Pub Date : 2023-08-03DOI: 10.2174/2352096516666230803144411
Aicha Bouzem, Othmane Bendaou, A. Yaakoubi
Machine Learning (ML) techniques have successfully replaced traditional control algorithms in recent years due to their ability to carry out complicated tasks with significant efficiency and accuracy. The main objective of the current work is to investigate and compare the performances of different ML models in modeling Maximum Power Point Tracking (MPPT) control for a wind turbine system. The main advantage of the designed MPPT based on ML is that it does not require any detailed mathematical model or prior knowledge of the system, such as turbine parameters or aerodynamic properties, unlike traditional MPPT techniques. The ML models included in this study were Support Vector Machines, Regression Trees, and Ensemble Trees. Their design was performed through a training process, and their performances were evaluated based on various metrics. During the training phase, the ML models were selected to understand the basic concept of the control strategy and extract essential hidden connections between the inputs and the output of the system. The effectiveness of the control method was investigated using MATLAB/Simulink. The findings of this study revealed that ML models were effective in modeling the MPPT for the studied wind power system, which provides an interesting and sophisticated alternative to classical control methods for wind systems. The ML models designed allow for optimal operation of the system with a simple structure that is independent of system parameters and wind speed measurement and is adaptable for any kind of system.
{"title":"An Intelligent Maximum Power Point Tracking Strategy for a Wind Energy Conversion System Using Machine Learning Algorithms","authors":"Aicha Bouzem, Othmane Bendaou, A. Yaakoubi","doi":"10.2174/2352096516666230803144411","DOIUrl":"https://doi.org/10.2174/2352096516666230803144411","url":null,"abstract":"\u0000\u0000Machine Learning (ML) techniques have successfully replaced traditional control algorithms in recent years due to their ability to carry out complicated tasks with significant efficiency and accuracy.\u0000\u0000\u0000\u0000The main objective of the current work is to investigate and compare the performances of different ML models in modeling Maximum Power Point Tracking (MPPT) control for a wind turbine system. The main advantage of the designed MPPT based on ML is that it does not require any detailed mathematical model or prior knowledge of the system, such as turbine parameters or aerodynamic properties, unlike traditional MPPT techniques.\u0000\u0000\u0000\u0000The ML models included in this study were Support Vector Machines, Regression Trees, and Ensemble Trees. Their design was performed through a training process, and their performances were evaluated based on various metrics. During the training phase, the ML models were selected to understand the basic concept of the control strategy and extract essential hidden connections between the inputs and the output of the system.\u0000\u0000\u0000\u0000The effectiveness of the control method was investigated using MATLAB/Simulink. The findings of this study revealed that ML models were effective in modeling the MPPT for the studied wind power system, which provides an interesting and sophisticated alternative to classical control methods for wind systems.\u0000\u0000\u0000\u0000The ML models designed allow for optimal operation of the system with a simple structure that is independent of system parameters and wind speed measurement and is adaptable for any kind of system.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"26 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78947024","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}
Pub Date : 2023-07-31DOI: 10.2174/2352096516666230731143503
Yifei Yin
The introduction of virtual resistance can effectively suppress the circulating current between micro-sources and improve power allocation in low-voltage microgrid, but it also causes the voltage deviation of micro-sources’ inverters. An optimization method of virtual resistance based on hybrid index is proposed in order to suppress circulating current and improve voltage deviation at the same time in this paper. The gradient descent method is used to design the virtual resistance optimization process, aiming at the optimization of hybrid index composed of circulating current and voltage deviation. The constraints are deduced with power quality requirements, capacity limitation and static stability, and then virtual resistance values are optimized. The effects of switching load and micro-source on the optimization results are analyzed through the simulation of low-voltage microgrid, and the simulation results show that the virtual resistance optimization method can significantly suppress circulating current while improving power quality. When distributed generators are connected to utility grid through inverters and feeders, differences in feeder parameters and inverter control strategies easily cause circulating current and uneven power distribution among micro-sources. The introduction of virtual resistance can effectively suppress the circulating current between micro-sources and improve power allocation in low-voltage microgrids, but it also causes the voltage deviation of micro-sources’ inverters. An optimization method of virtual resistance based on hybrid index is proposed in order to suppress circulating current and improve voltage deviation. The gradient descent method is used to design the virtual resistance optimization process, aiming at the optimization of hybrid index composed of circulating current and voltage deviation. The constraints are deduced with power quality requirements, capacity limitation and static stability, and then virtual resistance values are optimized. In the simulation scenario of two micro-sources and three micro-sources, the virtual resistance obtained by the method proposed in this paper has more obvious improvement on the system operation index, and is not affected by the load type. The method of optimizing virtual resistance based on the hybrid index can achieve the effect of restraining circulating current and improving power sharing degree on the premise of guaranteeing power quality and satisfying system stability. The optimization of virtual resistance is affected by the number of feeders. It is necessary to re-optimize the virtual resistance after changing the number of feeders, but the process of switching micro-source and adjusting load does not affect the optimized resistance value.
