Pub Date : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862521
Jayadev Pavuluri, Sanjeev M. Ranjan, Alok Naugarhiya
A brief analysis of Silicon on Insulator (SOI) LDMOS with various High-K Gate dielectrics under radiation environment was done in this paper. Four High-K gate dielectric stacks, $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}},mathbf{Al}_{boldsymbol{2}}mathbf{O}_{boldsymbol{3}}-mathbf{SiO}_{boldsymbol{2}}, mathbf{AlN}-mathbf{SiO}_{boldsymbol{2}},$ and $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}},$ are used to study the corresponding Strike fields, Breakdown voltages, and other significant parameters, and a comparison was made against Conventional LDMOS structure. It has been observed that the SOI LDMOS with $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{mathbf{3}}mathbf{N}_{mathbf{4}}-mathbf{SiO}_{mathbf{2}}$ gate dielectric provides better radiation hardening against SEGR compared to other dielectrics and SOI LDMOS with $mathbf{AlN}-mathbf{SiO}_{boldsymbol{2}}$ stack provides least radiation hardening against SEGR. The buried oxide layer modulates the electric field at the drift region and increases the Breakdown voltage. For an ion strike of linear energy transfer (LET) of 89 $mathbf{MeV.}mathbf{cm}^{boldsymbol{2}}/mathbf{mg}$, Strike fields of SOI LDMOS with $mathbf{RfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric are reduced by 15.3%, 28.8%, respectively compared to conventional LDMOS. For SOI LDMOS with $mathbf{RfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric, Breakdown voltage (BV) is increased by 20.09% compared to conventional LDMOS, and for SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric, BV is increased by 18.95%, compared to conventional LDMOS. Therefore, the Figure of Merit (FOM) of SOI LDMOS with $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric is improved by 29.21 % and 40.9%, respectively. Proposed LDMOS structures can be used for designing DC-to-DC converters in the radiation environment, in aerospace and satellite applications.
{"title":"Analysis of Gate Oxides in LDMOS for Radiation Hardening Against SEGR","authors":"Jayadev Pavuluri, Sanjeev M. Ranjan, Alok Naugarhiya","doi":"10.1109/ICICCSP53532.2022.9862521","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862521","url":null,"abstract":"A brief analysis of Silicon on Insulator (SOI) LDMOS with various High-K Gate dielectrics under radiation environment was done in this paper. Four High-K gate dielectric stacks, $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}},mathbf{Al}_{boldsymbol{2}}mathbf{O}_{boldsymbol{3}}-mathbf{SiO}_{boldsymbol{2}}, mathbf{AlN}-mathbf{SiO}_{boldsymbol{2}},$ and $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}},$ are used to study the corresponding Strike fields, Breakdown voltages, and other significant parameters, and a comparison was made against Conventional LDMOS structure. It has been observed that the SOI LDMOS with $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{mathbf{3}}mathbf{N}_{mathbf{4}}-mathbf{SiO}_{mathbf{2}}$ gate dielectric provides better radiation hardening against SEGR compared to other dielectrics and SOI LDMOS with $mathbf{AlN}-mathbf{SiO}_{boldsymbol{2}}$ stack provides least radiation hardening against SEGR. The buried oxide layer modulates the electric field at the drift region and increases the Breakdown voltage. For an ion strike of linear energy transfer (LET) of 89 $mathbf{MeV.}mathbf{cm}^{boldsymbol{2}}/mathbf{mg}$, Strike fields of SOI LDMOS with $mathbf{RfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric are reduced by 15.3%, 28.8%, respectively compared to conventional LDMOS. For SOI LDMOS with $mathbf{RfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric, Breakdown voltage (BV) is increased by 20.09% compared to conventional LDMOS, and for SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric, BV is increased by 18.95%, compared to conventional LDMOS. Therefore, the Figure of Merit (FOM) of SOI LDMOS with $mathbf{HfO}_{boldsymbol{2}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric and SOI LDMOS with $mathbf{Si}_{boldsymbol{3}}mathbf{N}_{boldsymbol{4}}-mathbf{SiO}_{boldsymbol{2}}$ gate dielectric is improved by 29.21 % and 40.9%, respectively. Proposed LDMOS structures can be used for designing DC-to-DC converters in the radiation environment, in aerospace and satellite applications.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125365996","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862409
Sai Venkat Vemala, L. Rao, Teja Yarroju, Sai Kiran Utla, Subhani Shaik
Recent days, the efficient distributed generation scheme is encouraged for obtaining required load demand by employing solar-PV energy generation complying with power-quality limitations. Amid of various custom-power devices, the Universal Power-Quality Compensator is the best choice for compensation of both voltage and current allied power-quality issues in distribution system. But, the traditional UPQC device consists of more switching devices which increases the dv/dt stress, switching loss, low efficiency performance, etc. In this regard, a novel reduced-switch UPQC has been proposed with the requirement of fewer switch elements over the traditional UPQC device. The proposed RSUPQC device is used for enhancing power-quality features and DG integration scheme for stabilizing the utility-grid fluctuations by using novel modulation-rate control technique. The performance of proposed RSUPQC device is verified in both power-quality enhancement and DG integration modes by using Matlab/Simulink tool, results are presented.
