As a commonly used mode of transportation in people’s daily lives, the normal operation of railway transportation is crucial. The track circuit, as a key component of the railway transportation system, is prone to malfunctions due to environmental factors. However, the current method of inspecting track circuit faults still relies on the experience of on-site personnel. In order to improve the efficiency and accuracy of fault diagnosis, we propose to establish an intelligent fault diagnosis system. Considering that the fault data are a one-dimensional time series, this paper presents a fault diagnosis method based on the UNet-LSTM network (ULN). The LSTM network is established on the basis of fault data and used for ZPW-2000A track circuit fault diagnosis. However, the use of a single LSTM network has a high error rate in the common fault diagnosis of track circuits. Therefore, this paper proposes a feature extraction method based on the UNet network. This method is used to extract the features of the original data and then input them into the LSTM network for fault diagnosis. Through experiments with on-site fault data, it has been verified that this method can accurately classify seven common track circuit faults. Finally, the superiority of the method is verified by comparing it with other commonly used fault classification methods.
{"title":"Track Circuits Fault Diagnosis Method Based on the UNet-LSTM Network (ULN)","authors":"Weijie Tao, Xiaowei Li, Zheng Li","doi":"10.1155/2024/1547428","DOIUrl":"https://doi.org/10.1155/2024/1547428","url":null,"abstract":"As a commonly used mode of transportation in people’s daily lives, the normal operation of railway transportation is crucial. The track circuit, as a key component of the railway transportation system, is prone to malfunctions due to environmental factors. However, the current method of inspecting track circuit faults still relies on the experience of on-site personnel. In order to improve the efficiency and accuracy of fault diagnosis, we propose to establish an intelligent fault diagnosis system. Considering that the fault data are a one-dimensional time series, this paper presents a fault diagnosis method based on the UNet-LSTM network (ULN). The LSTM network is established on the basis of fault data and used for ZPW-2000A track circuit fault diagnosis. However, the use of a single LSTM network has a high error rate in the common fault diagnosis of track circuits. Therefore, this paper proposes a feature extraction method based on the UNet network. This method is used to extract the features of the original data and then input them into the LSTM network for fault diagnosis. Through experiments with on-site fault data, it has been verified that this method can accurately classify seven common track circuit faults. Finally, the superiority of the method is verified by comparing it with other commonly used fault classification methods.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139808101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Unpredictable variations in load demand and unanticipated component failures are progressively impacting the operation of modern power systems, making system evaluation more stochastic in nature. Although deterministic approaches were formerly the norm for determining system status, probabilistic approaches have greatly improved the capacity to capture the stochastic behavior characteristic of power system operations. The presented work in the paper recommends the use of probabilistic modelling approaches with deterministic approaches, highlighting their crucial function in augmenting the reliability and security of contemporary power systems to unanticipated failures. In this paper, N − 1 security criteria based reliability of the composite power system (CPS) is proposed using an integrated deterministic and probabilistic framework (D-P) considering outage of the transmission line. For the deterministic approach (DA), line overloading on available lines is determined using the static security index (SSI). For the probabilistic approach (PA), reliability indices such as expected loss of power (ELOP), expected frequency of contingency (EFOC), expected loss of load (ELOL), probability of load curtailment (PLC), and expected duration of load curtailments (EDLC) are calculated. Further, for each contingency, a performance index is determined using both approaches to assess the severity of the contingency that occurred on the power system. Based on the N − 1 security criteria based reliability analysis using an integrated D-P framework, a credible critical set of transmission lines is obtained, which can serve as important information to system operators. The proposed techniques have been tested on IEEE 24 bus reliability test system (RTS).