{"title":"A Virtual Resistance Optimization Method Based on Hybrid Index in Low-Voltage Microgrid","authors":"Yifei Yin","doi":"10.2174/2352096516666230731143503","DOIUrl":"https://doi.org/10.2174/2352096516666230731143503","url":null,"abstract":"\u0000\u0000The introduction of virtual resistance can effectively suppress the circulating current between micro-sources and improve power allocation in low-voltage microgrid, but it also causes the voltage deviation of micro-sources’ inverters. An optimization method of virtual resistance based on hybrid index is proposed in order to suppress circulating current and improve voltage deviation at the same time in this paper. The gradient descent method is used to design the virtual resistance optimization process, aiming at the optimization of hybrid index composed of circulating current and voltage deviation. The constraints are deduced with power quality requirements, capacity limitation and static stability, and then virtual resistance values are optimized. The effects of switching load and micro-source on the optimization results are analyzed through the simulation of low-voltage microgrid, and the simulation results show that the virtual resistance optimization method can significantly suppress circulating current while improving power quality. When distributed generators are connected to utility grid through inverters and feeders, differences in feeder parameters and inverter control strategies easily cause circulating current and uneven power distribution among micro-sources. The introduction of virtual resistance can effectively suppress the circulating current between micro-sources and improve power allocation in low-voltage microgrids, but it also causes the voltage deviation of micro-sources’ inverters. An optimization method of virtual resistance based on hybrid index is proposed in order to suppress circulating current and improve voltage deviation.\u0000\u0000\u0000\u0000The gradient descent method is used to design the virtual resistance optimization process, aiming at the optimization of hybrid index composed of circulating current and voltage deviation. The constraints are deduced with power quality requirements, capacity limitation and static stability, and then virtual resistance values are optimized.\u0000\u0000\u0000\u0000In the simulation scenario of two micro-sources and three micro-sources, the virtual resistance obtained by the method proposed in this paper has more obvious improvement on the system operation index, and is not affected by the load type.\u0000\u0000\u0000\u0000The method of optimizing virtual resistance based on the hybrid index can achieve the effect of restraining circulating current and improving power sharing degree on the premise of guaranteeing power quality and satisfying system stability. The optimization of virtual resistance is affected by the number of feeders. It is necessary to re-optimize the virtual resistance after changing the number of feeders, but the process of switching micro-source and adjusting load does not affect the optimized resistance value.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"23 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79516162","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}
Pub Date : 2023-07-27DOI: 10.2174/2352096516666230727154910
Zhongxian Wang, Tengfei Ye, Xiaoqiang Chen
SMES systems as power compensation devices can effectively improve the transient stability of the power system. Due to the nonlinear and strongly coupled characteristics of the compensation device, an effective transfer function cannot be established, such that the traditional PI control by the linearization cannot accurately describe the complex nonlinear system. In this paper, a passive control strategy is introduced for the SMES System based on CLLC resonant converter to solve the problems that the traditional PI control cannot accurately describe the complex nonlinear system and the parameters’ settings are complicated. First, according to KVL and KCL, the mathematical model of the SMES system based on the CLLC resonant converter in the (d, q) coordinates is derived and established. Second, based on passive control theory, the port-controlled dissipation Hamiltonian model of CLLC-SMES is given. Third, combined with the passivity of SMES, the energy equation is established and the active and reactive power are analyzed respectively for the balanceable expectation, and then the energy equation is solved to obtain the drive signal of the switch tube. Fourth, the stability of the passive controller is verified by the Lyapunov equation, and the feasibility of the passive control strategy of CLLC-SMES is verified by simulation. The results show that compared with the traditional PI control strategy, the power compensation system based on the passive control strategy does not need to establish the transfer function and the parameters are simple to adjust. It can not only track the active and reactive power commands quickly and accurately but also improve the transient state of the power system effectively.
