Pub Date : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966917
G. Savva, K. Manousakis, Vasilis Sourlas, G. Ellinas
This work considers secure lightpath establishment and content placement in elastic optical networks (EONs). Security of confidential connections against eavesdropping attacks is ensured through network coding among confidential and non-confidential unicast or anycast lightpaths. A unicast connection requires a lightpath establishment from a specific source to a destination, whereas, for an anycast connection, the source can be chosen from a specific set of network nodes (data centers) where the content can be located at. To address this problem, a heuristic algorithm is developed that considers the different types of connections to be established, with the objective to maximize the security level of the confidential connections, while source node selection and content placement are performed for the anycast connections. Performance results demonstrate that anycast connections significantly improve the security level of confidential connections with no additional spectrum requirements, compared to the scenario where only non-confidential unicast connections are used for security purposes.
{"title":"Joint Content Placement and Secure Lightpath Provisioning in EONs Supporting Anycast Traffic","authors":"G. Savva, K. Manousakis, Vasilis Sourlas, G. Ellinas","doi":"10.1109/CAMAD55695.2022.9966917","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966917","url":null,"abstract":"This work considers secure lightpath establishment and content placement in elastic optical networks (EONs). Security of confidential connections against eavesdropping attacks is ensured through network coding among confidential and non-confidential unicast or anycast lightpaths. A unicast connection requires a lightpath establishment from a specific source to a destination, whereas, for an anycast connection, the source can be chosen from a specific set of network nodes (data centers) where the content can be located at. To address this problem, a heuristic algorithm is developed that considers the different types of connections to be established, with the objective to maximize the security level of the confidential connections, while source node selection and content placement are performed for the anycast connections. Performance results demonstrate that anycast connections significantly improve the security level of confidential connections with no additional spectrum requirements, compared to the scenario where only non-confidential unicast connections are used for security purposes.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121329790","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966916
Andreas Andreou, C. Mavromoustakis, J. M. Batalla, E. Markakis, G. Mastorakis, E. Pallis
Integration of UAVs into the fifth generation (5G) cellular networks as aerial base stations would be a promising technology to achieve several goals, namely ubiquitous accessibility, robust navigation, ease of monitoring and management. Real-time distribution of critical information must be embedded throughout transport infrastructure. The ability of Unmanned Aerial Vehicles (UAVs) with high agility, mobility, and flexibility to offload data traffic from terrestrial base stations and Road Side Units (RSUs) by providing additional access points enables swift, accurate, timely and actionable decisions in Intelligent Transportation System (ITS) based on data-driven insights. However, we must ensure secure data exchange when multi-purpose RSU is deployed for confidential data acquisition and distribution. It is a prerequisite for data sovereignty in the Internet of Vehicles (IoV) network to be facilitated by secure data exchange between trusted parties. Therefore, we propose a robust encryption method to incentivize data exchange within the ITS ecosystem to enable confidential data sharing in IoV communication. In addition, the novel encryption method we present enables real-time, encryption and decryption for ciphertexts containing confidential information between UAVs and the control center.
{"title":"Secure Two-Way Communications Between UAVs and Control Center in IoV 5G Communication","authors":"Andreas Andreou, C. Mavromoustakis, J. M. Batalla, E. Markakis, G. Mastorakis, E. Pallis","doi":"10.1109/CAMAD55695.2022.9966916","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966916","url":null,"abstract":"Integration of UAVs into the fifth generation (5G) cellular networks as aerial base stations would be a promising technology to achieve several goals, namely ubiquitous accessibility, robust navigation, ease of monitoring and management. Real-time distribution of critical information must be embedded throughout transport infrastructure. The ability of Unmanned Aerial Vehicles (UAVs) with high agility, mobility, and flexibility to offload data traffic from terrestrial base stations and Road Side Units (RSUs) by providing additional access points enables swift, accurate, timely and actionable decisions in Intelligent Transportation System (ITS) based on data-driven insights. However, we must ensure secure data exchange when multi-purpose RSU is deployed for confidential data acquisition and distribution. It is a prerequisite for data sovereignty in the Internet of Vehicles (IoV) network to be facilitated by secure data exchange between trusted parties. Therefore, we propose a robust encryption method to incentivize data exchange within the ITS ecosystem to enable confidential data sharing in IoV communication. In addition, the novel encryption method we present enables real-time, encryption and decryption for ciphertexts containing confidential information between UAVs and the control center.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115601046","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966883
Rohan Desai, T. G. Venkatesh
Machine Learning Algorithms have become a crucial tool for designing Intrusion Detection Systems(IDS). The research community has identified deep learning architectures like Convolutional Neural Networks(CNN) as the go-to solution for IDS. However, these deep learning models are not immune to new outliers. We propose a Robust Network intrusion Detection system (RNIDS) model, which combines a CNN architecture followed by K Nearest Neighbors method. The proposed RNIDS model can classify different known attacks, and then predict if a new arriving traffic is an outlier with very high accuracy. We train and evaluate a CNN-based model which can classify attacks with an accuracy of 98.3% using up only 70,252 training parameters.
