This paper is devoted to the improvement existing models of electronics devices, which are used in powers electronics as switching devices, and investigate a LabVIEW-based automatic test-bench for Silicon carbide (SiC) power devices. In recent years, power electronic devices are required to be capable handle with higher voltage, leads to development of new generation of power electronic devices, such as SiC devices. However, using a simulation platform, such as Spice, to diminish the complexity of power electronic design with these new devices is hindered by the lack of precise models. The proposed test-bench enables not only measuring static characteristics of SiC power devices, but also extracting key parameters required by simulations. These extracted parameters are then employed in the existing device model, and the simulation results which are based on the model with original parameters and models with extracted parameters are compared with measured results. The comparison clearly demonstrates that parameters obtained from the proposed test-bench significantly enhance the Spice model.
本文致力于改进在电力电子设备中用作开关器件的电子器件的现有模型，并研究基于 LabVIEW 的碳化硅（SiC）功率器件自动测试平台。近年来，要求电力电子器件能够处理更高的电压，从而开发出新一代电力电子器件，如碳化硅器件。然而，由于缺乏精确的模型，使用 Spice 等仿真平台来降低使用这些新器件进行电力电子设计的复杂性受到了阻碍。所提出的测试平台不仅能测量 SiC 功率器件的静态特性，还能提取仿真所需的关键参数。然后在现有器件模型中使用这些提取的参数，并将基于带原始参数的模型和带提取参数的模型的仿真结果与测量结果进行比较。比较结果清楚地表明，从建议的测试平台中获得的参数极大地增强了 Spice 模型。
{"title":"Automatic test-bench for SiC power devices using LabVIEW","authors":"Jan Leuchter, Ngoc Nam Pham, Huy Hoang Nguyen","doi":"10.2478/jee-2024-0011","DOIUrl":"https://doi.org/10.2478/jee-2024-0011","url":null,"abstract":"\u0000 This paper is devoted to the improvement existing models of electronics devices, which are used in powers electronics as switching devices, and investigate a LabVIEW-based automatic test-bench for Silicon carbide (SiC) power devices. In recent years, power electronic devices are required to be capable handle with higher voltage, leads to development of new generation of power electronic devices, such as SiC devices. However, using a simulation platform, such as Spice, to diminish the complexity of power electronic design with these new devices is hindered by the lack of precise models. The proposed test-bench enables not only measuring static characteristics of SiC power devices, but also extracting key parameters required by simulations. These extracted parameters are then employed in the existing device model, and the simulation results which are based on the model with original parameters and models with extracted parameters are compared with measured results. The comparison clearly demonstrates that parameters obtained from the proposed test-bench significantly enhance the Spice model.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"87 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140785685","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}
In this paper, a broadband(12-18G) low-noise amplifier (LNA) using 65-nm CMOS technology for satellite communication is presented. This LNA was designed in a cascode common source with inductive degeneration topology. In addition, the bulk isolation technique is employed to make the proposed LNA have a higher gain. Furthermore, a two-stage cascaded configuration combined with inductive parallel peaking technology is utilized to make the LNA achieve a wide operating band. For validation, we design this LNA in a 65nm CMOS technology. The simulated results show that S21 of 17.7dB ± 0.5dB, the input/output return loss of -10dB to -33dB and -12dB to -23dB, respectively. It offers the minimum noise figure (NF) performance of 3.33dB, reverse isolation(S12) better than 60dB, and third-order input point (IIP3) of -22.8 dBm obtained over the band of interest. Excluding the output buffer stage, the LNA is consuming 5.1 mW at a supply voltage of 0.8V and its layout area occupies 0.205 mm2.