{"title":"A Study on CLLC-SMES System Based on the Passivity Control Strategy","authors":"Zhongxian Wang, Tengfei Ye, Xiaoqiang Chen","doi":"10.2174/2352096516666230727154910","DOIUrl":"https://doi.org/10.2174/2352096516666230727154910","url":null,"abstract":"\u0000\u0000SMES systems as power compensation devices can effectively improve the transient stability of the power system. Due to the nonlinear and strongly coupled characteristics of the compensation device, an effective transfer function cannot be established, such that the traditional PI control by the linearization cannot accurately describe the complex nonlinear system.\u0000\u0000\u0000\u0000In this paper, a passive control strategy is introduced for the SMES System based on CLLC resonant converter to solve the problems that the traditional PI control cannot accurately describe the complex nonlinear system and the parameters’ settings are complicated.\u0000\u0000\u0000\u0000First, according to KVL and KCL, the mathematical model of the SMES system based on the CLLC resonant converter in the (d, q) coordinates is derived and established. Second, based on passive control theory, the port-controlled dissipation Hamiltonian model of CLLC-SMES is given. Third, combined with the passivity of SMES, the energy equation is established and the active and reactive power are analyzed respectively for the balanceable expectation, and then the energy equation is solved to obtain the drive signal of the switch tube. Fourth, the stability of the passive controller is verified by the Lyapunov equation, and the feasibility of the passive control strategy of CLLC-SMES is verified by simulation.\u0000\u0000\u0000\u0000The results show that compared with the traditional PI control strategy, the power compensation system based on the passive control strategy does not need to establish the transfer function and the parameters are simple to adjust.\u0000\u0000\u0000\u0000It can not only track the active and reactive power commands quickly and accurately but also improve the transient state of the power system effectively.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"25 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75766496","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}
Pub Date : 2023-07-20DOI: 10.2174/2352096516666230720164542
Garima Thakur, Sunil Kumar, Varun Vaid
The transition from the first generation of technology, which only had an analog voice, to the fifth generation, which also had connected gadgets, gave the technology a new structure and changed how people used it. Fifth-generation wireless technology, often known as 5G, is on the cusp of reaching its potential maximum data transfer rate with a peak data throughput of 20 gigabits per second (Gbps) and a typical data transfer rate of more than 100 megabits per second (Mbps). The Internet of Things serves as the cornerstone of the future, and it is projected that by 2025, individual users will use 13 times the amount of data that we do at this time. Therefore, 5G is extremely important and the main feature of the 2030 Sustainable Development Agenda, which was ratified by all of the Member States of the United Nations in 2015, and is the 17 Sustainable Development Goals (SDGs), which represent an urgent call to action for all nations. These goals are referred to collectively as the "SDGs." This study intends to examine how 5G networks might serve as important facilitators for achieving sustainability and meeting some of the 17 SDGs. This is further highlighted by evaluating the sustainability metrics for 5G networks. Ultimately, this helps to demonstrate that 5G networks are environmentally, socially, and economically responsible. This study focuses on the five primary SDGs that are important for the growth of smart cities.