{"title":"Robust Network Intrusion Detection Systems for Outlier Detection","authors":"Rohan Desai, T. G. Venkatesh","doi":"10.1109/CAMAD55695.2022.9966883","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966883","url":null,"abstract":"Machine Learning Algorithms have become a crucial tool for designing Intrusion Detection Systems(IDS). The research community has identified deep learning architectures like Convolutional Neural Networks(CNN) as the go-to solution for IDS. However, these deep learning models are not immune to new outliers. We propose a Robust Network intrusion Detection system (RNIDS) model, which combines a CNN architecture followed by K Nearest Neighbors method. The proposed RNIDS model can classify different known attacks, and then predict if a new arriving traffic is an outlier with very high accuracy. We train and evaluate a CNN-based model which can classify attacks with an accuracy of 98.3% using up only 70,252 training parameters.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114065346","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966900
Eric Gyamfi, A. Jurcut
The Industrial Internet of Things (IIoT) remains an inevitable system in various applications that require data collection and processing in the modern industrial revolution. The IIoTs are responsible for critical data collection and transmission to cloud servers to address life-dependent problems. However, these cyber-physical devices are vulnerable to network attacks such as selective forwarding, flooding, and Sybil attacks. Meanwhile, behavioural patterns characterise the IIoT devices under such attacks due to their effect on transmission latency, power consumption, and computational time. Hence, this paper presents a multi-trust security system to monitor and record these parameters, such as network byte-in and byte-out, CPU usage, and energy consumption on the IIoT device. Based on the ML model, we created an efficient multi-trust attack detection system (M-TADS) to detect denial of service attacks (DoS) in the IIoT. IIoT devices have resource constraints that practically prevent them from fully implementing the proposed M-TADS on the same cyber-physical device. Hence, the captured parameters from the IIoT devices are offloaded to a deep neural network model created with long short term memory (LSTM). The LSTM is hosted on a multi-access edge computing (MEC) server at the network edge to determine the possible existence of the DoS attack signature. Due to the high latency accompanying DoS attack, we introduce a custom hold and check filter on the IIoT devices. The proposed M-TADS performance is verified through simulations, and the results confirm high performance in terms of throughput, energy consumption, packet delay, and IIoT network DoS attack detection accuracy.
{"title":"M-TADS: A Multi-Trust DoS Attack Detection System for MEC-enabled Industrial loT","authors":"Eric Gyamfi, A. Jurcut","doi":"10.1109/CAMAD55695.2022.9966900","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966900","url":null,"abstract":"The Industrial Internet of Things (IIoT) remains an inevitable system in various applications that require data collection and processing in the modern industrial revolution. The IIoTs are responsible for critical data collection and transmission to cloud servers to address life-dependent problems. However, these cyber-physical devices are vulnerable to network attacks such as selective forwarding, flooding, and Sybil attacks. Meanwhile, behavioural patterns characterise the IIoT devices under such attacks due to their effect on transmission latency, power consumption, and computational time. Hence, this paper presents a multi-trust security system to monitor and record these parameters, such as network byte-in and byte-out, CPU usage, and energy consumption on the IIoT device. Based on the ML model, we created an efficient multi-trust attack detection system (M-TADS) to detect denial of service attacks (DoS) in the IIoT. IIoT devices have resource constraints that practically prevent them from fully implementing the proposed M-TADS on the same cyber-physical device. Hence, the captured parameters from the IIoT devices are offloaded to a deep neural network model created with long short term memory (LSTM). The LSTM is hosted on a multi-access edge computing (MEC) server at the network edge to determine the possible existence of the DoS attack signature. Due to the high latency accompanying DoS attack, we introduce a custom hold and check filter on the IIoT devices. The proposed M-TADS performance is verified through simulations, and the results confirm high performance in terms of throughput, energy consumption, packet delay, and IIoT network DoS attack detection accuracy.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127020675","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966902
Felix Klement, H. C. Pöhls, S. Katzenbeisser
Modern cars offer one common interface to the outside, the OBD. Among the multitude of protocols that could exchange messages with the car's internal devices over OBD the CAN-BUS protocol is the most well-known; several commercial devices (so-called dongles) would allow to send and receive messages without any user-controlled restrictions. In order to enable fine-grained filtering on the CAN - BUS we exploit a security weakness called man-in-the-middle: the car or dongle does not apply any origin authentication as neither digital signatures nor message authentication codes (MACs) are used. We are the first to present this approach and offer measurements for our concurrent and multi-stage design that enables a fine-grained and extensible filtering approach for all protocols within the OBD.