{"title":"N − 1 Security Criteria Based Integrated Deterministic and Probabilistic Framework for Composite Power System Reliability","authors":"Tanmay Jain, Kusum Verma, Mahendra Bhadu","doi":"10.1155/2024/5518874","DOIUrl":"https://doi.org/10.1155/2024/5518874","url":null,"abstract":"Unpredictable variations in load demand and unanticipated component failures are progressively impacting the operation of modern power systems, making system evaluation more stochastic in nature. Although deterministic approaches were formerly the norm for determining system status, probabilistic approaches have greatly improved the capacity to capture the stochastic behavior characteristic of power system operations. The presented work in the paper recommends the use of probabilistic modelling approaches with deterministic approaches, highlighting their crucial function in augmenting the reliability and security of contemporary power systems to unanticipated failures. In this paper, N − 1 security criteria based reliability of the composite power system (CPS) is proposed using an integrated deterministic and probabilistic framework (D-P) considering outage of the transmission line. For the deterministic approach (DA), line overloading on available lines is determined using the static security index (SSI). For the probabilistic approach (PA), reliability indices such as expected loss of power (ELOP), expected frequency of contingency (EFOC), expected loss of load (ELOL), probability of load curtailment (PLC), and expected duration of load curtailments (EDLC) are calculated. Further, for each contingency, a performance index is determined using both approaches to assess the severity of the contingency that occurred on the power system. Based on the N − 1 security criteria based reliability analysis using an integrated D-P framework, a credible critical set of transmission lines is obtained, which can serve as important information to system operators. The proposed techniques have been tested on IEEE 24 bus reliability test system (RTS).","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139882288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Unpredictable variations in load demand and unanticipated component failures are progressively impacting the operation of modern power systems, making system evaluation more stochastic in nature. Although deterministic approaches were formerly the norm for determining system status, probabilistic approaches have greatly improved the capacity to capture the stochastic behavior characteristic of power system operations. The presented work in the paper recommends the use of probabilistic modelling approaches with deterministic approaches, highlighting their crucial function in augmenting the reliability and security of contemporary power systems to unanticipated failures. In this paper, N − 1 security criteria based reliability of the composite power system (CPS) is proposed using an integrated deterministic and probabilistic framework (D-P) considering outage of the transmission line. For the deterministic approach (DA), line overloading on available lines is determined using the static security index (SSI). For the probabilistic approach (PA), reliability indices such as expected loss of power (ELOP), expected frequency of contingency (EFOC), expected loss of load (ELOL), probability of load curtailment (PLC), and expected duration of load curtailments (EDLC) are calculated. Further, for each contingency, a performance index is determined using both approaches to assess the severity of the contingency that occurred on the power system. Based on the N − 1 security criteria based reliability analysis using an integrated D-P framework, a credible critical set of transmission lines is obtained, which can serve as important information to system operators. The proposed techniques have been tested on IEEE 24 bus reliability test system (RTS).
{"title":"N − 1 Security Criteria Based Integrated Deterministic and Probabilistic Framework for Composite Power System Reliability","authors":"Tanmay Jain, Kusum Verma, Mahendra Bhadu","doi":"10.1155/2024/5518874","DOIUrl":"https://doi.org/10.1155/2024/5518874","url":null,"abstract":"Unpredictable variations in load demand and unanticipated component failures are progressively impacting the operation of modern power systems, making system evaluation more stochastic in nature. Although deterministic approaches were formerly the norm for determining system status, probabilistic approaches have greatly improved the capacity to capture the stochastic behavior characteristic of power system operations. The presented work in the paper recommends the use of probabilistic modelling approaches with deterministic approaches, highlighting their crucial function in augmenting the reliability and security of contemporary power systems to unanticipated failures. In this paper, N − 1 security criteria based reliability of the composite power system (CPS) is proposed using an integrated deterministic and probabilistic framework (D-P) considering outage of the transmission line. For the deterministic approach (DA), line overloading on available lines is determined using the static security index (SSI). For the probabilistic approach (PA), reliability indices such as expected loss of power (ELOP), expected frequency of contingency (EFOC), expected loss of load (ELOL), probability of load curtailment (PLC), and expected duration of load curtailments (EDLC) are calculated. Further, for each contingency, a performance index is determined using both approaches to assess the severity of the contingency that occurred on the power system. Based on the N − 1 security criteria based reliability analysis using an integrated D-P framework, a credible critical set of transmission lines is obtained, which can serve as important information to system operators. The proposed techniques have been tested on IEEE 24 bus reliability test system (RTS).","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139822216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rong Chang, Zhengxiong Mao, Jian Hu, Haicheng Bai, Anning Pan, Yang Yang, Shan Gao
Fire in power equipment has always been one of the main hazards of power equipment. Smoke detection and recognition have always been extremely important in power equipment, as they can provide early warning before a fire breaks out. Compared to relying on smoke concentration for recognition, image-based smoke recognition has the advantage of being unaffected by indoor and outdoor environments. This paper addresses the problems of limited smoke data, difficult labeling, and insufficient research on recognition algorithms in power systems. We propose using three-dimensional virtual technology to generate smoke and image masks and using environmental backgrounds such as HDR (high dynamic range imaging) lighting to realistically combine smoke and background. In addition, to address the characteristics of smoke in power equipment, a dual UNet model named DS-UNet is proposed. The model consists of a deep and a shallow network structure, which can effectively segment the details of smoke in power equipment and handle partial occlusion. Finally, DS-UNet is compared with other smoke segmentation networks with similar structures, and it demonstrates better smoke segmentation performance.
