Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752430
S. Dahiya, V. Siwach, Harkesh Sehrawat
Along with the advancement in the network and communication field in recent times, the attackers are also challenging the system in multiple ways. To ensure confidence, integrity, and availability, an intrusion detection system (IDS) is implemented to prevent possible network intrusion by inspecting network traffic and tracing malicious activities. The challenges associated with IDS are varied due to the pace of technology shift, new and different types of attacks need to develop a flexible and adaptive security system to mitigate the challenges. Due to advanced computational machine and CPU throughput, AI-based systems are used in various sectors, which apply machine and deep neural networks. In this paper, the recent paradigm shift of IDS systems to detect and prevent intrusions in public networks in a systematic manner with software defined networks is discussed at length.
{"title":"Review of AI Techniques in development of Network Intrusion Detection System in SDN Framework","authors":"S. Dahiya, V. Siwach, Harkesh Sehrawat","doi":"10.1109/ComPE53109.2021.9752430","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752430","url":null,"abstract":"Along with the advancement in the network and communication field in recent times, the attackers are also challenging the system in multiple ways. To ensure confidence, integrity, and availability, an intrusion detection system (IDS) is implemented to prevent possible network intrusion by inspecting network traffic and tracing malicious activities. The challenges associated with IDS are varied due to the pace of technology shift, new and different types of attacks need to develop a flexible and adaptive security system to mitigate the challenges. Due to advanced computational machine and CPU throughput, AI-based systems are used in various sectors, which apply machine and deep neural networks. In this paper, the recent paradigm shift of IDS systems to detect and prevent intrusions in public networks in a systematic manner with software defined networks is discussed at length.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"256 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121238062","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752029
V. Kiruthika, Madhava Reddy Dadana, V. Tejeswar Reddy, G. Balaji, K. Sankaran, G. Vimalarani
Nowadays traffic congestion has become a major concern in our day-to-day activities because of rapid increase in automobiles and also large time delays between traffic signals. Most of the present-day systems use pre-determined timing circuits to operate traffic signals. Difficulty also arises when there is a need for the emergency vehicles like ambulance, or fire engine to cross the lane during the peak hours. To overcome this issue, design of a constant traffic control framework which will control the traffic as per traffic density is required. This study is aimed at designing a prototype model to control the traffic based on density of vehicles, where the timing of signal will change automatically on sensing the traffic density at each lane. Infrared sensors are used to capture the density information and microcontroller helps in decision making process. In addition, a concept of power harvesting is also proposed in this study. When the density of vehicles is more, the idea is to generate electrical energy by piezo-electric method and store it for future use. The generated energy is stored in battery, and can be used to give power supply to street lights in the traffic junction. The developed system will certainly serve as a boon to regulate the traffic congestion.
{"title":"Intelligent System for Traffic Control with Emergency Vehicle Detection and Piezo-Electric Power Harvesting From Vehicles","authors":"V. Kiruthika, Madhava Reddy Dadana, V. Tejeswar Reddy, G. Balaji, K. Sankaran, G. Vimalarani","doi":"10.1109/ComPE53109.2021.9752029","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752029","url":null,"abstract":"Nowadays traffic congestion has become a major concern in our day-to-day activities because of rapid increase in automobiles and also large time delays between traffic signals. Most of the present-day systems use pre-determined timing circuits to operate traffic signals. Difficulty also arises when there is a need for the emergency vehicles like ambulance, or fire engine to cross the lane during the peak hours. To overcome this issue, design of a constant traffic control framework which will control the traffic as per traffic density is required. This study is aimed at designing a prototype model to control the traffic based on density of vehicles, where the timing of signal will change automatically on sensing the traffic density at each lane. Infrared sensors are used to capture the density information and microcontroller helps in decision making process. In addition, a concept of power harvesting is also proposed in this study. When the density of vehicles is more, the idea is to generate electrical energy by piezo-electric method and store it for future use. The generated energy is stored in battery, and can be used to give power supply to street lights in the traffic junction. The developed system will certainly serve as a boon to regulate the traffic congestion.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124940136","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 Wireless Sensor Network (WSN) is a group of hardware sensors linked together over a wireless network. The sensors are segregated into clusters where every cluster has a cluster head whose job is to collect and transmit data back to the sink node (base station). A sensor node performs activities like data capturing, processing and transfer, which consumes energy. Since these nodes are usually deployed in areas not easily accessible by humans, battery life is one of the key aspects to work on in WSNs. Choosing the appropriate node as a cluster head improves the energy efficiency of the network. This paper proposes a K-Means Energy Efficient Cluster Head Selection Algorithm (KE-CHSA) for WSN where machine learning is applied to form clusters and elect cluster heads. We propose an equation which dynamically changes the number of clusters every round, based on the number of sensor nodes alive and a density parameter. Our algorithm elects the best-suited node as the cluster head considering the energy remaining and its distance from the other nodes. KE-CHSA outperforms the traditional LEACH [21] and C-LEACH [22] by improving the lifetime of WSNs.