{"title":"A Comprehensive Review of 5G Networks for Sustainable and Smart Cities","authors":"Garima Thakur, Sunil Kumar, Varun Vaid","doi":"10.2174/2352096516666230720164542","DOIUrl":"https://doi.org/10.2174/2352096516666230720164542","url":null,"abstract":"\u0000\u0000The transition from the first generation of technology, which only had an analog voice, to the fifth generation, which also had connected gadgets, gave the technology a new structure and changed how people used it. Fifth-generation wireless technology, often known as 5G, is on the cusp of reaching its potential maximum data transfer rate with a peak data throughput of 20 gigabits per second (Gbps) and a typical data transfer rate of more than 100 megabits per second (Mbps). The Internet of Things serves as the cornerstone of the future, and it is projected that by 2025, individual users will use 13 times the amount of data that we do at this time. Therefore, 5G is extremely important and the main feature of the 2030 Sustainable Development Agenda, which was ratified by all of the Member States of the United Nations in 2015, and is the 17 Sustainable Development Goals (SDGs), which represent an urgent call to action for all nations. These goals are referred to collectively as the \"SDGs.\" This study intends to examine how 5G networks might serve as important facilitators for achieving sustainability and meeting some of the 17 SDGs. This is further highlighted by evaluating the sustainability metrics for 5G networks. Ultimately, this helps to demonstrate that 5G networks are environmentally, socially, and economically responsible. This study focuses on the five primary SDGs that are important for the growth of smart cities.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"160 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86171580","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}
Pub Date : 2023-07-19DOI: 10.2174/2352096516666230719114956
Y. Sucharitha, Pundru Chandra Shaker Reddy, S. Latha, G. Kumar
Integrated computing technologies such as the Internet of Things (IoT), Multi-Agent Systems (MAS), and automatic networking to deliver Internet of Vehicles (IoV) applications. The main objective of this paper is to combine MAS with IoT or IoV a new paradigm within its Cypher Physical System (CPS) for intelligent car applications. We proposed the MAS algorithm and applied it to control traffic lights at multiple intersections. When using MAS together with scattered computing architectures, IoV can achieve higher efficiency. The proposed combination is based on the independent knowledge, adaptability, assertiveness, and responsiveness that can be used in wireless sensor paradigms to bring new remedies. Smart products will explore further advancements and diverse mobility capabilities. IoT provides an appropriate atmosphere for connecting with MAS concepts and programs in addition to providing reliable, adaptable, efficient, and intelligent solutions in the automotive network. In addition, the combination of MAS with IoT and cognitive conditions could result in scalable, automated, and smart wireless sensor solutions. We conduct experiments on three different datasets, and the results demonstrate that MAS outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time.
{"title":"Multi-Agent Iot-Based System For Intelligent Vehicle Traffic Management Using Wireless Sensor Networks","authors":"Y. Sucharitha, Pundru Chandra Shaker Reddy, S. Latha, G. Kumar","doi":"10.2174/2352096516666230719114956","DOIUrl":"https://doi.org/10.2174/2352096516666230719114956","url":null,"abstract":"\u0000\u0000Integrated computing technologies such as the Internet of Things (IoT), Multi-Agent Systems (MAS), and automatic networking to deliver Internet of Vehicles (IoV) applications.\u0000\u0000\u0000\u0000The main objective of this paper is to combine MAS with IoT or IoV a new paradigm within its Cypher Physical System (CPS) for intelligent car applications. We proposed the MAS algorithm and applied it to control traffic lights at multiple intersections. When using MAS together with scattered computing architectures, IoV can achieve higher efficiency. The proposed combination is based on the independent knowledge, adaptability, assertiveness, and responsiveness that can be used in wireless sensor paradigms to bring new remedies. Smart products will explore further advancements and diverse mobility capabilities.\u0000\u0000\u0000\u0000IoT provides an appropriate atmosphere for connecting with MAS concepts and programs in addition to providing reliable, adaptable, efficient, and intelligent solutions in the automotive network. In addition, the combination of MAS with IoT and cognitive conditions could result in scalable, automated, and smart wireless sensor solutions.\u0000\u0000\u0000\u0000We conduct experiments on three different datasets, and the results demonstrate that MAS outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"33 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79445179","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}
Pub Date : 2023-07-18DOI: 10.2174/2352096516666230718155721