{"title":"A Ku band low-voltage and low-power CMOS low-noise amplifier with bulk isolation techniques","authors":"Zifeng Guo, Jian Liu","doi":"10.2478/jee-2024-0014","DOIUrl":"https://doi.org/10.2478/jee-2024-0014","url":null,"abstract":"\u0000 In this paper, a broadband(12-18G) low-noise amplifier (LNA) using 65-nm CMOS technology for satellite communication is presented. This LNA was designed in a cascode common source with inductive degeneration topology. In addition, the bulk isolation technique is employed to make the proposed LNA have a higher gain. Furthermore, a two-stage cascaded configuration combined with inductive parallel peaking technology is utilized to make the LNA achieve a wide operating band. For validation, we design this LNA in a 65nm CMOS technology. The simulated results show that S21 of 17.7dB ± 0.5dB, the input/output return loss of -10dB to -33dB and -12dB to -23dB, respectively. It offers the minimum noise figure (NF) performance of 3.33dB, reverse isolation(S12) better than 60dB, and third-order input point (IIP3) of -22.8 dBm obtained over the band of interest. Excluding the output buffer stage, the LNA is consuming 5.1 mW at a supply voltage of 0.8V and its layout area occupies 0.205 mm2.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"178 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140777727","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}
Test case prioritization (TCP) is a regression technique that sequences test cases by assigning priority based on specific criteria defined by software testers. Various parameters, such as code coverage, statement coverage, and method coverage, are utilized in Test Case Prioritization (TCP), wherein metaheuristic techniques are widely employed to determine the optimal order of test cases based on these specified parameters. However, simply applying these techniques does not ensure the satisfaction of all the needs of software testers. This paper introduces an empirical study that employs the multi-objective test case prioritization (MOTCP) technique to prioritize the test cases based on target points defined by software testers. The study calculates a Software Complexity Index (SCI) at the code level, identifying fault-prone areas. Furthermore, a Test-case Complexity Index (TCI) is also used for prioritization. The proposed technique incorporates various target points defined by the software tester to calculate SCI and TCI, which serve as our main objectives for TCP. A detailed analysis is also performed to examine the impact of these target points on the generated optimal order of test cases. Finally, the proposed model is compared with other state-of-the-art techniques across various evaluation parameters.
{"title":"Fault sensitivity index-based multi-objective testcase prioritization","authors":"Kamal Garg, Shashi Shekhar","doi":"10.2478/jee-2024-0018","DOIUrl":"https://doi.org/10.2478/jee-2024-0018","url":null,"abstract":"\u0000 Test case prioritization (TCP) is a regression technique that sequences test cases by assigning priority based on specific criteria defined by software testers. Various parameters, such as code coverage, statement coverage, and method coverage, are utilized in Test Case Prioritization (TCP), wherein metaheuristic techniques are widely employed to determine the optimal order of test cases based on these specified parameters. However, simply applying these techniques does not ensure the satisfaction of all the needs of software testers. This paper introduces an empirical study that employs the multi-objective test case prioritization (MOTCP) technique to prioritize the test cases based on target points defined by software testers. The study calculates a Software Complexity Index (SCI) at the code level, identifying fault-prone areas. Furthermore, a Test-case Complexity Index (TCI) is also used for prioritization. The proposed technique incorporates various target points defined by the software tester to calculate SCI and TCI, which serve as our main objectives for TCP. A detailed analysis is also performed to examine the impact of these target points on the generated optimal order of test cases. Finally, the proposed model is compared with other state-of-the-art techniques across various evaluation parameters.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"9 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140755908","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}
This paper describes realization, basic properties, testing, and experiments with a special prototype of a wearable two-channel photoplethysmography (PPG) sensor supplemented by contact thermometers that maps the skin temperature at the place where the optical part of the sensor touches a measured hand part (typically a wrist and fingers). Preliminary measurement confirms that proposed I2C thermometers have proper stability and precision, so can be successfully used in the developed PPG sensor. The performed main experiments show that the significant increase of temperature was always observed at the place of the worn PPG sensors during the whole measurement. This rise of temperature affects mainly the PPG signal range, thus it has also influence on the quality of the sensed PPG wave. The conclusion formulates the final recommendation about the necessity of at least 5-minute time delay between the PPG sensor placement on the hand and the start of the PPG signal acquisition. While the current measurements were realized in normal laboratory conditions, the whole wearable PPG sensor consists of non-ferromagnetic materials and all parts are fully shielded by aluminum boxes to enable measurement in a low magnetic field environment which, is our final long term research aim.
