

Zhang

2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

show abstract

“…Therefore, different optimization algorithms were used to determine the PID controller parameters and the results are presented below in the paper. Stochastic and hybrid algorithms are often used in the issues of reliability and maintenance, but this was not the case before for active foil bearings [15,52].…”

Section: Fig 1 Automatic Control System Making Use Of a Pid Controllermentioning

confidence: 99%

Comparable analysis of PID controller settings in order to ensure reliable operation of active foil bearings

Witanowski¹,

Breńkacz²,

Szewczuk-Krypa³

et al. 2022

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

In comparison to the traditional solutions, active bearings offer great operating flexibility, ensure better operating conditions over a wider range of rotational speeds and are safe to use. In order to ensure optimum bearing performance a bearing control system is used that adapts different geometries during device operation. The selection of optimal controller parameters requires the use of modern optimization methods that make it possible to quickly achieve the assumed parameters. This article presents the method that has been employed to select the parameters of a proportional integral derivative (PID) controller, in which both stochastic algorithms and hybrid methods have been compared. The results show that all of the used algorithms were able to reach the global optimum but only the hybrid algorithm was repeatable in all runs within a low value of the standard deviation. The best solution will be proposed in the future to control an active foil bearing. Analysing of this paper would help to prevent failures of active foil bearing used in the designed rotating machine.

show abstract

“…Extreme learning machine (ELM), as a new neural network algorithm with strong and fast learning ability, is commonly used in short-term wind power prediction. Chen et al 9 used principal component analysis, tree seeding algorithm, and extreme learning machine to compose a short-term compliance prediction model for power compliance prediction and achieved good results. Xia and Wang 10 proposed a combined IMVO-ELM prediction model to improve the prediction accuracy of short-term wind speed.…”

Section: Introductionmentioning

confidence: 99%

A novel combined intelligent algorithm prediction model for the tunnel surface settlement

Wang,

Dai,

Jia

et al. 2023

Sci Rep

View full text Add to dashboard Cite

To ensure the safety and stability of the shield tunnel construction process, the ground settlement induced by the shield construction needs to be effectively predicted. In this paper, a prediction method combining empirical mode decomposition (EMD), chaotic adaptive sparrow search algorithm (CASSA), and extreme learning machine (ELM) is proposed. First, the EMD is used to decompose the settlement sequence into trend vectors and fluctuation vectors to fully extract the effective information of the sequence; Second, the sparrow search algorithm is improved by introducing Cubic chaotic mapping to initialize the population and adaptive factor to optimize the searcher’s position formula, and the chaotic adaptive sparrow search algorithm is proposed; Finally, the CASSA-ELM prediction model is constructed by using CASSA to find the optimal values of weights and thresholds in the extreme learning machine. The fluctuation components and trend components decomposed by EMD are predicted one by one, and the prediction results are superimposed and reconstructed to obtain the predicted final settlement. Taking a shield interval in Jiangsu, China as an example, the meta-heuristic algorithm-optimized ELM model improves the prediction accuracy by 10.70% compared with the traditional ELM model. The combined EMD-CASSA-ELM prediction model can greatly improve the accuracy and speed of surface settlement prediction, and provide a new means for safety monitoring in shield tunnel construction. Intelligent prediction methods can predict surface subsidence more automatically and quickly, becoming a new development trend.

show abstract

Forecasting short-term electric load using extreme learning machine with improved tree seed algorithm based on Lévy flight

Cited by 19 publications

References 60 publications

The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data

The residual life prediction of power grid transformers based on GA-ELM computational model and digital twin data

Comparable analysis of PID controller settings in order to ensure reliable operation of active foil bearings

A novel combined intelligent algorithm prediction model for the tunnel surface settlement

Contact Info

Product

Resources

About