{"title":"Change Your Car's Filters: Efficient Concurrent and Multi-Stage Firewall for OBD-II Network Traffic","authors":"Felix Klement, H. C. Pöhls, S. Katzenbeisser","doi":"10.1109/CAMAD55695.2022.9966902","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966902","url":null,"abstract":"Modern cars offer one common interface to the outside, the OBD. Among the multitude of protocols that could exchange messages with the car's internal devices over OBD the CAN-BUS protocol is the most well-known; several commercial devices (so-called dongles) would allow to send and receive messages without any user-controlled restrictions. In order to enable fine-grained filtering on the CAN - BUS we exploit a security weakness called man-in-the-middle: the car or dongle does not apply any origin authentication as neither digital signatures nor message authentication codes (MACs) are used. We are the first to present this approach and offer measurements for our concurrent and multi-stage design that enables a fine-grained and extensible filtering approach for all protocols within the OBD.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"245 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120900191","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.10214402
Kyle Watters, E. Coyle
Power control algorithms for cognitive radio networks allow users to minimize interference with primary users. The interference values are calculated in reference to some known primary user, whose location is approximated as a bivariate distribution. To close links between nodes using minimal energy, the user must also be able to approximate the bit error rate (BER) of a transmission. This paper focuses on mobile cognitive radio networks utilizing sectored antennas. Nodes use BER estimation to minimize the transmitted energy required for each hop while choosing multi-hop routes that minimize the interference to primary users. Highly mobile networks necessitate the ability to approximate the BER and interference values quickly, necessitating the approximations in the paper.
{"title":"Achieving Low Probability of Interference in Spread Spectrum Cognitive Radio Networks","authors":"Kyle Watters, E. Coyle","doi":"10.1109/CAMAD55695.2022.10214402","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.10214402","url":null,"abstract":"Power control algorithms for cognitive radio networks allow users to minimize interference with primary users. The interference values are calculated in reference to some known primary user, whose location is approximated as a bivariate distribution. To close links between nodes using minimal energy, the user must also be able to approximate the bit error rate (BER) of a transmission. This paper focuses on mobile cognitive radio networks utilizing sectored antennas. Nodes use BER estimation to minimize the transmitted energy required for each hop while choosing multi-hop routes that minimize the interference to primary users. Highly mobile networks necessitate the ability to approximate the BER and interference values quickly, necessitating the approximations in the paper.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124868052","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966918
Caio B. Bezerra De Souza, J. J. Arnez, Tarcisio Fernandes, Cassio A. Tavares Alves, J. O. D. Sousa
The purpose of this work is to assess the battery consumption for voice call services in both 5G Standalone (SA) and 4G Long Term Evolution (LTE) mobile networks. The voice call services are assessed as a function of the power consumption during a call over IP Multimedia Subsystem (IMS) network. A top-class Device Under Test (DUT) and an experimental setup was used to evaluate the current and power values during the experimentation. Measurement results show that the DUT consumes up to 38.88 % less energy when performing voice calls using a 5G SA network. Additionally, voice calls made using 5G SA networks had superior quality compared to voice calls made in 4G networks, with an average jitter difference of up to 16.5 ms. Based on the results, analyses of the battery consumption are provided for improvements to the IMS technology and Voice over New Radio (VoNR) commercial use.