{"title":"Contact measurement of skin temperature using a wearable two-channel PPG optical sensor supplemented by thermometers","authors":"J. Přibil, A. Přibilová, I. Frollo","doi":"10.2478/jee-2024-0015","DOIUrl":"https://doi.org/10.2478/jee-2024-0015","url":null,"abstract":"\u0000 This paper describes realization, basic properties, testing, and experiments with a special prototype of a wearable two-channel photoplethysmography (PPG) sensor supplemented by contact thermometers that maps the skin temperature at the place where the optical part of the sensor touches a measured hand part (typically a wrist and fingers). Preliminary measurement confirms that proposed I2C thermometers have proper stability and precision, so can be successfully used in the developed PPG sensor. The performed main experiments show that the significant increase of temperature was always observed at the place of the worn PPG sensors during the whole measurement. This rise of temperature affects mainly the PPG signal range, thus it has also influence on the quality of the sensed PPG wave. The conclusion formulates the final recommendation about the necessity of at least 5-minute time delay between the PPG sensor placement on the hand and the start of the PPG signal acquisition. While the current measurements were realized in normal laboratory conditions, the whole wearable PPG sensor consists of non-ferromagnetic materials and all parts are fully shielded by aluminum boxes to enable measurement in a low magnetic field environment which, is our final long term research aim.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"46 26","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140771223","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}
Šimon Grác, Peter Beno, F. Duchoň, Michal Malý, Martin Dekan
The article proposes a solution for object classification using multiple views generated from 3D data rendering and convolutional neural networks. For presentation purposes and easier verification of the solution, an application was developed to create views of 3D objects, classify them using the selected CNN, and evaluate the performance of the CNN. The evaluation is based on metrics and characteristics described in the article. Seven testing objects were used to verify the proposed solution; five CNNs were tested for each.
{"title":"Object classification with aggregating multiple spatial views using a machine-learning approach","authors":"Šimon Grác, Peter Beno, F. Duchoň, Michal Malý, Martin Dekan","doi":"10.2478/jee-2024-0017","DOIUrl":"https://doi.org/10.2478/jee-2024-0017","url":null,"abstract":"\u0000 The article proposes a solution for object classification using multiple views generated from 3D data rendering and convolutional neural networks. For presentation purposes and easier verification of the solution, an application was developed to create views of 3D objects, classify them using the selected CNN, and evaluate the performance of the CNN. The evaluation is based on metrics and characteristics described in the article. Seven testing objects were used to verify the proposed solution; five CNNs were tested for each.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"162 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140781648","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}
In order to further improve the defect detection capability of gas insulated switchgear and avoid equipment faults, broadband current array sensing system is designed to simultaneously monitor the system status such as partial discharge, relative dielectric loss, and power frequency overvoltage. The dynamic model of the system is analysed, and based on which, the system state equation is obtained meanwhile fault observer is designed, and the system stability criterion under H ∞ condition is calculated. The reliability of the system under different packet loss rates is verified based on cloud models, and the principle of using appropriate electromagnetic compatibility to prevent packet loss rates below 50% is proposed.
为进一步提高气体绝缘开关设备的缺陷检测能力，避免设备故障，设计了宽带电流阵列传感系统，可同时监测局部放电、相对介质损耗和工频过电压等系统状态。分析了系统的动态模型，在此基础上得到了系统状态方程，同时设计了故障观测器，并计算了 H ∞ 条件下的系统稳定性准则。基于云模型验证了不同丢包率下系统的可靠性，并提出了利用适当的电磁兼容性防止丢包率低于 50%的原则。
{"title":"Stability and reliability analysis for broadband current array sensing system applied to GIS","authors":"F. Du, Hao Yu, Shuai Yuan, Jiangang Bi, Dehui Fu","doi":"10.2478/jee-2024-0020","DOIUrl":"https://doi.org/10.2478/jee-2024-0020","url":null,"abstract":"\u0000 In order to further improve the defect detection capability of gas insulated switchgear and avoid equipment faults, broadband current array sensing system is designed to simultaneously monitor the system status such as partial discharge, relative dielectric loss, and power frequency overvoltage. The dynamic model of the system is analysed, and based on which, the system state equation is obtained meanwhile fault observer is designed, and the system stability criterion under H\u0000 ∞ condition is calculated. The reliability of the system under different packet loss rates is verified based on cloud models, and the principle of using appropriate electromagnetic compatibility to prevent packet loss rates below 50% is proposed.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"240 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140776720","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}
The paper presents the performance enhancement of band-pass filter-based M-class phasor estimation. The performance of the M-class phasor estimation using a band-pass FIR filter is enhanced with a magnitude correction factor for the off-nominal frequency range. The band-pass filter is implemented for the phasor estimation with various window functions Tukey, Rife Vincent class-I order-2 (RV2), Hamming, Hanning, Blackman, and Flat-top (FT) and its performance are evaluated under the steady and dynamic state tests prescribed by the standard. A rigorous performance analysis of enhanced phasor estimation using band-pass FIR filter with various window functions is presented with the accuracy indices of total vector error (TVE), frequency error (FE), and rate of change of frequency error (RFE). The result analysis reveals that the performance enhanced phasor estimation using band-pass FIR filter offers significantly less error than reported work at the low sampling rate. The design and performance analysis of the phasor estimation using the band-pass FIR filter is performed in the MATLAB platform.
