Pub Date : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938295
U. Prasad, S. Mohanty, S. Singh
This paper aims to investigate the impact of the Conservation of Voltage Reduction scheme (CVR) on a typical protection system of distribution systems (DS). CVR is an energy-saving scheme in which the bus voltages of a DS are maintained in the lower 5% range of the rated value. Changing the operating condition of a DS may have a significant impact on the deployed protection system. It has been observed that maloperation of protective devices is more frequent than the occurrence of a genuine fault. Such a condition arises due to the occurrence of any such event that has not been taken into consideration while designing the protection problem formulation. In this paper, the CVR scheme has been deployed by regulating the taps of OLTC governed by the Line Drop Compensation (LDC) scheme and switching action of Capacitor Banks (CB) to maintain the bus voltages at the desired levels. Whereas the protection objectives have been accomplished by determining optimal settings of the deployed directional overcurrent relays (DOCR) in the DS. A protection objective reassures the reliable functioning of the protective devices by determining optimal operating time and proper coordination among the relays. The protection problem formulation is non-linear programming (NLP) in nature and solved using Nature-Inspired Algorithms (NIA) based Particle Swarm Optimisation (PSO) optimisation technique. The study has been performed on the IEEE 13 node test feeder and distribution portion of the IEEE 14 bus system. The test systems have been modelled on the PowerFactory software by DIgSILENT to deploy the CVR scheme and the relay actions. Furthermore, the optimisation problem has been solved in MATLAB. Although the CVR scheme comes under the planning and operation aspects of distribution systems, its impact on the performance of protection infrastructure cannot be ignored as the effects of both phenomena come hand in hand, and the same has not been discussed in the literature yet.
{"title":"Impact Analysis of CVR on Distribution System Protection Scheme","authors":"U. Prasad, S. Mohanty, S. Singh","doi":"10.1109/GlobConPT57482.2022.9938295","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938295","url":null,"abstract":"This paper aims to investigate the impact of the Conservation of Voltage Reduction scheme (CVR) on a typical protection system of distribution systems (DS). CVR is an energy-saving scheme in which the bus voltages of a DS are maintained in the lower 5% range of the rated value. Changing the operating condition of a DS may have a significant impact on the deployed protection system. It has been observed that maloperation of protective devices is more frequent than the occurrence of a genuine fault. Such a condition arises due to the occurrence of any such event that has not been taken into consideration while designing the protection problem formulation. In this paper, the CVR scheme has been deployed by regulating the taps of OLTC governed by the Line Drop Compensation (LDC) scheme and switching action of Capacitor Banks (CB) to maintain the bus voltages at the desired levels. Whereas the protection objectives have been accomplished by determining optimal settings of the deployed directional overcurrent relays (DOCR) in the DS. A protection objective reassures the reliable functioning of the protective devices by determining optimal operating time and proper coordination among the relays. The protection problem formulation is non-linear programming (NLP) in nature and solved using Nature-Inspired Algorithms (NIA) based Particle Swarm Optimisation (PSO) optimisation technique. The study has been performed on the IEEE 13 node test feeder and distribution portion of the IEEE 14 bus system. The test systems have been modelled on the PowerFactory software by DIgSILENT to deploy the CVR scheme and the relay actions. Furthermore, the optimisation problem has been solved in MATLAB. Although the CVR scheme comes under the planning and operation aspects of distribution systems, its impact on the performance of protection infrastructure cannot be ignored as the effects of both phenomena come hand in hand, and the same has not been discussed in the literature yet.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114775281","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938220
M. Khalid, B. K. Panigrahi
The grid-interactive charging station powered by PV and multiple energy storage systems is proposed to have a decentralized power management scheme (DPMS) in this article. The key feature of the proposed DPMS is to reduce the system complexity while enabling easy extension of load as well as new renewable sources. The DPMS considers all possible variations of PV, grid intentional/unintentional non-availability, and changes in local loads. It has the feasibility to detect the mode of operating of the system without measuring load currents and powers or any kind of communication. Grid end bidirectional converter transfers real power between DC bus and utility grid in effect with line compensated droop with the storage system. Additionally, it provides ancillary services including harmonic reduction, reactive power assistance for utilities, and maintenance of unity power factor (UPF) at the point of common connection (PCC). In the proposed system, power-sharing is utilized based on the SoC of the battery to enhance the lifecycle and also reduce the current stress on the battery. It provides smooth dc-bus voltage regulation. During the autonomous mode of the grid, the various condition is addressed such as PV output variation, load changes, etc. MATLAB simulation is performance d to verify the proposed DPMS.