{"title":"A Solar-PV Integrated Novel Reduced-Switch UPQC Device for Power-Quality Improvement","authors":"Sai Venkat Vemala, L. Rao, Teja Yarroju, Sai Kiran Utla, Subhani Shaik","doi":"10.1109/ICICCSP53532.2022.9862409","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862409","url":null,"abstract":"Recent days, the efficient distributed generation scheme is encouraged for obtaining required load demand by employing solar-PV energy generation complying with power-quality limitations. Amid of various custom-power devices, the Universal Power-Quality Compensator is the best choice for compensation of both voltage and current allied power-quality issues in distribution system. But, the traditional UPQC device consists of more switching devices which increases the dv/dt stress, switching loss, low efficiency performance, etc. In this regard, a novel reduced-switch UPQC has been proposed with the requirement of fewer switch elements over the traditional UPQC device. The proposed RSUPQC device is used for enhancing power-quality features and DG integration scheme for stabilizing the utility-grid fluctuations by using novel modulation-rate control technique. The performance of proposed RSUPQC device is verified in both power-quality enhancement and DG integration modes by using Matlab/Simulink tool, results are presented.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121591927","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862324
S. Samantaray, P. Kayal
Modern power distribution infrastructure are characterised by efficient and reliable power delivery. However, utilities are facing challenges due to highly volatile demand pattern caused by the variety of loads used by the customers. The necessity of using battery storage systems (BSSs) has come into the scene to ease the challenges. However, planning and integration of BSSs in power distribution network is crucial. This paper presents a strategy for optimal sizing and charging discharging scheduling of BSSs in a power distribution network. The suitable size and schedule of BSSs in a 24-hour time frame has been identified using particle swarm optimization (PSO) technique with viewpoint of minimization of annualized network power loss cost and BSSs investment cost. To test the efficacy of the proposed method it has been is tested on a typical 28-bus Indian radial distribution system. The reduction of network power losses and improvement in low voltage points of the network in high demand hours using proposed model establishes its importance in distribution system (DS) expansion planning.
{"title":"Concurrent Optimization of Sizing and Scheduling for Battery Storage in Power Distribution Network","authors":"S. Samantaray, P. Kayal","doi":"10.1109/ICICCSP53532.2022.9862324","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862324","url":null,"abstract":"Modern power distribution infrastructure are characterised by efficient and reliable power delivery. However, utilities are facing challenges due to highly volatile demand pattern caused by the variety of loads used by the customers. The necessity of using battery storage systems (BSSs) has come into the scene to ease the challenges. However, planning and integration of BSSs in power distribution network is crucial. This paper presents a strategy for optimal sizing and charging discharging scheduling of BSSs in a power distribution network. The suitable size and schedule of BSSs in a 24-hour time frame has been identified using particle swarm optimization (PSO) technique with viewpoint of minimization of annualized network power loss cost and BSSs investment cost. To test the efficacy of the proposed method it has been is tested on a typical 28-bus Indian radial distribution system. The reduction of network power losses and improvement in low voltage points of the network in high demand hours using proposed model establishes its importance in distribution system (DS) expansion planning.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122784761","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862515
Kavya Tammali, Sai Srujan Vangala, Sushmitha Vattikonda, Kowstubha Palle, A. Bhanuchandar, Kasoju Bharath Kumar
In this paper, a generalized reduced-carrier modulation technique is proposed for an asymmetric source configuration of single-phase CHB-MLI topology. To achieve higher level output with fewer modules and isolated DC sources, an asymmetric source configuration is reported in the literature. Basically, trinary (1:3:9) and quasi-linear (1:2:6) source configurations of CHB-topology may offer 27 and 19-levels of output respectively. To achieve a specified level output, level shifted PWM techniques require many numbers of high switching frequency carrier signals and states to decoder arrangements. However, the proposed control technique with reduced carrier modulation does not require states to decoder and thus lowering control complexity. This technique provides low Total Harmonic Distortion (THD) and filtering requirements at the inverter output. The PLECS platform is used to test the functionality of the proposed control scheme.