本文介绍了基于带通滤波器的 M 级相位估计的性能提升。使用带通 FIR 滤波器的 M 级相位估算性能在非标称频率范围内通过幅值修正系数得到了增强。该带通滤波器用于相位估计，具有各种窗函数 Tukey、Rife Vincent Class-I order-2 (RV2)、Hamming、Hanning、Blackman 和 Flat-top (FT)，并在标准规定的稳态和动态测试下对其性能进行了评估。利用各种窗函数的带通 FIR 滤波器对增强型相位估计进行了严格的性能分析，并给出了总矢量误差（TVE）、频率误差（FE）和频率变化率误差（RFE）等精度指标。结果分析表明，在低采样率条件下，使用带通 FIR 滤波器的性能增强型相位估算的误差明显小于已有研究。使用带通 FIR 滤波器进行相位估计的设计和性能分析是在 MATLAB 平台上完成的。
{"title":"Performance enhancement of band-pass FIR filter-based M-class phasor estimation","authors":"Mukesh Kumar, M. S. Kumar","doi":"10.2478/jee-2024-0016","DOIUrl":"https://doi.org/10.2478/jee-2024-0016","url":null,"abstract":"\u0000 The paper presents the performance enhancement of band-pass filter-based M-class phasor estimation. The performance of the M-class phasor estimation using a band-pass FIR filter is enhanced with a magnitude correction factor for the off-nominal frequency range. The band-pass filter is implemented for the phasor estimation with various window functions Tukey, Rife Vincent class-I order-2 (RV2), Hamming, Hanning, Blackman, and Flat-top (FT) and its performance are evaluated under the steady and dynamic state tests prescribed by the standard. A rigorous performance analysis of enhanced phasor estimation using band-pass FIR filter with various window functions is presented with the accuracy indices of total vector error (TVE), frequency error (FE), and rate of change of frequency error (RFE). The result analysis reveals that the performance enhanced phasor estimation using band-pass FIR filter offers significantly less error than reported work at the low sampling rate. The design and performance analysis of the phasor estimation using the band-pass FIR filter is performed in the MATLAB platform.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"12 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140786951","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}
A 90° hybrid coupler operating at a central frequency of 5.40 GHz is introduced, offering high-performance characteristics with compact dimensions of 616.65 mm² (33.3 mm × 18.5 mm). These features are achieved while maintaining a design that makes it easy to produce. The unique aspect of this microstrip FR4 substrate-based design is the consistent S-parameters, which remain steady despite changes in structural dimensions, thereby making it adaptable to fabrication variations. The reported S-parameters measured in 5.4 GHz are as follows: |S11|= –29.46 dB, |S21|= –4.11 dB, |S31|= –3.96 dB, and |S41|= –21.23 dB. This hybrid coupler operates over a bandwidth of 0.8 GHz (16%), demonstrating remarkable performance within this spectrum. In addition to its design, the coupler exhibits robust resilience against changes in substrate parameters and structural dimensions, ensuring reliability during the fabrication process. Following thorough simulation studies, a physical prototype of the coupler was constructed and subjected to laboratory measurements. The experimental results align closely with the simulation data, validating the accuracy and predictability of the design. In comparison with other studies and designs documented in the literature, this compact, high-performance 90° hybrid coupler exhibits clear advantages in terms of size, isolation, phase deviation, and structural complexity. Therefore, the benefits and applicability of this presented structure in the context of microwave circuits and systems are underscored. It’s noteworthy to mention that the central frequency of 5.4 GHz falls within the sub-6 GHz 5G band range.