{"title":"SoC-based Decentralized Power Management in Multi BESS-PV for EVs Charging Applications","authors":"M. Khalid, B. K. Panigrahi","doi":"10.1109/GlobConPT57482.2022.9938220","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938220","url":null,"abstract":"The grid-interactive charging station powered by PV and multiple energy storage systems is proposed to have a decentralized power management scheme (DPMS) in this article. The key feature of the proposed DPMS is to reduce the system complexity while enabling easy extension of load as well as new renewable sources. The DPMS considers all possible variations of PV, grid intentional/unintentional non-availability, and changes in local loads. It has the feasibility to detect the mode of operating of the system without measuring load currents and powers or any kind of communication. Grid end bidirectional converter transfers real power between DC bus and utility grid in effect with line compensated droop with the storage system. Additionally, it provides ancillary services including harmonic reduction, reactive power assistance for utilities, and maintenance of unity power factor (UPF) at the point of common connection (PCC). In the proposed system, power-sharing is utilized based on the SoC of the battery to enhance the lifecycle and also reduce the current stress on the battery. It provides smooth dc-bus voltage regulation. During the autonomous mode of the grid, the various condition is addressed such as PV output variation, load changes, etc. MATLAB simulation is performance d to verify the proposed DPMS.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125973136","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938216
Mayank Arora, Gururaj M V, Ankush Sharma
Typically, the wireless power transfer is compensated using Parallel Series architecture powered by an inverter that is current sourced (CSI). It is mainly regulated at duty cycle with a 50% approach. This allows the system to run at its resonance frequency, which wanders as a result of load as well as other variable fluctuations. Due to such a controlling limitation, the loading specifications are met by installing an extra dc-dc converter at the circuit end. This simulation study provides an open loop and closed loop control approach for a Parallel-Series WPT topology, which is supplied by a full-bridge CSI to fulfill the load requirement directly. So, the converter's output side chopper is eliminated. The control objectives are met by a two-loop technique in which source current is regulated by the inner loop and load current by outer loop. This study describes in-depth converter design analysis and closed loop control design in PSIM software.
{"title":"Simulation of Parallel-Series Converter in Open Loop and Closed Loop for Wireless Power Transfer","authors":"Mayank Arora, Gururaj M V, Ankush Sharma","doi":"10.1109/GlobConPT57482.2022.9938216","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938216","url":null,"abstract":"Typically, the wireless power transfer is compensated using Parallel Series architecture powered by an inverter that is current sourced (CSI). It is mainly regulated at duty cycle with a 50% approach. This allows the system to run at its resonance frequency, which wanders as a result of load as well as other variable fluctuations. Due to such a controlling limitation, the loading specifications are met by installing an extra dc-dc converter at the circuit end. This simulation study provides an open loop and closed loop control approach for a Parallel-Series WPT topology, which is supplied by a full-bridge CSI to fulfill the load requirement directly. So, the converter's output side chopper is eliminated. The control objectives are met by a two-loop technique in which source current is regulated by the inner loop and load current by outer loop. This study describes in-depth converter design analysis and closed loop control design in PSIM software.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122275406","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938237
S. Deb, Dacheng Li, Jihong Wang
Energy systems are becoming localized, digitalized, and decarbonized. This is the era of smart local energy system (LES) having combined heat and power (CHP). In traditional CHPs the imbalance between energy generation and load demand results in improper utilization of energy and economic losses. This paper puts forward a planning and operation scheme of LES having CHP and Lithium-ion battery for energy storage. A novel Ant Lion Optimization (ALO) algorithm is applied for solving the planning and operation of LES. ALO is a novel nature inspired algorithm mimicking the process of hunting of ant lions. The great balance between exploitation and exploration in ALO is effectively utilized in solving the planning and operation of LES. Simulation results confirm the efficacy of ALO over other state of art algorithms.