{"title":"Cluster Head Selection Algorithm For Wireless Sensor Networks Using Machine Learning","authors":"Samkit Mody, Sulalah Mirkar, Rutwik Ghag, Priyanka Kotecha","doi":"10.1109/ComPE53109.2021.9752264","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752264","url":null,"abstract":"A Wireless Sensor Network (WSN) is a group of hardware sensors linked together over a wireless network. The sensors are segregated into clusters where every cluster has a cluster head whose job is to collect and transmit data back to the sink node (base station). A sensor node performs activities like data capturing, processing and transfer, which consumes energy. Since these nodes are usually deployed in areas not easily accessible by humans, battery life is one of the key aspects to work on in WSNs. Choosing the appropriate node as a cluster head improves the energy efficiency of the network. This paper proposes a K-Means Energy Efficient Cluster Head Selection Algorithm (KE-CHSA) for WSN where machine learning is applied to form clusters and elect cluster heads. We propose an equation which dynamically changes the number of clusters every round, based on the number of sensor nodes alive and a density parameter. Our algorithm elects the best-suited node as the cluster head considering the energy remaining and its distance from the other nodes. KE-CHSA outperforms the traditional LEACH [21] and C-LEACH [22] by improving the lifetime of WSNs.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125052307","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752461
Aashima, Shashank Bhargav, S. Kaushik, V. Dutt
Data-driven techniques like neural networks (ANNs) have often been studied for predicting blood glucose levels (BGLs) of diabetes patients. However, the application of temporal convolutional networks (TCNs) is less known. Moreover, much of the existing literature contains patient-specific BGL models. The objective of this research is to evaluate TCNs for generalized BGL prediction of type-1 diabetes (T1D) patients and compare different calibration methods for selecting optimal hyperparameters for the TCNs. The results obtained by TCNs for BGL prediction using different calibration methods are also compared with artificial neural networks (ANNs). The ANNs were designed to have nearly the same number of trainable parameters as the TCNs. Twenty-four-hour time-series of forty T1D patients at fifteen-minutes intervals were generated using the Automated Insulin Dosage Advisor (AIDA) simulator. Thirty-two patients were chosen at random for model training, and the remaining eight patients were used for model testing. Three calibration methods based on training data, validation data, and k-fold cross-validation were used for hyperparameter tuning. The results showed that the second calibration method of randomly splitting the training data into training and validation datasets, and using the validation results for selecting optimal hyperparameters was the most appropriate. The TCN model with four temporal convolution layers followed by a dense layer obtained the best results. This research highlights the utility of TCNs for generalized BGL prediction.