{"title":"An Asymmetric Source Configuration of Single-Phase CHB-MLI Topology with a Generalized Reduced-Carrier Modulation Technique","authors":"Kavya Tammali, Sai Srujan Vangala, Sushmitha Vattikonda, Kowstubha Palle, A. Bhanuchandar, Kasoju Bharath Kumar","doi":"10.1109/ICICCSP53532.2022.9862515","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862515","url":null,"abstract":"In this paper, a generalized reduced-carrier modulation technique is proposed for an asymmetric source configuration of single-phase CHB-MLI topology. To achieve higher level output with fewer modules and isolated DC sources, an asymmetric source configuration is reported in the literature. Basically, trinary (1:3:9) and quasi-linear (1:2:6) source configurations of CHB-topology may offer 27 and 19-levels of output respectively. To achieve a specified level output, level shifted PWM techniques require many numbers of high switching frequency carrier signals and states to decoder arrangements. However, the proposed control technique with reduced carrier modulation does not require states to decoder and thus lowering control complexity. This technique provides low Total Harmonic Distortion (THD) and filtering requirements at the inverter output. The PLECS platform is used to test the functionality of the proposed control scheme.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121736037","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862378
P. Choudhary, S. Mohapatra, D. Das
Portfolio inflexibility is one of the most explored topics in FIES (financial investment expert system). Conventional ways to resolving the non-linear limited portfolio optimization issue with multi-objective functions are inefficient. In this work, Class Topper Optimization (CTO) technique is used to provide a meta-heuristic strategy for portfolio optimization. The mean-variance portfolio selection is the subject of the research. The goal is to manage an asset portfolio that reduces risk while adhering to the constraint of ensuring a certain level of return. In this work, Indian stock exchange share market value is examined to maximize the sharp ratio and expected returns with minimizing the risk of portfolio. A comparative study with CTO algorithm is undertaken when the model is put to the test on a number of hazardous stock holdings, both restricted and unconstrained. The CTO model has a great processing efficiency when it comes to build optimal risky portfolios. According to preliminary studies of PSO and excel solver, the method looks to be quite promising, with results that are comparable to some state-of-the-art solvers.
{"title":"Class Topper Optimization for the Problem of Portfolio Optimization with a Restricted Set of Assets","authors":"P. Choudhary, S. Mohapatra, D. Das","doi":"10.1109/ICICCSP53532.2022.9862378","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862378","url":null,"abstract":"Portfolio inflexibility is one of the most explored topics in FIES (financial investment expert system). Conventional ways to resolving the non-linear limited portfolio optimization issue with multi-objective functions are inefficient. In this work, Class Topper Optimization (CTO) technique is used to provide a meta-heuristic strategy for portfolio optimization. The mean-variance portfolio selection is the subject of the research. The goal is to manage an asset portfolio that reduces risk while adhering to the constraint of ensuring a certain level of return. In this work, Indian stock exchange share market value is examined to maximize the sharp ratio and expected returns with minimizing the risk of portfolio. A comparative study with CTO algorithm is undertaken when the model is put to the test on a number of hazardous stock holdings, both restricted and unconstrained. The CTO model has a great processing efficiency when it comes to build optimal risky portfolios. According to preliminary studies of PSO and excel solver, the method looks to be quite promising, with results that are comparable to some state-of-the-art solvers.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120861554","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862453
Satyabrata Sahoo, E. Rajsekhar, P. S. Puhan
Nowaday, the power control technique for a large wind turbine is mainly controlled through pitch angle control. The necessity for control of pitch angle is because of stochastic nature of the speed of wind. In this paper, different strategies for pitch angle controllers are compared for a wind turbine with doubly fed induction generator to achieve the steady output power for above rated wind speed. The control strategy utilized here are the conventional Proportional Integral (PI) and Genetic algorithm (GA) optimized PI controllers, which are developed through MATLAB. Finally, the performances of the control strategies are compared. From the results it is found that the GA optimized PI controller depicts an improved performance in comparison to PI controller.