With the recent COVID-19 pandemic, people have become increasingly concerned about their physical health. Therefore, the ability to monitor changes in the surrounding environment in real-time and automatically improve the environment has become a current hot topic to improve the overall health level. This article describes the design of a high-performance intelligent home system that can simultaneously perform monitoring and automatic adjustment functions. The ESP8266 was used as the core controller, and the DHT11 and G12-04 sensors were used to collect data, such as temperature, humidity, and ambient light intensity. The sampling frequency was increased and the sampled data were processed to improve data accuracy. The sampled data were wirelessly transmitted to a PC or mobile terminal for real-time display. When the sampled data underwent sudden changes, an alert message was sent via the mobile terminal. Based on the real-time changes in ambient light, an improved lighting brightness adjustment algorithm combining bang-bang and single neuron adaptive PID control was used to adjust the lighting brightness. After testing the system designed in this paper and analyzing the errors compared to standard values, the temperature measurement error ranged from 0% to 0.01107%, and the humidity measurement error ranged from 0% to 0.03797%. The improved algorithm was simulated and tested using MATLAB software and compared with traditional PID algorithms and single-neuron adaptive PID algorithms. The improved algorithm did not overshoot during adjustment, and the system reached a steady state much faster than traditional algorithms. The system showed good performance in real-time, stability, and accuracy, fully demonstrating the effectiveness of the devices and algorithms used in the system. This provides ideas for the design and improvement of future smart homes.
{"title":"High-performance Smart Home System Based on Optimization Algorithm","authors":"","doi":"10.2174/2352096516666230718155721","DOIUrl":"https://doi.org/10.2174/2352096516666230718155721","url":null,"abstract":"\u0000\u0000With the recent COVID-19 pandemic, people have become increasingly concerned about their physical health. Therefore, the ability to monitor changes in the surrounding environment in real-time and automatically improve the environment has become a current hot topic to improve the overall health level.\u0000\u0000\u0000\u0000This article describes the design of a high-performance intelligent home system that can simultaneously perform monitoring and automatic adjustment functions.\u0000\u0000\u0000\u0000The ESP8266 was used as the core controller, and the DHT11 and G12-04 sensors were used to collect data, such as temperature, humidity, and ambient light intensity. The sampling frequency was increased and the sampled data were processed to improve data accuracy. The sampled data were wirelessly transmitted to a PC or mobile terminal for real-time display. When the sampled data underwent sudden changes, an alert message was sent via the mobile terminal. Based on the real-time changes in ambient light, an improved lighting brightness adjustment algorithm combining bang-bang and single neuron adaptive PID control was used to adjust the lighting brightness.\u0000\u0000\u0000\u0000After testing the system designed in this paper and analyzing the errors compared to standard values, the temperature measurement error ranged from 0% to 0.01107%, and the humidity measurement error ranged from 0% to 0.03797%. The improved algorithm was simulated and tested using MATLAB software and compared with traditional PID algorithms and single-neuron adaptive PID algorithms. The improved algorithm did not overshoot during adjustment, and the system reached a steady state much faster than traditional algorithms.\u0000\u0000\u0000\u0000The system showed good performance in real-time, stability, and accuracy, fully demonstrating the effectiveness of the devices and algorithms used in the system. This provides ideas for the design and improvement of future smart homes.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"1201 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77678436","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}
Pub Date : 2023-07-17DOI: 10.2174/2352096516666230717102625
Y. Sucharitha, Pundru Chandra Shaker Reddy, A. Vivekanand
Businesses in the E-Commerce sector, especially those in the business-to-consumer segment, are engaged in fierce competition for survival, trying to gain access to their rivals' client bases while keeping current customers from defecting. The cost of acquiring new customers is rising as more competitors join the market with significant upfront expenditures and cutting-edge penetration strategies, making client retention essential for these organizations. The main objective of this research is to detect probable churning customers and prevent churn with temporary retention measures. It's also essential to understand why the customer decided to go away to apply customized win-back strategies. Predictive analysis uses the hybrid classification approach to address the regression and classification issues. The process for forecasting E-Commerce customer attrition based on support vector machines is presented in this paper, along with a hybrid recommendation strategy for targeted retention initiatives. You may prevent future customer churn by suggesting reasonable offers or services. The empirical findings demonstrate a considerable increase in the coverage ratio, hit ratio, lift degree, precision rate, and other metrics using the integrated forecasting model. To effectively identify separate groups of lost customers and create a customer churn retention strategy, categorize the various lost customer types using the RFM principle.
