2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)最新文献_第2页

MEC-EnergySaver: Unleashing Efficiency Through D2D and Data Compression MEC-EnergySaver：通过 D2D 和数据压缩提高效率

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427262

Anindita Ghosh, Poulomi Mukherjee, Tanmay De

{"title":"MEC-EnergySaver: Unleashing Efficiency Through D2D and Data Compression","authors":"Anindita Ghosh, Poulomi Mukherjee, Tanmay De","doi":"10.1109/COMSNETS59351.2024.10427262","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427262","url":null,"abstract":"The shift from basic cell phones to smartphones has ushered in intelligent devices, alongside a surge in mobile apps that reshape daily life. Simultaneously, technologies like data analytics, AI and IoT have enabled smart homes and advanced transport systems, demanding substantial computational power from mobile devices. To tackle this challenge, mobile-edge computing (MEC) has emerged as a solution. Unlike remote cloud computing, MEC offers computing services at the network's edge, allowing mobile users to transfer their computing tasks to MEC servers located nearby. However, MEC systems face challenges in efficient computation offloading and distributing resources in a way that reduces energy use and processing times. The evolution of mobile devices and the rise of data-intensive applications have led to the need for efficient computing solutions like MEC, with the potential to integrate data compression for energy savings. This paper introduced a two-phase approach for request servicing in MEC systems. The first phase prioritizes Device-to-Device (D2D) connections based on device proximity, efficiently pairing devices for data exchange. Unpaired devices are directed to the nearest MEC node. In the second phase, requests not fulfilled via D2D connections are handled by strategically positioned MEC nodes, ensuring comprehensive coverage and minimizing network energy consumption.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"105 2","pages":"551-557"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532738","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}

引用次数: 0

Towards Peer-to-Peer Split Learning 实现点对点拆分学习

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427274

Jayant Vyas, Ritesh Dhananjay Nikose, Pallavi Ramicetty, Shravan Mohan, Milind Savagaonkar, Anutosh Maitra, Shubhashis Sengupta

{"title":"Towards Peer-to-Peer Split Learning","authors":"Jayant Vyas, Ritesh Dhananjay Nikose, Pallavi Ramicetty, Shravan Mohan, Milind Savagaonkar, Anutosh Maitra, Shubhashis Sengupta","doi":"10.1109/COMSNETS59351.2024.10427274","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427274","url":null,"abstract":"In this paper, the $N$-split learning scheme is presented. This scheme allows for learning a feed-forward deep neural network on devices with limited memory for model and data. The central idea in this scheme is to divide the model and data over different devices. The model is split layer-wise (in subsets of consecutive layers), while the data is split homogeneously. The device with the first few layers starts the forward pass of the backpropagation algorithm for a training sample from its data subset and passes the output to the device with the next subset of layers. This process continues till the last layers are computed. The last device to compute the forward pass then computes the backward pass, and the process proceeds in the reverse direction, thereby calculating a part of the gradients. The gradients are accumulated for a batch of samples, and the parameters are updated. After completing an epoch, the devices perform a swap of the layers, and the above process starts again. It continues till the model is trained satisfactorily. In an improved variant, called Fast $N$-split learning, the forward and backward passes are considered separately and possibly done on different devices to gain from pipeline parallelism. The layers performing the forward pass store the output in a buffer, which will be used by the devices performing the backward pass. The devices performing backward passes communicate the update for parameters to the devices doing forward passes. As earlier, this continues till the model is trained satisfactorily. Analysis, routines for determining the optimal split for both schemes and simulations are presented for corroboration.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"279 4","pages":"881-888"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532830","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}

引用次数: 0

Prediction of Drug-Target Interactions Using BERT for Protein Sequences and Drug Compound 使用 BERT 预测蛋白质序列和药物化合物的药物-靶点相互作用

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427536

Essmily Simon, Sanjay S Bankapur

引用次数: 0

Performance Analysis of Multiple HAPS-Based Hybrid FSO/RF Space-Air-Ground Network 基于多个 HAPS 的 FSO/RF 空地混合网络性能分析