这项工作的目的是评估5G独立(SA)和4G长期演进(LTE)移动网络中语音通话服务的电池消耗。语音通话业务以IP多媒体子系统IMS (call over IP Multimedia Subsystem)网络的功耗为函数进行评估。采用一流的被测设备(DUT)和实验装置来评估实验过程中的电流和功率值。测试结果表明，在5G SA组网下，被测设备语音通话能耗可降低38.88%。此外，使用5G SA网络进行的语音通话质量优于使用4G网络进行的语音通话，平均抖动差高达16.5 ms。在此基础上，为改进IMS技术和VoNR商用提供了电池消耗分析。
{"title":"Analysis of Power Consumption in 4G VoLTE and 5G VoNR Over IMS Network","authors":"Caio B. Bezerra De Souza, J. J. Arnez, Tarcisio Fernandes, Cassio A. Tavares Alves, J. O. D. Sousa","doi":"10.1109/CAMAD55695.2022.9966918","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966918","url":null,"abstract":"The purpose of this work is to assess the battery consumption for voice call services in both 5G Standalone (SA) and 4G Long Term Evolution (LTE) mobile networks. The voice call services are assessed as a function of the power consumption during a call over IP Multimedia Subsystem (IMS) network. A top-class Device Under Test (DUT) and an experimental setup was used to evaluate the current and power values during the experimentation. Measurement results show that the DUT consumes up to 38.88 % less energy when performing voice calls using a 5G SA network. Additionally, voice calls made using 5G SA networks had superior quality compared to voice calls made in 4G networks, with an average jitter difference of up to 16.5 ms. Based on the results, analyses of the battery consumption are provided for improvements to the IMS technology and Voice over New Radio (VoNR) commercial use.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128561434","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966903
Neda Ahmadi, I. Mporas, Anastasios K. Papazafeiropoulos, P. Kourtessis, J. Senior
Power control (PC) plays a crucial role in massive multiple-input-multiple-output (mMIMO) networks. There are several heuristic algorithms, like the weighted mean square error (WMMSE) algorithm, used to optimise the PC. In order these algorithms to perform the power allocation they require high computational power. In this paper, we address this problem through the application of machine learning (ML)-based algorithms as they can produce close to optimal solutions with a very low computational complexity. We propose the use of transfer learning with deep neural networks (TLDNN) under the objective of maximising the sum spectral efficiency (SE). The evaluation results demonstrate that the TLDNN approach outperforms the deep neural network (DNN) based PC and is twice faster than the WMMSE based PC.
{"title":"Power Control in massive MIMO Networks Using Transfer Learning with Deep Neural Networks","authors":"Neda Ahmadi, I. Mporas, Anastasios K. Papazafeiropoulos, P. Kourtessis, J. Senior","doi":"10.1109/CAMAD55695.2022.9966903","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966903","url":null,"abstract":"Power control (PC) plays a crucial role in massive multiple-input-multiple-output (mMIMO) networks. There are several heuristic algorithms, like the weighted mean square error (WMMSE) algorithm, used to optimise the PC. In order these algorithms to perform the power allocation they require high computational power. In this paper, we address this problem through the application of machine learning (ML)-based algorithms as they can produce close to optimal solutions with a very low computational complexity. We propose the use of transfer learning with deep neural networks (TLDNN) under the objective of maximising the sum spectral efficiency (SE). The evaluation results demonstrate that the TLDNN approach outperforms the deep neural network (DNN) based PC and is twice faster than the WMMSE based PC.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125281473","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966911
I. Keramidi, D. Uzunidis, Marinos Vlasakis, P. Sarigiannidis, I. Moscholios
Machine Learning (ML) algorithms can be efficiently employed to calculate various performance metrics in telecommunication systems showing comparable accuracy with analytical expressions while at the same time decreasing the computation time in several operational cases. In this paper, we examine the impact of six ML methods both on the accuracy of calculations and on the estimation time and benchmark them against an analytical formalism which solves a 2D Markov chain to estimate seven performance metrics in a vehicular system of a mobile hotspot. As a consequence, when using ML methods, we show that the computational complexity can be reduced, especially in cases where the system capacity is large and the computational complexity of the 2D Markov chain increases. More specifically, the proposed approach is applied in a dataset which comprises 100,000 operational cases, demonstrating a reduction of estimation time of more than two orders of magnitude while maintaining the average error less than 4.5%.