{"title":"Customer Churn Prevention For E-Commerce Platforms Using Machine Learning-Based Business Intelligence","authors":"Y. Sucharitha, Pundru Chandra Shaker Reddy, A. Vivekanand","doi":"10.2174/2352096516666230717102625","DOIUrl":"https://doi.org/10.2174/2352096516666230717102625","url":null,"abstract":"\u0000\u0000Businesses in the E-Commerce sector, especially those in the business-to-consumer segment, are engaged in fierce competition for survival, trying to gain access to their rivals' client bases while keeping current customers from defecting. The cost of acquiring new customers is rising as more competitors join the market with significant upfront expenditures and cutting-edge penetration strategies, making client retention essential for these organizations.\u0000\u0000\u0000\u0000The main objective of this research is to detect probable churning customers and prevent churn with temporary retention measures. It's also essential to understand why the customer decided to go away to apply customized win-back strategies. Predictive analysis uses the hybrid classification approach to address the regression and classification issues. The process for forecasting E-Commerce customer attrition based on support vector machines is presented in this paper, along with a hybrid recommendation strategy for targeted retention initiatives. You may prevent future customer churn by suggesting reasonable offers or services.\u0000\u0000\u0000\u0000The empirical findings demonstrate a considerable increase in the coverage ratio, hit ratio, lift degree, precision rate, and other metrics using the integrated forecasting model.\u0000\u0000\u0000\u0000To effectively identify separate groups of lost customers and create a customer churn retention strategy, categorize the various lost customer types using the RFM principle.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"29 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86203684","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}
Pub Date : 2023-07-14DOI: 10.2174/2352096516666230714154857
Zhenghui Zhao, Zhi-Fei Ma, Yang Wang, Zhihao Hou
The implementation of Battery Energy Storage Systems (BESSs) and carbon capture units can effectively reduce the total carbon emissions of distribution networks. However, their widespread adoption has been hindered by the high investment costs associated with the BESSs and power generation costs of carbon capture units. The objective of this paper is to optimize the location and sizing of BESSs in distribution networks that comprise renewable power plants and coal-fired power units with carbon capture systems. The optimization process aims to minimize the grid’s impact from the configuration while maximizing economic cost savings and the benefits of reducing carbon emissions. A bi-layer optimization model is proposed to determine the configuration of BESSs. The upper layer of the model optimizes the size and operation strategy of the BESSs to minimize the configuration and power generation costs, using YALMIP and CPLEX optimization tools. Carbon emission reduction benefits are considered through deep peak-shaving and carbon tax. The lower layer of the model aims to optimizes the placement of the BESSs to minimize voltage fluctuation and network loss in the power grid. To achieve this, we improved the efficiency of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to update the BESS’s placement. The IEEE33-bus and IEEE118-bus systems were utilized for simulation and comparison in various scenarios. The findings demonstrate that the proposed configuration method can decrease the cost of investment and power generation. Furthermore, it reduces the degree of node voltage fluctuation and network loss in the distribution network. The study reveals that determining the optimal scale of BESSs can mitigate high energy consumption in carbon capture systems and improve the overall performance of power systems that integrate carbon capture technology and renewable power plants.