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427543

D. Singh, Swaminathan Ramabadran, Aravind Marrapu, A. Madhukumar

{"title":"Performance Analysis of Multiple HAPS-Based Hybrid FSO/RF Space-Air-Ground Network","authors":"D. Singh, Swaminathan Ramabadran, Aravind Marrapu, A. Madhukumar","doi":"10.1109/COMSNETS59351.2024.10427543","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427543","url":null,"abstract":"Sixth generation (6G) networks are anticipated to support increasingly data-hungry applications by expanding the network capabilities and connectivity. Free space optics (FSO) communication with space-air-ground (SAG) network becomes a potential solution to meet the enormous traffic demands and ubiquitous connectivity requirement in 6G networks. In spite of various advantages offered by FSO communication such as high bandwidth availability, large unlicensed spectrum, better security, etc., the FSO link exhibits a high degree of responsiveness to atmospheric turbulence, attenuation, and pointing errors. Thus to mitigate the severe atmospheric effects, we propose a multiple high-altitude platform station (HAPS)-based SAG network, where HAPS functions as a decode-and-forward (DF) relay node between ground station and satellite. We take into account a hybrid FSO/radio frequency (RF) link for connecting ground station and HAPS nodes and an FSO link between HAPS and satellite. The performance analysis of the proposed SAG network involves evaluating the outage probability and average symbol error rate (SER) considering the presence of pointing errors and assuming Málaga distribution in case of FSO and shadowed k - µ fading distribution in case of RF link. Furthermore, asymptotic analysis is conducted to determine the diversity gain of the proposed system. Numerical results demonstrate that the proposed multiple HAPS-based hybrid FSO/RF SAG network outperforms all other existing HAPS-based SAG network models in the literature.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"12 1","pages":"920-926"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532585","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}

引用次数: 0

MaOC: Model-Assisted Optimal Control for Ductless-Split Cooling Systems in Building Environments MaOC：建筑环境中无管道分体式冷却系统的模型辅助优化控制

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427219

Keshav Kaushik, Vinayak S. Naik

{"title":"MaOC: Model-Assisted Optimal Control for Ductless-Split Cooling Systems in Building Environments","authors":"Keshav Kaushik, Vinayak S. Naik","doi":"10.1109/COMSNETS59351.2024.10427219","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427219","url":null,"abstract":"Demand for energy in buildings is growing exponentially, and cooling systems contribute to more than50% of buildings' energy consumption. With global warming, we need to save energy on the cooling systems. This paper targets spaces where multiple ductless-split cooling systems are deployed, commonly known as split ACs. Unlike ducted centralized cooling systems, they do not have central sensing and control. To optimize the energy consumption of the ductless-split cooling system, we propose a Model-assisted Optimal Control (MaOC) algorithm that observes the thermal environment of the room, measures efficiencies of the ACs in cooling the room, and generates an optimal execution schedule for the cooling system. We observe that the mathematical model generated for cooling systems follows the properties of the convex function. We define a MAXMIN problem to minimize energy consumption and maximize efficiency. We use the statistical distribution of cooling systems' efficiency to generate a long-term control trajectory. We evaluate MaOC for ductless-split cooling systems in a real-world environment and simulation. We compare it with solutions based on the greedy technique and Reinforcement Learning. It consumes 17% of energy compared to the one using a greedy technique and takes 34% less time to reach the desired temperature. We observe that MaOC consumes almost the same energy as a more complex one that uses Reinforcement Learning but takes less time to cool the room. In the simulation, we find that the energy consumption of MaOS is nearer to the optimum.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"477 1","pages":"790-797"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532597","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}

引用次数: 0

Cognitive Controller Framework for Seamless Orchestration and Management in Enterprise Wireless Networks 面向企业无线网络无缝协调和管理的认知控制器框架

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10426990

S. Nadaf, H. Rath, Sumanta Patro, Garima Mishra, M. Menon

{"title":"Cognitive Controller Framework for Seamless Orchestration and Management in Enterprise Wireless Networks","authors":"S. Nadaf, H. Rath, Sumanta Patro, Garima Mishra, M. Menon","doi":"10.1109/COMSNETS59351.2024.10426990","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10426990","url":null,"abstract":"There is an exponential rise in the usage of mobiles for accessing different applications and services in today's technology world. Many different use cases such as vehicular communications, sensors/other devices communications, tactile communications, virtual reality, rural broadband, industrial/factory applications, satellite communications etc., are being realized with the help of high-end communication technologies. However, to meet different requirements suitably, there is a need for intelligent communication systems which can adapt to business requirements and deliver service guarantee based on certain criteria. Perhaps, the use of Artificial Intelligence/Machine Learning (AI/ML) techniques becomes imperative to gather the state of the underlying network elements and make optimal decisions for handling upcoming service requests. Further, efficient operations of the communication networks based on the insights gathered on prevailing conditions is the need of the hour. In this paper, we propose a Cognitive Controller framework which can help for better management and orchestration of Enterprise Wireless Local Area Networks (WLANs). It is based on the microservices architecture, and we demonstrate a seamless mobility management use-case for Enterprise WLAN using the Cognitive Controller framework.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"309 5","pages":"321-323"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532818","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}