{"title":"Generation of Smoke Dataset for Power Equipment and Study of Image Semantic Segmentation","authors":"Rong Chang, Zhengxiong Mao, Jian Hu, Haicheng Bai, Anning Pan, Yang Yang, Shan Gao","doi":"10.1155/2024/9298478","DOIUrl":"https://doi.org/10.1155/2024/9298478","url":null,"abstract":"Fire in power equipment has always been one of the main hazards of power equipment. Smoke detection and recognition have always been extremely important in power equipment, as they can provide early warning before a fire breaks out. Compared to relying on smoke concentration for recognition, image-based smoke recognition has the advantage of being unaffected by indoor and outdoor environments. This paper addresses the problems of limited smoke data, difficult labeling, and insufficient research on recognition algorithms in power systems. We propose using three-dimensional virtual technology to generate smoke and image masks and using environmental backgrounds such as HDR (high dynamic range imaging) lighting to realistically combine smoke and background. In addition, to address the characteristics of smoke in power equipment, a dual UNet model named DS-UNet is proposed. The model consists of a deep and a shallow network structure, which can effectively segment the details of smoke in power equipment and handle partial occlusion. Finally, DS-UNet is compared with other smoke segmentation networks with similar structures, and it demonstrates better smoke segmentation performance.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139533926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Eko Adhi Setiawan, Muhammad Fathurrahman, Radityo Fajar Pamungkas, Samsul Ma’arif
Maintaining the maximum performance of solar panels poses the foremost challenge for solar photovoltaic power plants in this era. One of the common PV faults which decreases PV power output is a hot spot which is caused by a prolonged local partial shading from objects, such as dust piles or animal waste. To prevent it, an enormous effort for PV inspection is needed especially for large solar power plants. Hence, automatic partial shading detection is critical in preventing PV hot spots to assist maintenance activities which are associated with a drop in energy output. This research developed fast partial shading detection application on PV modules using digital image processing to detect the hot spot and PV modules areas and afterwards calculate the PV systems power loss ratio. The proposed method demonstrated a hot spot detection rate of 94.74% and a module detection rate of 100%. The power loss ratio calculation is compared and validated using IV curve measurement and has 91.26% similarity value which is a feasible application for the real-world system.