{"title":"Study on the optimal configuration of battery energy storage system in distribution networks considering carbon capture units","authors":"Zhenghui Zhao, Zhi-Fei Ma, Yang Wang, Zhihao Hou","doi":"10.2174/2352096516666230714154857","DOIUrl":"https://doi.org/10.2174/2352096516666230714154857","url":null,"abstract":"\u0000\u0000The implementation of Battery Energy Storage Systems (BESSs) and carbon capture units can effectively reduce the total carbon emissions of distribution networks. However, their widespread adoption has been hindered by the high investment costs associated with the BESSs and power generation costs of carbon capture units.\u0000\u0000\u0000\u0000The objective of this paper is to optimize the location and sizing of BESSs in distribution networks that comprise renewable power plants and coal-fired power units with carbon capture systems. The optimization process aims to minimize the grid’s impact from the configuration while maximizing economic cost savings and the benefits of reducing carbon emissions.\u0000\u0000\u0000\u0000A bi-layer optimization model is proposed to determine the configuration of BESSs. The upper layer of the model optimizes the size and operation strategy of the BESSs to minimize the configuration and power generation costs, using YALMIP and CPLEX optimization tools. Carbon emission reduction benefits are considered through deep peak-shaving and carbon tax. The lower layer of the model aims to optimizes the placement of the BESSs to minimize voltage fluctuation and network loss in the power grid. To achieve this, we improved the efficiency of the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to update the BESS’s placement.\u0000\u0000\u0000\u0000The IEEE33-bus and IEEE118-bus systems were utilized for simulation and comparison in various scenarios. The findings demonstrate that the proposed configuration method can decrease the cost of investment and power generation. Furthermore, it reduces the degree of node voltage fluctuation and network loss in the distribution network.\u0000\u0000\u0000\u0000The study reveals that determining the optimal scale of BESSs can mitigate high energy consumption in carbon capture systems and improve the overall performance of power systems that integrate carbon capture technology and renewable power plants.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"1 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86911062","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}
Pub Date : 2023-07-14DOI: 10.2174/2352096516666230714141145
Bing-Tuan Gao, Yongkang Wang, Guangbin Yu
The dynamics research of gear transmission systems mainly revolves around "excitation-model-response". The increasing number of dynamic incentive factors considered in the study has brought new problems to selecting modeling and solution methods and analyzing dynamic characteristics. This study aims to sort out the main research content of gear transmission system dynamics. Moepver, the commonly used analysis models, modeling, and solution methods are compared, and references for method selection and in-depth research are provided. This paper reviews the representative papers and patents related to the dynamic analysis of the gear system. The main contents of the dynamic excitation, dynamic model and dynamic characteristic analysis of the gear system are discussed, and suggestions for future development directions are given. The dynamic excitations mainly considered in the current research are internal excitations and external excitations; random excitations are rarely considered. This paper analyzes and summarizes the commonly used modeling methods, model classification, solution methods, and dynamic characteristics research content. The advantages and disadvantages of several commonly used analysis models, modeling, and solution methods and their applicable occasions are summarized for the reference of researchers. The dynamics study of the gear system is a systematic work. It requires comprehensively considering the influence of dynamic excitations and selecting appropriate methods to establish and solve the model to obtain the dynamic characteristics that can better reflect the actual working conditions of the gear system. It is of great significance to improve the performance of the gear system.