{"title":"Temporal Convolutional Networks Involving Multi-Patient Approach for Blood Glucose Level Predictions","authors":"Aashima, Shashank Bhargav, S. Kaushik, V. Dutt","doi":"10.1109/ComPE53109.2021.9752461","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752461","url":null,"abstract":"Data-driven techniques like neural networks (ANNs) have often been studied for predicting blood glucose levels (BGLs) of diabetes patients. However, the application of temporal convolutional networks (TCNs) is less known. Moreover, much of the existing literature contains patient-specific BGL models. The objective of this research is to evaluate TCNs for generalized BGL prediction of type-1 diabetes (T1D) patients and compare different calibration methods for selecting optimal hyperparameters for the TCNs. The results obtained by TCNs for BGL prediction using different calibration methods are also compared with artificial neural networks (ANNs). The ANNs were designed to have nearly the same number of trainable parameters as the TCNs. Twenty-four-hour time-series of forty T1D patients at fifteen-minutes intervals were generated using the Automated Insulin Dosage Advisor (AIDA) simulator. Thirty-two patients were chosen at random for model training, and the remaining eight patients were used for model testing. Three calibration methods based on training data, validation data, and k-fold cross-validation were used for hyperparameter tuning. The results showed that the second calibration method of randomly splitting the training data into training and validation datasets, and using the validation results for selecting optimal hyperparameters was the most appropriate. The TCN model with four temporal convolution layers followed by a dense layer obtained the best results. This research highlights the utility of TCNs for generalized BGL prediction.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115341738","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 project, we are uncovering the transient stability analysis and the load flow analysis of the interconnected power system. The Gauss-Seidel method is a successive displacement method; it is an iterative method that is used for nonlinear algebraic equations. The principle behind this method is to solve a set of nonlinear equations of the real and reactive power at each node. This method determines the realization of the solution depending on the precision index set for the power inconsistency and continues iterating until the size of an element is less than the specified value. When the solution converges, real and reactive powers are calculated. The DIgSILENT PowerFactory software is used to substantiate the load flow analysis; it provides different load flow calculation methods. Newton Raphson solution technique is used in combination with current or power mismatch repetitions, and the implemented algorithms show excellent stability and convergence. The analysis of DC power flow rectifies the flow of active power and voltage angle, it is indeed very fast and powerful. Multiple iteration levels guarantee convergence under all conditions and optionally change constraints.
{"title":"Transient Stability Analysis of a Power System Network Using DIgSILENT PowerFactory Software","authors":"Spoorthi Bekal, Subhas Hosamani, Minal Salunke, Shreyanka Patil, Shrinidhi Hedge","doi":"10.1109/ComPE53109.2021.9752440","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752440","url":null,"abstract":"In this project, we are uncovering the transient stability analysis and the load flow analysis of the interconnected power system. The Gauss-Seidel method is a successive displacement method; it is an iterative method that is used for nonlinear algebraic equations. The principle behind this method is to solve a set of nonlinear equations of the real and reactive power at each node. This method determines the realization of the solution depending on the precision index set for the power inconsistency and continues iterating until the size of an element is less than the specified value. When the solution converges, real and reactive powers are calculated. The DIgSILENT PowerFactory software is used to substantiate the load flow analysis; it provides different load flow calculation methods. Newton Raphson solution technique is used in combination with current or power mismatch repetitions, and the implemented algorithms show excellent stability and convergence. The analysis of DC power flow rectifies the flow of active power and voltage angle, it is indeed very fast and powerful. Multiple iteration levels guarantee convergence under all conditions and optionally change constraints.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122567227","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752232
Md Zubair Ahmad, N. Ahmad
In modern society, the importance of software system is growing rapidly. Therefore, quality, reliability, and user fulfillment are the major goals for software development institutions. Software reliability modeling plays an major part in the evaluation of software reliability. In this paper, we present the literature survey during the past forty years of software reliability growth model (SRGM) proposed by researchers. This paper brings all together the theory, practice, and models required to effectively access software reliability. We also review the testing effort functions (TEFs) incorporated into SRGM proposed by various authors to improve software reliability. We discuss and present the classification of software reliability growth models. This paper helps the researchers to have a clear view of parametric software reliability growth modeling. Finally, we conclude the paper by highlighting the contributions and possible research directions.