保持太阳能电池板的最大性能是当今太阳能光伏发电站面临的首要挑战。减少光伏发电量的常见光伏故障之一是热斑，它是由灰尘堆或动物粪便等物体长期局部遮挡造成的。为了防止这种情况的发生，尤其是大型太阳能发电站，需要花费大量人力物力进行光伏检测。因此，自动局部遮阳检测对于防止光伏热点、协助维护活动至关重要，因为光伏热点会导致能量输出下降。这项研究利用数字图像处理技术开发了光伏模块快速部分遮光检测应用，以检测热点和光伏模块区域，然后计算光伏系统的功率损耗率。该方法的热点检测率为 94.74%，模块检测率为 100%。功率损耗率计算通过 IV 曲线测量进行比较和验证，相似值为 91.26%，在实际系统中的应用是可行的。
{"title":"Fast Partial Shading Detection on PV Modules for Precise Power Loss Ratio Estimation Using Digital Image Processing","authors":"Eko Adhi Setiawan, Muhammad Fathurrahman, Radityo Fajar Pamungkas, Samsul Ma’arif","doi":"10.1155/2024/9385602","DOIUrl":"https://doi.org/10.1155/2024/9385602","url":null,"abstract":"Maintaining the maximum performance of solar panels poses the foremost challenge for solar photovoltaic power plants in this era. One of the common PV faults which decreases PV power output is a hot spot which is caused by a prolonged local partial shading from objects, such as dust piles or animal waste. To prevent it, an enormous effort for PV inspection is needed especially for large solar power plants. Hence, automatic partial shading detection is critical in preventing PV hot spots to assist maintenance activities which are associated with a drop in energy output. This research developed fast partial shading detection application on PV modules using digital image processing to detect the hot spot and PV modules areas and afterwards calculate the PV systems power loss ratio. The proposed method demonstrated a hot spot detection rate of 94.74% and a module detection rate of 100%. The power loss ratio calculation is compared and validated using IV curve measurement and has 91.26% similarity value which is a feasible application for the real-world system.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139385393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chu Donatus Iweh, Guy Clarence Sèmassou, R. Ahouansou
The use of decentralized renewable energy systems will continue to play a significant role in electricity generation especially in developing countries where grid expansion to most remote areas is uneconomical. The income levels of these off-grid communities are often low, such that there is a need for the delivery of cost-effective energy solutions through optimum control and sizing of energy system components. This paper aims at minimizing the net present cost (NPC) and the levelised cost of energy (LCOE). The study presents a hybrid power system involving a hydroelectric, solar photovoltaic (PV), and battery system for a rural community in Cameroon. The optimization of the system was done using HOMER Pro and validated using a meta-heuristic algorithm known as genetic algorithm (GA). The GA approach was programmed using the MATLAB software. After the HOMER simulation, the optimal power capacity of 3 kW solar PV, 334.89 Ah battery, and 32.2 kW microhydropower was used to meet the load. The village load profile had a daily energy usage of 431.32 kWh/day and a peak power demand of 38.49 kW. The optimized results showed an NPC and LCOE of $90,469.16 and 0.0453 $/kWh, respectively. The system configuration was tested against an increase in hydropower capacity, and it was observed that increasing the hydropower capacity has the ability to significantly reduce the LCOE as well as the battery and solar PV size. A comparative analysis of the two approaches showed that the optimization using GA was more cost-effective than HOMER Pro with the least LCOE of 0.0344 $/kWh and NPC of $86,990.94 as well as a loss of power supply probability (LPSP) of 0.99%. In addition, the GA method gave more hydropower generation than HOMER Pro. This supports the fact that stochastic methods are more realistic and economically viable. They also accurately predict system operation than deterministic methods.