{"title":"A Novel Ant Lion Optimization Algorithm for Planning and Operation of Local Energy System having Combined Heat and Power and Lithium Ion Battery Energy Storage","authors":"S. Deb, Dacheng Li, Jihong Wang","doi":"10.1109/GlobConPT57482.2022.9938237","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938237","url":null,"abstract":"Energy systems are becoming localized, digitalized, and decarbonized. This is the era of smart local energy system (LES) having combined heat and power (CHP). In traditional CHPs the imbalance between energy generation and load demand results in improper utilization of energy and economic losses. This paper puts forward a planning and operation scheme of LES having CHP and Lithium-ion battery for energy storage. A novel Ant Lion Optimization (ALO) algorithm is applied for solving the planning and operation of LES. ALO is a novel nature inspired algorithm mimicking the process of hunting of ant lions. The great balance between exploitation and exploration in ALO is effectively utilized in solving the planning and operation of LES. Simulation results confirm the efficacy of ALO over other state of art algorithms.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127861895","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938357
Ankita Dixit, Mohit Vashishtha, Karan Guleri
Understanding emotions of people in a group is an essential facet of learning in today's time. Lot of information about emotional state, feeling and identity of human beings is conveyed via facial expression. Emotion recognition is a striking and demanding problem which in turn can help harness insights about individual and organizational behavior and can add big value to various businesses ranging from education, hospitality, entertainment, eateries, etc. In our research paper, we have proposed an AI rooted Emotion detection and recognition feedback system using mathematical solutions. AI based proposed solution will be self -governing and will be freewheeling from gender and age of human being in emotion detection and recognition, unlike past systems, which have largely failed to provide. This proposed solution system will greatly increase the potential to use the recognized emotion data from a wider applicability perspective and giving scope for customization as per customer's business requirement. In this study paper, a unique AI based emotion recognition detection mathematical solution system is proposed to analyze the behavior/reaction of people in a group. Proposed solution system will act as a feedback system and is able to amass multiple faces, extract respective emotions and formulate the detected emotions through proposed solution system to give aggregated behavior/emotion of the group as a whole.
{"title":"An AI based Formulated Feedback-System for Interpreting Conclusive Emotions for A Group of People","authors":"Ankita Dixit, Mohit Vashishtha, Karan Guleri","doi":"10.1109/GlobConPT57482.2022.9938357","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938357","url":null,"abstract":"Understanding emotions of people in a group is an essential facet of learning in today's time. Lot of information about emotional state, feeling and identity of human beings is conveyed via facial expression. Emotion recognition is a striking and demanding problem which in turn can help harness insights about individual and organizational behavior and can add big value to various businesses ranging from education, hospitality, entertainment, eateries, etc. In our research paper, we have proposed an AI rooted Emotion detection and recognition feedback system using mathematical solutions. AI based proposed solution will be self -governing and will be freewheeling from gender and age of human being in emotion detection and recognition, unlike past systems, which have largely failed to provide. This proposed solution system will greatly increase the potential to use the recognized emotion data from a wider applicability perspective and giving scope for customization as per customer's business requirement. In this study paper, a unique AI based emotion recognition detection mathematical solution system is proposed to analyze the behavior/reaction of people in a group. Proposed solution system will act as a feedback system and is able to amass multiple faces, extract respective emotions and formulate the detected emotions through proposed solution system to give aggregated behavior/emotion of the group as a whole.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132219343","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938231
Karthik Singh Parihar, R. Rai, Pushpant Kumar, M. K. Pathak
This article proposes a Bidirectional half-bridge AC-AC converter topology for Solid State Transformer (SST). AC-AC converter is comprised of two active half bridges along with one high frequency (HF) transformer. Four-quadrant switches are employed in each bridge to ensure power flow in both directions. The proposed converter configuration has fewer active switches, a simpler circuit design, and avoids the use of bulky electrolytic capacitors. These characteristics enhance the power density and reliability of the overall SST. The steady state working modes are outlined, and soft switching constraints are examined. To validate the theoretical analysis, simulation results are presented.