引用次数: 0

Green 6G: Energy Awareness in Design 绿色 6G：设计中的能源意识

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427334

Rashmi Kamran, Shwetha Kiran, P. Jha, A. Karandikar, P. Chaporkar

{"title":"Green 6G: Energy Awareness in Design","authors":"Rashmi Kamran, Shwetha Kiran, P. Jha, A. Karandikar, P. Chaporkar","doi":"10.1109/COMSNETS59351.2024.10427334","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427334","url":null,"abstract":"Usage and application trends for Sixth Generation (6G) networks (based on ITU's IMT-2030 framework) include immersive multimedia and multi-sensory interactions, digital twin and virtual world, smart industries, digital health and well-being, integration of sensing and communication along with ubiquitous connectivity, intelligence, and computing. 6G technology to support such diverse and demanding use case scenarios is also expected to result in minimized and efficient usage of energy. 6G networks designed to address the challenge of environmental sustainability in addition to serving the above use case scenarios can be named “Green 6G”. In Green 6G, the proposal is to include energy awareness in its design along with energy usage optimization at the network level. Users can be provided with information on service-level energy usage in the network including the source of energy (renewable or non-renewable sources), and their (user's) choice should be taken into consideration for service delivery in the network. In this context, there are various ongoing activities in standardization bodies to bring energy awareness into network design. We summarize these standardization initiatives and identify aspects which remain unaddressed in the existing mobile networks. Further, we present the required features of Green 6G design for future networks and highlight associated challenges. We also provide a design perspective for Green 6G architecture as a step towards this direction.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"302 1","pages":"1122-1125"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140532820","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}

引用次数: 0

Machine Learning-Based Trustworthy Diabetes Prediction Model 基于机器学习的可信糖尿病预测模型

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427272

Aruna Devi B, Karthik N

引用次数: 0

Time-Series Forecasting Using Continuous Variables-Based Quantum Neural Networks 使用基于连续变量的量子神经网络进行时间序列预测

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427192

Prabhat Anand, M. G. Chandra, Ankit Khandelwal

{"title":"Time-Series Forecasting Using Continuous Variables-Based Quantum Neural Networks","authors":"Prabhat Anand, M. G. Chandra, Ankit Khandelwal","doi":"10.1109/COMSNETS59351.2024.10427192","DOIUrl":"https://doi.org/10.1109/COMSNETS59351.2024.10427192","url":null,"abstract":"Continuous Variable-based Quantum Computing (CVQC) has been developing at speed with a lot of promise in the field of quantum machine learning. It provides a direct and natural way to accommodate continuous values into the quantum computing framework. We carried out experiments on quantum simulators where we compared the results of time series forecasting on a type of continuous-variable quantum variational circuit, called CV-Quantum Neural Networks (CVQNN) for different types of time series like Energy Consumption data and stock price data. We compared their performance with a discrete variable-based variational quantum algorithm as well as with a classical Neural Network. Experiments showed that CVQNN can function just like a neural network but with a lesser number of parameters while tackling the two obstacles that are faced in qubit-based computing, which are, tackling continuous values and introducing controlled non-linearity into the circuits. We used the circuit for multi-step forecasting that performed better for a larger prediction window than one-step forecasting done iteratively on the predicted data. The resembling architecture of CVQNN with that of a neural network offers the flexibility of using a similar structure for both one-step and multi-step forecasting.","PeriodicalId":518748,"journal":{"name":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","volume":"185 1","pages":"994-999"},"PeriodicalIF":0.0,"publicationDate":"2024-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140533010","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}

引用次数: 0

Palanam: A Deep Learning Based Childhood Defense System 帕拉纳姆基于深度学习的童年防御系统

2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS) Pub Date : 2024-01-03 DOI: 10.1109/COMSNETS59351.2024.10427109

Anurag Singh, Preeti Singh, Vibhor Sharma, Dhruv Tyagi, Nilesh Pandey, Bhavesh Vaid

引用次数: 0