分散式可再生能源系统的使用将继续在发电方面发挥重要作用，尤其是在发展中国家，因为将电网扩展到大多数偏远地区并不经济。这些离网社区的收入水平往往很低，因此需要通过优化能源系统组件的控制和大小来提供具有成本效益的能源解决方案。本文旨在最大限度地降低净现值成本（NPC）和平准化能源成本（LCOE）。研究介绍了喀麦隆一个农村社区的混合动力系统，包括水电、太阳能光伏（PV）和电池系统。系统优化使用 HOMER Pro 完成，并使用一种称为遗传算法 (GA) 的元启发式算法进行验证。遗传算法使用 MATLAB 软件进行编程。经过 HOMER 仿真，使用 3 kW 太阳能光伏发电、334.89 Ah 蓄电池和 32.2 kW 微水电的最佳发电量来满足负荷。该村的负荷情况为：日用电量 431.32 kWh/天，峰值电力需求 38.49 kW。优化结果显示，NPC 和 LCOE 分别为 90,469.16 美元和 0.0453 美元/千瓦时。该系统配置针对增加水电容量进行了测试，结果表明，增加水电容量能够显著降低 LCOE 以及电池和太阳能光伏发电的规模。两种方法的对比分析表明，使用 GA 进行优化比 HOMER Pro 更具成本效益，LCOE 最低为 0.0344 美元/千瓦时，NPC 最低为 86,990.94 美元，供电损失概率 (LPSP) 最低为 0.99%。此外，GA 方法的水力发电量高于 HOMER Pro。这证明了随机方法更加现实和经济可行。与确定性方法相比，随机方法还能准确预测系统运行情况。
{"title":"Optimization of a Hybrid Off-Grid Solar PV—Hydro Power Systems for Rural Electrification in Cameroon","authors":"Chu Donatus Iweh, Guy Clarence Sèmassou, R. Ahouansou","doi":"10.1155/2024/4199455","DOIUrl":"https://doi.org/10.1155/2024/4199455","url":null,"abstract":"The use of decentralized renewable energy systems will continue to play a significant role in electricity generation especially in developing countries where grid expansion to most remote areas is uneconomical. The income levels of these off-grid communities are often low, such that there is a need for the delivery of cost-effective energy solutions through optimum control and sizing of energy system components. This paper aims at minimizing the net present cost (NPC) and the levelised cost of energy (LCOE). The study presents a hybrid power system involving a hydroelectric, solar photovoltaic (PV), and battery system for a rural community in Cameroon. The optimization of the system was done using HOMER Pro and validated using a meta-heuristic algorithm known as genetic algorithm (GA). The GA approach was programmed using the MATLAB software. After the HOMER simulation, the optimal power capacity of 3 kW solar PV, 334.89 Ah battery, and 32.2 kW microhydropower was used to meet the load. The village load profile had a daily energy usage of 431.32 kWh/day and a peak power demand of 38.49 kW. The optimized results showed an NPC and LCOE of $90,469.16 and 0.0453 $/kWh, respectively. The system configuration was tested against an increase in hydropower capacity, and it was observed that increasing the hydropower capacity has the ability to significantly reduce the LCOE as well as the battery and solar PV size. A comparative analysis of the two approaches showed that the optimization using GA was more cost-effective than HOMER Pro with the least LCOE of 0.0344 $/kWh and NPC of $86,990.94 as well as a loss of power supply probability (LPSP) of 0.99%. In addition, the GA method gave more hydropower generation than HOMER Pro. This supports the fact that stochastic methods are more realistic and economically viable. They also accurately predict system operation than deterministic methods.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139452728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
T. Odu, Moses O. Olaniyan, T. Ogunfunmi, Isaac A. Samuel, J. Badejo, Atayero
It is imperative to establish an automated system for the identification of neonates (1–28 days old) and infants (29 days–12 months old) through the utilisation of the readily accessible 500 ppi fingerprint reader. This measure is crucial in addressing the issue of newborn swapping, facilitating the identification of missing children, monitoring immunisation records, maintaining comprehensive medical history, and other related purposes. The objective of this study is to demonstrate the potential for future identification of infants using fingerprints obtained from a 500 ppi fingerprint reader by employing a fusion technique that combines multiple instances of fingerprints, specifically the left thumb and right index fingers. The fingerprints were acquired from babies who were between the ages of one day and six months at the enrolment session. The sum-score fusion algorithm was implemented. The approach mentioned above yielded verification accuracies of 73.8%, 69.05%, and 57.14% for time intervals of 1 month, 3 months, and 6 months, respectively, between the enrolment and query fingerprints.