{"title":"A High Power-Density Bidirectional Half-Bridge Solid-State Transformer Architecture","authors":"Karthik Singh Parihar, R. Rai, Pushpant Kumar, M. K. Pathak","doi":"10.1109/GlobConPT57482.2022.9938231","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938231","url":null,"abstract":"This article proposes a Bidirectional half-bridge AC-AC converter topology for Solid State Transformer (SST). AC-AC converter is comprised of two active half bridges along with one high frequency (HF) transformer. Four-quadrant switches are employed in each bridge to ensure power flow in both directions. The proposed converter configuration has fewer active switches, a simpler circuit design, and avoids the use of bulky electrolytic capacitors. These characteristics enhance the power density and reliability of the overall SST. The steady state working modes are outlined, and soft switching constraints are examined. To validate the theoretical analysis, simulation results are presented.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133930332","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938158
Yasmin Nigar, A. Agalgaonkar, K. Muttaqi
The world is transitioning to utilise distributed generation (DG) to reduce social, economic and environmental effects. As DG penetration is increasing, the need of determining the associated impacts on distribution networks is vital. This paper proposes a concept around sphere of influence of single and multiple DG units through line current analysis and Sankey visualisation. The advantage of the proposed method is it acts as a visual lens to study the network and take necessary actions based on the outcomes. The proposed method is tested using 33 bus distribution network and visualisation is carried out using python library.
{"title":"Identification of Sphere of Influence of single and multiple DG Units through Visualisation in Distribution Networks","authors":"Yasmin Nigar, A. Agalgaonkar, K. Muttaqi","doi":"10.1109/GlobConPT57482.2022.9938158","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938158","url":null,"abstract":"The world is transitioning to utilise distributed generation (DG) to reduce social, economic and environmental effects. As DG penetration is increasing, the need of determining the associated impacts on distribution networks is vital. This paper proposes a concept around sphere of influence of single and multiple DG units through line current analysis and Sankey visualisation. The advantage of the proposed method is it acts as a visual lens to study the network and take necessary actions based on the outcomes. The proposed method is tested using 33 bus distribution network and visualisation is carried out using python library.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131749025","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938150
S. Rajendran, D. Jena, M. Díaz, V. Devi
An efficient condition monitoring technique is essential for power converters to avoid unscheduled maintenance. In this work, the condition monitoring of capacitors in a single-ended primary inductance converter (SEPIC) is proposed based on the following machine learning classifiers: K nearest neighbor, support vector machine, back propagation neural network, Naive Bayes, and deep neural network. The feature of the machine learning algorithms is extracted by three node voltages such as voltage across $C$ 1,C2, and load. These features are utilized for training the algorithms. Moreover, the effectiveness of the different classifies are evaluated by considering the accuracy and area under the curve. Further, each algorithm is trained with a different percentage of a dataset. Finally, a comparative study has been made between the algorithms, and the results exhibit that the deep neural network performs better classification than other algorithms.
{"title":"Comparative analysis of different machine learning techniques for condition monitoring of capacitors in a SEPIC converter","authors":"S. Rajendran, D. Jena, M. Díaz, V. Devi","doi":"10.1109/GlobConPT57482.2022.9938150","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938150","url":null,"abstract":"An efficient condition monitoring technique is essential for power converters to avoid unscheduled maintenance. In this work, the condition monitoring of capacitors in a single-ended primary inductance converter (SEPIC) is proposed based on the following machine learning classifiers: K nearest neighbor, support vector machine, back propagation neural network, Naive Bayes, and deep neural network. The feature of the machine learning algorithms is extracted by three node voltages such as voltage across $C$ 1,C2, and load. These features are utilized for training the algorithms. Moreover, the effectiveness of the different classifies are evaluated by considering the accuracy and area under the curve. Further, each algorithm is trained with a different percentage of a dataset. Finally, a comparative study has been made between the algorithms, and the results exhibit that the deep neural network performs better classification than other algorithms.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130900611","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938198
Gaurav Modi, Bhim Singh
The microgrid is generally designed to switch its operating mode from grid connected mode to autonomous mode during the disruption in grid supply so that the power supply remains undisturbed at the load terminal. The effectiveness of shifting microgrid operation from one mode to another is governed by the parameters of the local grid and point of common coupling (PPC) voltages such as amplitude, frequency, and phase. However, their estimation is defected by the DC offset, harmonics, and unbalance in the voltages. Therefore, this work proposes a second-order generalized integrator (SOGI) and αβ-cascaded delay signal cancellation (αβCDSC) (m = 4, 8)- quasi-type-l phase-locked loop (PLL) method, which effectively estimates the voltage parameters in the above-specified issues in the sensed voltages. The presented SOGI-αβCDSC method demonstrates similar filtering capability and dynamics response as the full-length αβCDSC CDSC (m= 2, 4, 8, 16) method, with reduced execution time. In addition, the introduced SOGI-αβCDSC is used as a filter to the local load currents, connected at the PCC of the microgrid. These filtered load currents are administered by the designed control to provide ancillary services, such as compensation to the load harmonics current and its reactive power, utilizing the microgrid's power converter. The Simulation validation is presented to showcase the performance of the designed control.