{"title":"Design and simulation of a GA optimized variable speed DFIG based wind turbine using MATLAB","authors":"Satyabrata Sahoo, E. Rajsekhar, P. S. Puhan","doi":"10.1109/ICICCSP53532.2022.9862453","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862453","url":null,"abstract":"Nowaday, the power control technique for a large wind turbine is mainly controlled through pitch angle control. The necessity for control of pitch angle is because of stochastic nature of the speed of wind. In this paper, different strategies for pitch angle controllers are compared for a wind turbine with doubly fed induction generator to achieve the steady output power for above rated wind speed. The control strategy utilized here are the conventional Proportional Integral (PI) and Genetic algorithm (GA) optimized PI controllers, which are developed through MATLAB. Finally, the performances of the control strategies are compared. From the results it is found that the GA optimized PI controller depicts an improved performance in comparison to PI controller.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128344160","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862513
Amar Nath, Bhooshan A. Rajpathak
This paper explains how the Battery Management System (BMS) in an Electric Vehicle uses cell balancing techniques to balance the li-ion cells in lithium-ion battery pack. Cell balancing is done to ensure that all li-ion cells in a battery pack are charged and drained together. There are two types of cells balancing techniques: Passive cell balancing and active cell balancing. Passive cell balancing is accomplished by discharging the excess charge to a bleeding resistor but active cell balancing is accomplished by transferring the charge from higher charged cell to lower charged cell. Moreover, the charge is squandered in passive cell balancing, therefore in this technique cell balancing efficiency is harmed. However, when it comes to active cell balancing, charge transfer is accomplished via a transformer, inductor and capacitor so this balancing technique gives high efficiency compared to passive one. The simulation results of all methods of cell balancing are presented in this paper.
{"title":"Analysis Of Cell Balancing Techniques In BMS For Electric Vehicle","authors":"Amar Nath, Bhooshan A. Rajpathak","doi":"10.1109/ICICCSP53532.2022.9862513","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862513","url":null,"abstract":"This paper explains how the Battery Management System (BMS) in an Electric Vehicle uses cell balancing techniques to balance the li-ion cells in lithium-ion battery pack. Cell balancing is done to ensure that all li-ion cells in a battery pack are charged and drained together. There are two types of cells balancing techniques: Passive cell balancing and active cell balancing. Passive cell balancing is accomplished by discharging the excess charge to a bleeding resistor but active cell balancing is accomplished by transferring the charge from higher charged cell to lower charged cell. Moreover, the charge is squandered in passive cell balancing, therefore in this technique cell balancing efficiency is harmed. However, when it comes to active cell balancing, charge transfer is accomplished via a transformer, inductor and capacitor so this balancing technique gives high efficiency compared to passive one. The simulation results of all methods of cell balancing are presented in this paper.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134053111","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862437
Vaibhav Tiwari, Chandrasen Pandey, D. S. Roy
Understanding the flexibility of traffic requirements on wireless networks is challenging due to the high density of mobile devices connected to the network. This has made things more difficult given the wide range of devices available and the different types of services they can provide. Internet activity data of 5G billing traffic is an important way to analyze load in a confined area, providing solutions for various 5G infrastructure and applications. In previous decades, deep learning techniques have played a vital role in analyzing such data, and their result consolidates the proof of its veteran performance. The open-source dataset used in this experimentation work is well known as Big data Challenge 2014, which was made publicly available by Telecom of Italia. We evaluate our work with four different networks GRU, LSTM, Bi-directional LSTM and encoder decoder LSTM in which we achieve the lowest mean absolute error in the encoder-decoder CNN-LSTM model with a training loss of 0.0108 and validation loss of 0.0064.
{"title":"Internet Activity Forecasting Over 5G Billing Data Using Deep Learning Techniques","authors":"Vaibhav Tiwari, Chandrasen Pandey, D. S. Roy","doi":"10.1109/ICICCSP53532.2022.9862437","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862437","url":null,"abstract":"Understanding the flexibility of traffic requirements on wireless networks is challenging due to the high density of mobile devices connected to the network. This has made things more difficult given the wide range of devices available and the different types of services they can provide. Internet activity data of 5G billing traffic is an important way to analyze load in a confined area, providing solutions for various 5G infrastructure and applications. In previous decades, deep learning techniques have played a vital role in analyzing such data, and their result consolidates the proof of its veteran performance. The open-source dataset used in this experimentation work is well known as Big data Challenge 2014, which was made publicly available by Telecom of Italia. We evaluate our work with four different networks GRU, LSTM, Bi-directional LSTM and encoder decoder LSTM in which we achieve the lowest mean absolute error in the encoder-decoder CNN-LSTM model with a training loss of 0.0108 and validation loss of 0.0064.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130946983","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862495
R. Sivapriyan, N. Kumar, Cv Mohan, N. Sakshi
An efficient and adroit surveillance system is im-perative in the fast-paced digital world, with a monumental rise in video-based surveillance systems for security and monitoring. The pandemic has created the need for effective surveillance and made it more relevant than ever before. The AI-based surveillance system proposed in this paper is capable of performing the traditional functions of a surveillance system and checking if a person is wearing a mask and if his temperature is below a certain threshold. The proposed surveillance system is a video-based surveillance system capable of logging people who are not wearing a mask or whose temperature is not below a specified value. This system is implemented with Raspberry Pi as the central hub for processing, extracting, and analyzing the video stream from a camera. The proposed system aims to identify the mask on people by using a cascade classifier generated by Machine learning techniques, thus mulling down the effects of external factors (lighting condition, position, etc.) that affect the performance of a traditional video surveillance system.