{"title":"Multi-Instance Contingent Fusion for the Verification of Infant Fingerprints","authors":"T. Odu, Moses O. Olaniyan, T. Ogunfunmi, Isaac A. Samuel, J. Badejo, Atayero","doi":"10.1155/2024/7728707","DOIUrl":"https://doi.org/10.1155/2024/7728707","url":null,"abstract":"It is imperative to establish an automated system for the identification of neonates (1–28 days old) and infants (29 days–12 months old) through the utilisation of the readily accessible 500 ppi fingerprint reader. This measure is crucial in addressing the issue of newborn swapping, facilitating the identification of missing children, monitoring immunisation records, maintaining comprehensive medical history, and other related purposes. The objective of this study is to demonstrate the potential for future identification of infants using fingerprints obtained from a 500 ppi fingerprint reader by employing a fusion technique that combines multiple instances of fingerprints, specifically the left thumb and right index fingers. The fingerprints were acquired from babies who were between the ages of one day and six months at the enrolment session. The sum-score fusion algorithm was implemented. The approach mentioned above yielded verification accuracies of 73.8%, 69.05%, and 57.14% for time intervals of 1 month, 3 months, and 6 months, respectively, between the enrolment and query fingerprints.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139390464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. Gobin-Rahimbux, N. Gooda Sahib, N. Peerthy, A. Taylor
Voice-based smart personal assistants (VSPAs) are applications that recognize speech-based input and perform a task. In many domains, VSPA can play an important role as it mimics an interaction with another human. For low-resource languages, developing a VSPA can be challenging due to the lack of available audio datasets. In this work, a VSPA in Kreol Morisien (KM), the native language of Mauritius, is proposed to support users with mental health issues. Seven conversational flows were considered, and two speech recognition models were developed using CMUSphinx and DeepSpeech, respectively. A comparative user evaluation was conducted with 17 participants who were requested to speak 151 sentences of varying lengths in KM. It was observed that DeepSpeech was more accurate with a word error rate (WER) of 18% compared to CMUSphinx at 24%, that is, DeepSpeech fully recognized 76 sentences compared to CMUSphinx where only 57 sentences were fully recognized. However, DeepSpeech could not fully recognize any 7-word sentences, and thus, it was concluded that the contributions of DeepSpeech to automatic speech recognition in KM should be further explored. Nevertheless, this research is a stepping stone towards developing more VSPA to support various activities among the Mauritian population.
{"title":"A Voice-Based Personal Assistant for Mental Health in Kreol Morisien","authors":"B. Gobin-Rahimbux, N. Gooda Sahib, N. Peerthy, A. Taylor","doi":"10.1155/2023/5532967","DOIUrl":"https://doi.org/10.1155/2023/5532967","url":null,"abstract":"Voice-based smart personal assistants (VSPAs) are applications that recognize speech-based input and perform a task. In many domains, VSPA can play an important role as it mimics an interaction with another human. For low-resource languages, developing a VSPA can be challenging due to the lack of available audio datasets. In this work, a VSPA in Kreol Morisien (KM), the native language of Mauritius, is proposed to support users with mental health issues. Seven conversational flows were considered, and two speech recognition models were developed using CMUSphinx and DeepSpeech, respectively. A comparative user evaluation was conducted with 17 participants who were requested to speak 151 sentences of varying lengths in KM. It was observed that DeepSpeech was more accurate with a word error rate (WER) of 18% compared to CMUSphinx at 24%, that is, DeepSpeech fully recognized 76 sentences compared to CMUSphinx where only 57 sentences were fully recognized. However, DeepSpeech could not fully recognize any 7-word sentences, and thus, it was concluded that the contributions of DeepSpeech to automatic speech recognition in KM should be further explored. Nevertheless, this research is a stepping stone towards developing more VSPA to support various activities among the Mauritian population.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2023-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139152970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the increasing number of virtual power plants (VPP) participating in market transactions, the joint operation and energy sharing mode of multiple virtual power plants (multi-VPP) has attracted attention. A peer aggregation model for the multi-VPP energy sharing is proposed based on sharing price. At the VPP autonomous optimization level, each VPP operator formulates an autonomous optimization strategy based on the price incentives and the internal resource parameters and adopts a robust optimization method to improve the strategy’s robustness. At the overall level, a sharing level index is introduced to formulate the sharing price mechanism and an overall sharing strategy is proposed. The case simulation results show that compared with the independent operation of each VPP, participating in energy sharing can effectively promote the overall consumption of renewable energy and the overall operating cost is reduced by 18%. The introduction of the sharing level index into the sharing price can effectively improve the rationality of the formulated sharing price, and the net electricity load fluctuation has a greater impact on the system cost than the thermal load fluctuation.