{"title":"Parametric Software Reliability Growth Model with Testing Effort: A Review","authors":"Md Zubair Ahmad, N. Ahmad","doi":"10.1109/ComPE53109.2021.9752232","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752232","url":null,"abstract":"In modern society, the importance of software system is growing rapidly. Therefore, quality, reliability, and user fulfillment are the major goals for software development institutions. Software reliability modeling plays an major part in the evaluation of software reliability. In this paper, we present the literature survey during the past forty years of software reliability growth model (SRGM) proposed by researchers. This paper brings all together the theory, practice, and models required to effectively access software reliability. We also review the testing effort functions (TEFs) incorporated into SRGM proposed by various authors to improve software reliability. We discuss and present the classification of software reliability growth models. This paper helps the researchers to have a clear view of parametric software reliability growth modeling. Finally, we conclude the paper by highlighting the contributions and possible research directions.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122600611","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 the current scenario of the COVID-19 pandemic estimating the count of number of people present in public places at a particular time has become a significant task. Crowd count is attracting a lot of researchers from the computer vision and deep learning field. It has been found that to achieve this objective computer vision techniques such as deep learning, machine learning, etc. outperform traditional ways of estimating crowd count that uses handcrafted features such as Histogram of gradients, Haar, Scale Invariant Feature Transform and gives better results with higher accuracy. The paper studies the effect of dilation on convolution layers in estimating the crowd count. We have also done a comparative analysis of the developed model with different dilation rates on the ShanghaiTech dataset (part A and part B). The model is trained with images containing occluded and restricted visibility of heads. The model outputs the result with substantial accuracy in estimating the headcount in images of the dense crowd in a sensibly less amount of time.
在当前COVID-19大流行的情况下，估计特定时间公共场所的人数已成为一项重要任务。Crowd count吸引了大量来自计算机视觉和深度学习领域的研究人员。人们发现，为了实现这一目标，深度学习、机器学习等计算机视觉技术比传统的使用梯度直方图(Histogram of gradients)、Haar、尺度不变特征变换(Scale Invariant Feature Transform)等手工特征估计人群数量的方法要好，结果更好，精度更高。本文研究了膨胀对卷积层在估计人群数量中的影响。我们还在ShanghaiTech数据集(a部分和B部分)上对开发的模型进行了不同膨胀率的对比分析。该模型使用包含头部遮挡和受限可见性的图像进行训练。该模型在较短的时间内以相当高的精度在密集人群的图像中估计人数。
{"title":"Dilated CNN for Crowd Count","authors":"Deevesh Chaudhary, Devesh Kumar Srivastava, Akhilesh Kumar Sharma","doi":"10.1109/ComPE53109.2021.9752224","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752224","url":null,"abstract":"In the current scenario of the COVID-19 pandemic estimating the count of number of people present in public places at a particular time has become a significant task. Crowd count is attracting a lot of researchers from the computer vision and deep learning field. It has been found that to achieve this objective computer vision techniques such as deep learning, machine learning, etc. outperform traditional ways of estimating crowd count that uses handcrafted features such as Histogram of gradients, Haar, Scale Invariant Feature Transform and gives better results with higher accuracy. The paper studies the effect of dilation on convolution layers in estimating the crowd count. We have also done a comparative analysis of the developed model with different dilation rates on the ShanghaiTech dataset (part A and part B). The model is trained with images containing occluded and restricted visibility of heads. The model outputs the result with substantial accuracy in estimating the headcount in images of the dense crowd in a sensibly less amount of time.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122613566","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752314
Tabish Mufti, B. Gupta, S. S. Sohail, Deepak Kumar
In the recent, Corona Virus epidemic (COVID-19) increases day-to-day from one individual to another because of contact transmission and COVID-19 is created by the SARS-CoV-2. Identifying and stopping the spreading of contagious epidemic such as COVID-19 is important to handling diseases. One major part contracted to find and detect their previous connections so as to then carefully dissociate any persons likely to have been affected and accommodate dispersion is to find out or explore more transmissible persons. These previous connections can be traced using smart machine such as smart watches and smart phones, which can frequently find and collect the connections and location of their infected ones through their embedded transmissions and localization methodologies or technologies, such as Global Positioning System (GPS) location-based navigation rule, Wi-Fi, biological connections, and Bluetooth. Contact Tracing is the one of the best technologies in which we use a methodology for stopping and controlling the COVID19. The main point of this review paper on the methodology of these smart technologies and figure the model of contact tracing accuracy on the flow of the COVID-19, working of contact tracing, algorithms and control of the COVID-19. In this paper, we have determined the role of contact tracing in COVID-19, effective impacts of Contact Tracing and designed a COVID-19 epidemic model that we created to evaluate the number of people quarantined and effectiveness of the steps to be taken, through the smart watches and smart phone contact tracing technique used. In this review paper, our result shows that in order to be accurate for the COVID-19 pandemic, the contact tracing technique must be traced speedily, a valuation ratio of the population must apply the smart devices technique, contact tracing application and this technology must be correct. All these rigid needs make smart device-based contact tracing rather inefficient at accommodating the flow of the virus during the COVID-19. However, in this phase smart machine-based contact tracing could be immensely and enormously effective and recognizing a second section, where a segment of the community will have increased immunity.
