SPSO-DBN based compensation algorithm for lackness of electric energy metering in micro-grid

Gao, Jinggeng; Wang, Xinggui; Yang, Weiman

doi:10.1016/j.aej.2021.10.018

Cited by 6 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(BP) (Bian et al, 2020), convolutional neural network (CNN) (Imani, 2021;Zhang et al, 2021), artificial neural network (ANN) (Xiao et al, 2022;Sa'ad et al, 2022;Aly, 2020), LSTM networks (Bouktif et al, 2018;Kong et al, 2019;Yu et al, 2019;Memarzadeh and Keynia, 2021;Peng et al, 2022;Zhaorui Meng and Xie, 2022), support vector machine (SVM) (Xia et al, 2018;Mayur Barman, 2020), extreme learning machine (ELM) (Chen et al, 2020;Jeddi and Sharifian, 2020;Sahu et al, 2021;Krishna Rayi et al, 2022), and deep belief network (DBN) (Gao et al, 2022;Hong et al, 2022). Using only a neural network for load forecasting faces several limitations since it cannot fully utilize historical data for learning and generalization.…”

Section: Figurementioning

confidence: 99%

An improved LSTM-Seq2Seq-based forecasting method for electricity load

Wang

Zheng

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

Power load forecasting has gained considerable research interest in recent years. The power load is vulnerable to randomness and uncertainty during power grid operations. Therefore, it is crucial to effectively predict the electric load and improve the accuracy of the prediction. This study proposes a novel power load forecasting method based on an improved long short-term memory (LSTM) neural network. Thus, an long short-term memory neural network model is established for power load forecasting, which supports variable-length inputs and outputs. The conventional convolutional neural network (CNN) and recurrent neural network (RNN) cannot reflect the sequence dependence between the output labels. Therefore, the LSTM-Seq2Seq prediction model was established by combining the sequence-to-sequence (Seq2Seq) structure with that of the long short-term memory model to improve the prediction accuracy. Four prediction models, i.e., long short-term memory, deep belief network (DBN), support vector machine (SVM), and LSTM-Seq2Seq, were simulated and tested on two different datasets. The results demonstrated the effectiveness of the proposed LSTM-Seq2Seq method. In the future, this model can be extended to more prediction application scenarios.

show abstract

Section: Figurementioning

confidence: 99%

An improved LSTM-Seq2Seq-based forecasting method for electricity load

Wang

Zheng

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

show abstract

“…In recent years, the power company has actively promoted the construction of metering automation system, and now has built more than 4 million different types of power energy data collection field terminals, which have realized load forecasting and control, electricity monitoring and abnormal analysis, anti-theft, "quarter" line loss statistics, and customer demand side management services for local power supply bureaus. With an advanced and efficient technical method [1]. However, due to the increasing scale of power metering automation system, the maintenance and overhaul of on-site equipment is increasingly difficult.…”

Section: Introductionmentioning

confidence: 99%

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

Yan Liu, Chaoran Bi, Yaoyu Wang

2024

jes

View full text Add to dashboard Cite

In view of the great pressure of operation and maintenance of power energy data collection terminal after putting into operation, an intelligent fault diagnosis system for power equipment terminal based on computer was developed. This paper proposes an Agent based on autonomy, promotility, cooperation and interactivity. It also provides a flexible interactive communication interface and load balancing optimization method. It can meet a variety of data transmission specifications and a large number of data service transmission requirements. The SA-KNN algorithm is used to analyze the power quality. Methods The operation data of maintenance electricity were collected. Learning and cluster analysis are carried out by using relevant data, and the calculation model of automatic check device failure is established. At the same time, the outlier points in the collected data are used to accurately locate the fault points of the power grid. This method can realize the comprehensive fault diagnosis of the power grid by using the interaction between the power grid and each component.

show abstract

“…After the concept of IoT was proposed, scholars started to use IoT technology in different fields. Concepts such as smart medical healthcare [2,3], smart buildings [4,5], smart grid [6,7], and smart transportation [8,9] have begun to be proposed. e Industrial Internet of ings (IIoT) means the use of IoT technology in the industry, which makes industrial manufacturing intelligent [10,11].…”

Section: Introductionmentioning

confidence: 99%

Construction of a Smart Supply Chain for Sand Factory Using the Edge-Computing-Based Deep Learning Algorithm

Zhang

Ban

et al. 2022

Scientific Programming

View full text Add to dashboard Cite

The diminishing natural sand has facilitated the booming of the sand manufacturing industry, and intelligent management of sand factories, in a time- and cost-efficient way, has become a growing tendency for the future. A role has been played in achieving intelligent management by constructing a smart supply chain. However, the smart sand factories are hardly involved in previously reported studies, which is inconsistent with related studies on smart factories and the Industrial Internet of Things (IIoT). In this paper, a smart supply chain management system (SSCMS) is constructed to realize the intelligence and automatization of the management of sand factories, using edge-computing and deep learning techniques. Along the supply chain, the deep learning model is used to realize the automatic identification of sand, avoiding the disadvantages of human identification, while improving the quality of sand factory operations. In order to relieve the pressure of network bandwidth, reduce system delay, and improve system operation efficiency, we use edge-computing technology to process data at the edge. To verify the performance of the constructed system, a sand factory simulation platform is established. Experiments show that the most critical indicator in the system, the accuracy rate of sand type identification, is above 98%, and the sand type identification time is only 0.022 s. In general, compared with traditional supply chain management, the constructed smart supply chain improves the quality and efficiency of sand factory operations, and all indicators of the designed system have achieved satisfactory results.

show abstract

SPSO-DBN based compensation algorithm for lackness of electric energy metering in micro-grid

Cited by 6 publications

References 27 publications

An improved LSTM-Seq2Seq-based forecasting method for electricity load

An improved LSTM-Seq2Seq-based forecasting method for electricity load

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

Construction of a Smart Supply Chain for Sand Factory Using the Edge-Computing-Based Deep Learning Algorithm

Contact Info

Product

Resources

About