{"title":"Energy Sharing of Multiple Virtual Power Plants Based on a Peer Aggregation Model","authors":"Sheng Li, Yujie Huang","doi":"10.1155/2023/9130209","DOIUrl":"https://doi.org/10.1155/2023/9130209","url":null,"abstract":"With the increasing number of virtual power plants (VPP) participating in market transactions, the joint operation and energy sharing mode of multiple virtual power plants (multi-VPP) has attracted attention. A peer aggregation model for the multi-VPP energy sharing is proposed based on sharing price. At the VPP autonomous optimization level, each VPP operator formulates an autonomous optimization strategy based on the price incentives and the internal resource parameters and adopts a robust optimization method to improve the strategy’s robustness. At the overall level, a sharing level index is introduced to formulate the sharing price mechanism and an overall sharing strategy is proposed. The case simulation results show that compared with the independent operation of each VPP, participating in energy sharing can effectively promote the overall consumption of renewable energy and the overall operating cost is reduced by 18%. The introduction of the sharing level index into the sharing price can effectively improve the rationality of the formulated sharing price, and the net electricity load fluctuation has a greater impact on the system cost than the thermal load fluctuation.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139161545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiadong Dong, Kai Pan, Chunxiang Zheng, Lin Chen, Shunfeng Wu, Xiaoling Zhang
Multiaccess edge computing (MEC) is a novel distributed computing paradigm. In this paper, we investigate the challenges of task offloading scheduling, communication bandwidth, and edge server computing resource allocation for multiple user equipments (UEs) in MEC. Our primary objective is to minimize system latency and local energy consumption. We explore the binary offloading and partial offloading methods and introduce the dual agent-TD3 (DA-TD3) algorithm based on the deep reinforcement learning (DRL) TD3 algorithm. The proposed algorithm coordinates task offloading scheduling and resource allocation for two intelligent agents. Specifically, agent 1 overcomes the action space explosion problem caused by the increasing number of UEs, by utilizing both binary and partial offloading. Agent 2 dynamically allocates communication bandwidth and computing resources to adapt to different task scenarios and network environments. Our simulation experiments demonstrate that the binary and partial offloading schemes of the DA-TD3 algorithm significantly reduce system latency and local energy consumption compared with deep deterministic policy gradient (DDPG) and other offloading schemes. Furthermore, the partial offloading optimization scheme performs the best.
{"title":"A Dual-Agent Approach for Coordinated Task Offloading and Resource Allocation in MEC","authors":"Jiadong Dong, Kai Pan, Chunxiang Zheng, Lin Chen, Shunfeng Wu, Xiaoling Zhang","doi":"10.1155/2023/6134837","DOIUrl":"https://doi.org/10.1155/2023/6134837","url":null,"abstract":"Multiaccess edge computing (MEC) is a novel distributed computing paradigm. In this paper, we investigate the challenges of task offloading scheduling, communication bandwidth, and edge server computing resource allocation for multiple user equipments (UEs) in MEC. Our primary objective is to minimize system latency and local energy consumption. We explore the binary offloading and partial offloading methods and introduce the dual agent-TD3 (DA-TD3) algorithm based on the deep reinforcement learning (DRL) TD3 algorithm. The proposed algorithm coordinates task offloading scheduling and resource allocation for two intelligent agents. Specifically, agent 1 overcomes the action space explosion problem caused by the increasing number of UEs, by utilizing both binary and partial offloading. Agent 2 dynamically allocates communication bandwidth and computing resources to adapt to different task scenarios and network environments. Our simulation experiments demonstrate that the binary and partial offloading schemes of the DA-TD3 algorithm significantly reduce system latency and local energy consumption compared with deep deterministic policy gradient (DDPG) and other offloading schemes. Furthermore, the partial offloading optimization scheme performs the best.","PeriodicalId":46573,"journal":{"name":"Journal of Electrical and Computer Engineering","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138949374","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：