{"title":"Contact Tracing: A Cloud Based Architecture for Safe Covid-19 Mapping","authors":"Tabish Mufti, B. Gupta, S. S. Sohail, Deepak Kumar","doi":"10.1109/ComPE53109.2021.9752314","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752314","url":null,"abstract":"In the recent, Corona Virus epidemic (COVID-19) increases day-to-day from one individual to another because of contact transmission and COVID-19 is created by the SARS-CoV-2. Identifying and stopping the spreading of contagious epidemic such as COVID-19 is important to handling diseases. One major part contracted to find and detect their previous connections so as to then carefully dissociate any persons likely to have been affected and accommodate dispersion is to find out or explore more transmissible persons. These previous connections can be traced using smart machine such as smart watches and smart phones, which can frequently find and collect the connections and location of their infected ones through their embedded transmissions and localization methodologies or technologies, such as Global Positioning System (GPS) location-based navigation rule, Wi-Fi, biological connections, and Bluetooth. Contact Tracing is the one of the best technologies in which we use a methodology for stopping and controlling the COVID19. The main point of this review paper on the methodology of these smart technologies and figure the model of contact tracing accuracy on the flow of the COVID-19, working of contact tracing, algorithms and control of the COVID-19. In this paper, we have determined the role of contact tracing in COVID-19, effective impacts of Contact Tracing and designed a COVID-19 epidemic model that we created to evaluate the number of people quarantined and effectiveness of the steps to be taken, through the smart watches and smart phone contact tracing technique used. In this review paper, our result shows that in order to be accurate for the COVID-19 pandemic, the contact tracing technique must be traced speedily, a valuation ratio of the population must apply the smart devices technique, contact tracing application and this technology must be correct. All these rigid needs make smart device-based contact tracing rather inefficient at accommodating the flow of the virus during the COVID-19. However, in this phase smart machine-based contact tracing could be immensely and enormously effective and recognizing a second section, where a segment of the community will have increased immunity.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116747242","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752251
Amaresh Gantayet, D. K. Dheer
A scenario-based optimal planning strategy of wind distributed generations (WDGs) for a radial distribution network (RDN) considering the dual reactive power support (DRPS) of the three level solid state transformers (SSTs) is proposed in this paper. The K-means algorithm is employed to generate a multi-scenario model for wind speed estimation analogous to each hour of the day and a 24-hour variable load demand is considered in this work. A multi-objective mixed integer non linear programming problem (MINLP) is formulated to address the objectives of voltage profile enhancement (VPE) and energy loss curtailment (ELC), to obtain the capacity and location requirements of SSTs together with the locations and numbers of units of wind turbines to be integrated into the system. The simulation results validated the proposed model and algorithm’s applicability and logic on the 33 bus RDN. The programming was developed in MATLAB R2020a and the paretosearch algorithm is used to address MINLP.