{"title":"A simple 90° hybrid branchline coupler with wideband phase balance for 5G applications","authors":"Ümit Can Ünal, K. Karaçuha, Sehabeddin Taha İmeci","doi":"10.2478/jee-2024-0012","DOIUrl":"https://doi.org/10.2478/jee-2024-0012","url":null,"abstract":"\u0000 A 90° hybrid coupler operating at a central frequency of 5.40 GHz is introduced, offering high-performance characteristics with compact dimensions of 616.65 mm² (33.3 mm × 18.5 mm). These features are achieved while maintaining a design that makes it easy to produce. The unique aspect of this microstrip FR4 substrate-based design is the consistent S-parameters, which remain steady despite changes in structural dimensions, thereby making it adaptable to fabrication variations. The reported S-parameters measured in 5.4 GHz are as follows: |S11|= –29.46 dB, |S21|= –4.11 dB, |S31|= –3.96 dB, and |S41|= –21.23 dB. This hybrid coupler operates over a bandwidth of 0.8 GHz (16%), demonstrating remarkable performance within this spectrum. In addition to its design, the coupler exhibits robust resilience against changes in substrate parameters and structural dimensions, ensuring reliability during the fabrication process. Following thorough simulation studies, a physical prototype of the coupler was constructed and subjected to laboratory measurements. The experimental results align closely with the simulation data, validating the accuracy and predictability of the design. In comparison with other studies and designs documented in the literature, this compact, high-performance 90° hybrid coupler exhibits clear advantages in terms of size, isolation, phase deviation, and structural complexity. Therefore, the benefits and applicability of this presented structure in the context of microwave circuits and systems are underscored. It’s noteworthy to mention that the central frequency of 5.4 GHz falls within the sub-6 GHz 5G band range.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"242 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140783743","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}
The paper evaluates how the control of transmitted power affects the intensity of radiation in a mobile network cell. Cell models without power control, with standard power control and a model with power control and channel reallocation are considered. The relative reduction of radiation is evaluated and several examples of calculations are presented. Remarks are given on the dependence of radiation reduction on the number of traffic channels, traffic intensity and signal attenuation coefficient. The assessment procedure and results are based on previously verified traffic process simulation models.
{"title":"Influence of power control in the mobile network on the radiation level","authors":"D. Mitic, A. Lebl, Z. Markov","doi":"10.2478/jee-2024-0019","DOIUrl":"https://doi.org/10.2478/jee-2024-0019","url":null,"abstract":"\u0000 The paper evaluates how the control of transmitted power affects the intensity of radiation in a mobile network cell. Cell models without power control, with standard power control and a model with power control and channel reallocation are considered. The relative reduction of radiation is evaluated and several examples of calculations are presented. Remarks are given on the dependence of radiation reduction on the number of traffic channels, traffic intensity and signal attenuation coefficient. The assessment procedure and results are based on previously verified traffic process simulation models.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"88 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140768954","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}
Anuratha Kesavan, Nandhini Jembu Mohanram, Soshya Joshi, Uma Sankar
The emergence of Internet of Things enabled with mobile computing has the applications in the field of unmanned aerial vehicle (UAV) development. The development of mobile edge computational offloading in UAV is dependent on low latency applications such as disaster management, Forest fire control and remote operations. The task completion efficiency is improved by means of using edge intelligence algorithm and the optimal offloading policy is constructed on the application of deep reinforcement learning (DRL) in order to fulfill the target demand and to ease the transmission delay. The joint optimization curtails the weighted sum of average energy consumption and execution delay. This edge intelligence algorithm combined with DRL network exploits computing operation to increase the probability that at least one of the tracking and data transmission is usable. The proposed joint optimization significantly performs well in terms of execution delay, offloading cost and effective convergence over the prevailing methodologies proposed for UAV development. The proposed DRL enables the UAV to real-time decisions based on the disaster scenario and computing resources availability.
{"title":"Deep reinforcement learning based computing offloading in unmanned aerial vehicles for disaster management","authors":"Anuratha Kesavan, Nandhini Jembu Mohanram, Soshya Joshi, Uma Sankar","doi":"10.2478/jee-2024-0013","DOIUrl":"https://doi.org/10.2478/jee-2024-0013","url":null,"abstract":"\u0000 The emergence of Internet of Things enabled with mobile computing has the applications in the field of unmanned aerial vehicle (UAV) development. The development of mobile edge computational offloading in UAV is dependent on low latency applications such as disaster management, Forest fire control and remote operations. The task completion efficiency is improved by means of using edge intelligence algorithm and the optimal offloading policy is constructed on the application of deep reinforcement learning (DRL) in order to fulfill the target demand and to ease the transmission delay. The joint optimization curtails the weighted sum of average energy consumption and execution delay. This edge intelligence algorithm combined with DRL network exploits computing operation to increase the probability that at least one of the tracking and data transmission is usable. The proposed joint optimization significantly performs well in terms of execution delay, offloading cost and effective convergence over the prevailing methodologies proposed for UAV development. The proposed DRL enables the UAV to real-time decisions based on the disaster scenario and computing resources availability.","PeriodicalId":508697,"journal":{"name":"Journal of Electrical Engineering","volume":"74 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140764728","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：