{"title":"SOGI -αβCDSC Quasi Type-l PLL Control for Seamless Transition Between Grid Connected and Autonomous Operating Modes of Microgrid","authors":"Gaurav Modi, Bhim Singh","doi":"10.1109/GlobConPT57482.2022.9938198","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938198","url":null,"abstract":"The microgrid is generally designed to switch its operating mode from grid connected mode to autonomous mode during the disruption in grid supply so that the power supply remains undisturbed at the load terminal. The effectiveness of shifting microgrid operation from one mode to another is governed by the parameters of the local grid and point of common coupling (PPC) voltages such as amplitude, frequency, and phase. However, their estimation is defected by the DC offset, harmonics, and unbalance in the voltages. Therefore, this work proposes a second-order generalized integrator (SOGI) and αβ-cascaded delay signal cancellation (αβCDSC) (m = 4, 8)- quasi-type-l phase-locked loop (PLL) method, which effectively estimates the voltage parameters in the above-specified issues in the sensed voltages. The presented SOGI-αβCDSC method demonstrates similar filtering capability and dynamics response as the full-length αβCDSC CDSC (m= 2, 4, 8, 16) method, with reduced execution time. In addition, the introduced SOGI-αβCDSC is used as a filter to the local load currents, connected at the PCC of the microgrid. These filtered load currents are administered by the designed control to provide ancillary services, such as compensation to the load harmonics current and its reactive power, utilizing the microgrid's power converter. The Simulation validation is presented to showcase the performance of the designed control.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131180977","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 : 2022-09-23DOI: 10.1109/GlobConPT57482.2022.9938239
Saurav Kumar, P. Sumathi
An object detection framework based on modified YOLOv3 architecture is proposed for perception systems. In order to test the proposed object detector, a novel dataset consisting of road images for Indian road scenarios has been developed with various environmental conditions. The seven classes are considered in the object detection, in which five are vehicles frequently encountered during the Indian driving scenarios along with pedestrians and riders. The modified YOLOv3 promises the mean average precision of 84% for the detection of specified classes in the dataset. The F1 score and average IoU for the modified YOLOv3 are 81% and 71.78% respectively. The detection kernel is modified to train on the proposed dataset. The object detection results are compared with Faster Region-based Convolutional neural network (R-CNN), cascade R-CNN, single sort detector (SSD), baseline YOLOv3, and modified YOLOv3-tiny. The proposed object detector based on modified YOLOv3 yields improved mAP and hence it is more suitable for camera-based perception systems used in autonomous driving.
{"title":"An Object Detection Framework with Modified YOLOv3 for Camera Based Perception Systems","authors":"Saurav Kumar, P. Sumathi","doi":"10.1109/GlobConPT57482.2022.9938239","DOIUrl":"https://doi.org/10.1109/GlobConPT57482.2022.9938239","url":null,"abstract":"An object detection framework based on modified YOLOv3 architecture is proposed for perception systems. In order to test the proposed object detector, a novel dataset consisting of road images for Indian road scenarios has been developed with various environmental conditions. The seven classes are considered in the object detection, in which five are vehicles frequently encountered during the Indian driving scenarios along with pedestrians and riders. The modified YOLOv3 promises the mean average precision of 84% for the detection of specified classes in the dataset. The F1 score and average IoU for the modified YOLOv3 are 81% and 71.78% respectively. The detection kernel is modified to train on the proposed dataset. The object detection results are compared with Faster Region-based Convolutional neural network (R-CNN), cascade R-CNN, single sort detector (SSD), baseline YOLOv3, and modified YOLOv3-tiny. The proposed object detector based on modified YOLOv3 yields improved mAP and hence it is more suitable for camera-based perception systems used in autonomous driving.","PeriodicalId":431406,"journal":{"name":"2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133843520","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：