{"title":"Multiobjective Planning Strategy for a Distribution Network integrated with Wind Power System considering Solid State Transformer","authors":"Amaresh Gantayet, D. K. Dheer","doi":"10.1109/ComPE53109.2021.9752251","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752251","url":null,"abstract":"A scenario-based optimal planning strategy of wind distributed generations (WDGs) for a radial distribution network (RDN) considering the dual reactive power support (DRPS) of the three level solid state transformers (SSTs) is proposed in this paper. The K-means algorithm is employed to generate a multi-scenario model for wind speed estimation analogous to each hour of the day and a 24-hour variable load demand is considered in this work. A multi-objective mixed integer non linear programming problem (MINLP) is formulated to address the objectives of voltage profile enhancement (VPE) and energy loss curtailment (ELC), to obtain the capacity and location requirements of SSTs together with the locations and numbers of units of wind turbines to be integrated into the system. The simulation results validated the proposed model and algorithm’s applicability and logic on the 33 bus RDN. The programming was developed in MATLAB R2020a and the paretosearch algorithm is used to address MINLP.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129936535","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751832
Nishit Rathod, Tanuj Gupta, N. Sharma, Saurabh Sharma
As the world has seen a dramatic ascent in the utilization of innovation in recent many years, the field of network safety has gotten always significant. Because of this, it has seen numerous advancements with the field of AI assuming a gigantic part in it. As AI or profound learning is additionally turning out to be further developed every day, use its advantages. Over, the most recent couple of years we have likewise seen a significant ascent in information significance which has made information assortment and development essential. This paper centers around the advancement of Network Intrusion Detection Systems (NIDS) utilizing Deep Learning. NIDS or IDS are utilized to identify any organizations which might act as an assault on any framework. We have utilized the UNSW NB15 dataset for our methodology as it is the latest and is enhanced different variables from its archetype and generally chipped away at the dataset – KDD CUP 99. We have utilized different normalizing instruments and extra trees classifier to set up the dataset for proper profound learning models and highlight determination. The executions utilized here are – Convolutional Neural Network, Recurrent Neural Network, and Long Recurrent Convolutional - Network to think about the outcomes. The arrangements carried out in this paper are both in double and multiclass with the significant center in regard to greatest full- scale accuracy, review, and f-score for the multiclass approach utilizing a connection of proper assault types and a way for additional exploration
近年来，随着世界对创新的利用急剧上升，网络安全领域一直具有重要意义。正因为如此，它已经看到了许多进步，人工智能领域在其中扮演了巨大的角色。随着人工智能或深度学习每天都在进一步发展，利用它的优势。最近几年，我们也看到了信息重要性的显著提升，这使得信息的分类和开发变得至关重要。本文围绕利用深度学习的网络入侵检测系统(NIDS)的进展展开。NIDS或IDS用于识别可能对任何框架进行攻击的任何组织。我们使用了UNSW NB15数据集作为我们的方法，因为它是最新的，并且从原型中增强了不同的变量，并且通常在数据集KDD CUP 99上进行了削减。我们使用了不同的归一化工具和额外的树分类器来建立合适的深度学习模型和突出显示确定的数据集。这里使用的执行是卷积神经网络，循环神经网络和长循环卷积网络来考虑结果。本文所进行的安排是双重和多类的，重要的中心是考虑到最大的全尺寸精度，审查和多类方法的f分，利用适当的攻击类型和一种额外的探索方式的联系
{"title":"Model Comparison and Multiclass Implementation Analysis on the UNSW NB15 Dataset","authors":"Nishit Rathod, Tanuj Gupta, N. Sharma, Saurabh Sharma","doi":"10.1109/ComPE53109.2021.9751832","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751832","url":null,"abstract":"As the world has seen a dramatic ascent in the utilization of innovation in recent many years, the field of network safety has gotten always significant. Because of this, it has seen numerous advancements with the field of AI assuming a gigantic part in it. As AI or profound learning is additionally turning out to be further developed every day, use its advantages. Over, the most recent couple of years we have likewise seen a significant ascent in information significance which has made information assortment and development essential. This paper centers around the advancement of Network Intrusion Detection Systems (NIDS) utilizing Deep Learning. NIDS or IDS are utilized to identify any organizations which might act as an assault on any framework. We have utilized the UNSW NB15 dataset for our methodology as it is the latest and is enhanced different variables from its archetype and generally chipped away at the dataset – KDD CUP 99. We have utilized different normalizing instruments and extra trees classifier to set up the dataset for proper profound learning models and highlight determination. The executions utilized here are – Convolutional Neural Network, Recurrent Neural Network, and Long Recurrent Convolutional - Network to think about the outcomes. The arrangements carried out in this paper are both in double and multiclass with the significant center in regard to greatest full- scale accuracy, review, and f-score for the multiclass approach utilizing a connection of proper assault types and a way for additional exploration","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128359937","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：