{"title":"Research Progress on Gear Transmission System Dynamics","authors":"Bing-Tuan Gao, Yongkang Wang, Guangbin Yu","doi":"10.2174/2352096516666230714141145","DOIUrl":"https://doi.org/10.2174/2352096516666230714141145","url":null,"abstract":"\u0000\u0000The dynamics research of gear transmission systems mainly revolves around \"excitation-model-response\". The increasing number of dynamic incentive factors considered in the study has brought new problems to selecting modeling and solution methods and analyzing dynamic characteristics.\u0000\u0000\u0000\u0000This study aims to sort out the main research content of gear transmission system dynamics. Moepver, the commonly used analysis models, modeling, and solution methods are compared, and references for method selection and in-depth research are provided.\u0000\u0000\u0000\u0000This paper reviews the representative papers and patents related to the dynamic analysis of the gear system. The main contents of the dynamic excitation, dynamic model and dynamic characteristic analysis of the gear system are discussed, and suggestions for future development directions are given.\u0000\u0000\u0000\u0000The dynamic excitations mainly considered in the current research are internal excitations and external excitations; random excitations are rarely considered. This paper analyzes and summarizes the commonly used modeling methods, model classification, solution methods, and dynamic characteristics research content. The advantages and disadvantages of several commonly used analysis models, modeling, and solution methods and their applicable occasions are summarized for the reference of researchers.\u0000\u0000\u0000\u0000The dynamics study of the gear system is a systematic work. It requires comprehensively considering the influence of dynamic excitations and selecting appropriate methods to establish and solve the model to obtain the dynamic characteristics that can better reflect the actual working conditions of the gear system. It is of great significance to improve the performance of the gear system.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":" 16","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72500193","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}
Pub Date : 2023-07-13DOI: 10.2174/2352096516666230713163440
Pundru Chandra Shaker Reddy, Y. Sucharitha
Over the past few years, researchers have greatly focused on increasing the electrical efficiency of large computer systems. Virtual machine (VM) migration helps data centers keep their pages' content updated on a regular basis, which speeds up the time it takes to access data. Offline VM migration is best accomplished by sharing memory without requiring any downtime. The objective of the paper was to reduce energy consumption and deploy a unique green computing architecture. The proposed virtual machine is transferred from one host to another through dynamic mobility. The proposed technique migrates the maximally loaded virtual machine to the least loaded active node, while maintaining the performance and energy efficiency of the data centers. Taking into account the cloud environment, the use of electricity could continue to be critical. These large uses of electricity by the internet information facilities that maintain computing capacity are becoming another major concern. Another way to reduce resource use is to relocate the VM. Using a non-linear forecasting approach, the research presents improved decentralized virtual machine migration (IDVMM) that could mitigate electricity consumption in cloud information warehouses. It minimizes violations of support agreements in a relatively small number of all displaced cases and improves the efficiency of resources. The proposed approach further develops two thresholds to divide overloaded hosts into massively overloaded hosts, moderately overloaded hosts, and lightly overloaded hosts. The migration decision of VMs in all stages pursues the goal of reducing the energy consumption of the network during the migration process. Given ten months of data, actual demand tracing is done through PlanetLab and then assessed using a cloud service.
{"title":"An Energy-saving Data Transmission Approach Based on Migrating Virtual Machine Technology to Cloud Computing","authors":"Pundru Chandra Shaker Reddy, Y. Sucharitha","doi":"10.2174/2352096516666230713163440","DOIUrl":"https://doi.org/10.2174/2352096516666230713163440","url":null,"abstract":"\u0000\u0000Over the past few years, researchers have greatly focused on increasing the electrical efficiency of large computer systems. Virtual machine (VM) migration helps data centers keep their pages' content updated on a regular basis, which speeds up the time it takes to access data. Offline VM migration is best accomplished by sharing memory without requiring any downtime.\u0000\u0000\u0000\u0000The objective of the paper was to reduce energy consumption and deploy a unique green computing architecture. The proposed virtual machine is transferred from one host to another through dynamic mobility. The proposed technique migrates the maximally loaded virtual machine to the least loaded active node, while maintaining the performance and energy efficiency of the data centers. Taking into account the cloud environment, the use of electricity could continue to be critical. These large uses of electricity by the internet information facilities that maintain computing capacity are becoming another major concern. Another way to reduce resource use is to relocate the VM.\u0000\u0000\u0000\u0000Using a non-linear forecasting approach, the research presents improved decentralized virtual machine migration (IDVMM) that could mitigate electricity consumption in cloud information warehouses. It minimizes violations of support agreements in a relatively small number of all displaced cases and improves the efficiency of resources.\u0000\u0000\u0000\u0000The proposed approach further develops two thresholds to divide overloaded hosts into massively overloaded hosts, moderately overloaded hosts, and lightly overloaded hosts. The migration decision of VMs in all stages pursues the goal of reducing the energy consumption of the network during the migration process. Given ten months of data, actual demand tracing is done through PlanetLab and then assessed using a cloud service.\u0000","PeriodicalId":43275,"journal":{"name":"Recent Advances in Electrical & Electronic Engineering","volume":"51 1","pages":""},"PeriodicalIF":0.6,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85111084","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：