{"title":"Intelligent Surveillance System with Mask Detection and Temperature Monitoring","authors":"R. Sivapriyan, N. Kumar, Cv Mohan, N. Sakshi","doi":"10.1109/ICICCSP53532.2022.9862495","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862495","url":null,"abstract":"An efficient and adroit surveillance system is im-perative in the fast-paced digital world, with a monumental rise in video-based surveillance systems for security and monitoring. The pandemic has created the need for effective surveillance and made it more relevant than ever before. The AI-based surveillance system proposed in this paper is capable of performing the traditional functions of a surveillance system and checking if a person is wearing a mask and if his temperature is below a certain threshold. The proposed surveillance system is a video-based surveillance system capable of logging people who are not wearing a mask or whose temperature is not below a specified value. This system is implemented with Raspberry Pi as the central hub for processing, extracting, and analyzing the video stream from a camera. The proposed system aims to identify the mask on people by using a cascade classifier generated by Machine learning techniques, thus mulling down the effects of external factors (lighting condition, position, etc.) that affect the performance of a traditional video surveillance system.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133815244","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 : 2022-07-21DOI: 10.1109/ICICCSP53532.2022.9862396
C. K. Rao, S. Sahoo, F. F. Yanine
Solar electricity is generated using photovoltaic (PV) systems all over the world. Solar power sources are irregular in nature since PV system output power is intermittent and highly dependent on environmental conditions. Irradiance, humidity, PV surface temperature, and wind speed are only a few of these variables. The uncertainty in photovoltaic generating, it's crucial to plan ahead for solar power generation. Solar power forecasting is required for electric grid supply and demand planning. Because solar power generation is weather-dependent and unregulated, this forecast is complicated and difficult. Selective developed to this goal. Traditional approaches such as statistics, autoregressive moving average, regression, and others were used to forecast PV power before the widespread usage variables are assessed for prediction models based on Artificial Neural Networks (ANN) and regression models. Several PV forecasting algorithms have been of machine learning technologies. Artificial Neural Networks, Support Vector Machines, and hybrid techniques have grown popular as a result of recent advances in machine learning methodologies and access to huge data. This study examines the impacts of numerous environmental conditions on PV system output, as well as the working principle and application of various PV forecasting approaches, in order to better comprehend the insights of PV prediction. Furthermore, the important parameters influencing PV generation are calculated using real-time data.
{"title":"Forecasting Electric Power Generation in a Photovoltaic Power Systems for Smart Energy Management","authors":"C. K. Rao, S. Sahoo, F. F. Yanine","doi":"10.1109/ICICCSP53532.2022.9862396","DOIUrl":"https://doi.org/10.1109/ICICCSP53532.2022.9862396","url":null,"abstract":"Solar electricity is generated using photovoltaic (PV) systems all over the world. Solar power sources are irregular in nature since PV system output power is intermittent and highly dependent on environmental conditions. Irradiance, humidity, PV surface temperature, and wind speed are only a few of these variables. The uncertainty in photovoltaic generating, it's crucial to plan ahead for solar power generation. Solar power forecasting is required for electric grid supply and demand planning. Because solar power generation is weather-dependent and unregulated, this forecast is complicated and difficult. Selective developed to this goal. Traditional approaches such as statistics, autoregressive moving average, regression, and others were used to forecast PV power before the widespread usage variables are assessed for prediction models based on Artificial Neural Networks (ANN) and regression models. Several PV forecasting algorithms have been of machine learning technologies. Artificial Neural Networks, Support Vector Machines, and hybrid techniques have grown popular as a result of recent advances in machine learning methodologies and access to huge data. This study examines the impacts of numerous environmental conditions on PV system output, as well as the working principle and application of various PV forecasting approaches, in order to better comprehend the insights of PV prediction. Furthermore, the important parameters influencing PV generation are calculated using real-time data.","PeriodicalId":326163,"journal":{"name":"2022 International Conference on Intelligent Controller and Computing for Smart Power (ICICCSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116464189","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：