{"title":"Exploiting Machine Learning for the Performance Analysis of a Mobile Hotspot with a Call Admission Control Mechanism","authors":"I. Keramidi, D. Uzunidis, Marinos Vlasakis, P. Sarigiannidis, I. Moscholios","doi":"10.1109/CAMAD55695.2022.9966911","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966911","url":null,"abstract":"Machine Learning (ML) algorithms can be efficiently employed to calculate various performance metrics in telecommunication systems showing comparable accuracy with analytical expressions while at the same time decreasing the computation time in several operational cases. In this paper, we examine the impact of six ML methods both on the accuracy of calculations and on the estimation time and benchmark them against an analytical formalism which solves a 2D Markov chain to estimate seven performance metrics in a vehicular system of a mobile hotspot. As a consequence, when using ML methods, we show that the computational complexity can be reduced, especially in cases where the system capacity is large and the computational complexity of the 2D Markov chain increases. More specifically, the proposed approach is applied in a dataset which comprises 100,000 operational cases, demonstrating a reduction of estimation time of more than two orders of magnitude while maintaining the average error less than 4.5%.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123708185","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 : 2022-11-02DOI: 10.1109/CAMAD55695.2022.9966914
Kalpit Dilip Ballal, Radheshyam Singh, S. C. Nwabuona, L. Dittmann, S. Ruepp
As the number of connected devices is increasing, several new communication technologies are getting developed and deployed to serve the rising need. Cellular Internet of Things (C-IoT) is the umbrella of Low Power Wide Area Network (LPWAN) technologies introduced by 3GPP in order to support critical IoT applications. C- IoT technologies are deployed by Mobile Network Operators (MNO) of the country to support IoT devices. Unfortunately, just like other wireless communication technologies, C- IoT may also suffer coverage outages in some regions of the country (e.g., Forests, basements, etc.). Unlike other wireless technologies such as LTE, 5G, etc. C-IoT is typically only deployed in one frequency spectrum (band 20 in Denmark [17]), making the handover of these IoT devices in an outage scenario difficult. This significantly affects critical IoT applications like remote health monitors, location tracers, etc., where communicating data through the network is extremely important. This paper focuses on using Device-to-Device (D2D) communication using LoRa and LoRaWAN to create a low-cost, easy-to-deploy, and manage network infrastructure to minimize data loss because of outage scenarios. In order to validate this approach, authors have developed a number of prototype devices based on C-IoT and LoRa/LoRaWAN and performed experiments.
{"title":"Implementation of Failure Recovery in Emergency IoT Applications Using D2D in LoRa/LoRaWAN","authors":"Kalpit Dilip Ballal, Radheshyam Singh, S. C. Nwabuona, L. Dittmann, S. Ruepp","doi":"10.1109/CAMAD55695.2022.9966914","DOIUrl":"https://doi.org/10.1109/CAMAD55695.2022.9966914","url":null,"abstract":"As the number of connected devices is increasing, several new communication technologies are getting developed and deployed to serve the rising need. Cellular Internet of Things (C-IoT) is the umbrella of Low Power Wide Area Network (LPWAN) technologies introduced by 3GPP in order to support critical IoT applications. C- IoT technologies are deployed by Mobile Network Operators (MNO) of the country to support IoT devices. Unfortunately, just like other wireless communication technologies, C- IoT may also suffer coverage outages in some regions of the country (e.g., Forests, basements, etc.). Unlike other wireless technologies such as LTE, 5G, etc. C-IoT is typically only deployed in one frequency spectrum (band 20 in Denmark [17]), making the handover of these IoT devices in an outage scenario difficult. This significantly affects critical IoT applications like remote health monitors, location tracers, etc., where communicating data through the network is extremely important. This paper focuses on using Device-to-Device (D2D) communication using LoRa and LoRaWAN to create a low-cost, easy-to-deploy, and manage network infrastructure to minimize data loss because of outage scenarios. In order to validate this approach, authors have developed a number of prototype devices based on C-IoT and LoRa/LoRaWAN and performed experiments.","PeriodicalId":166029,"journal":{"name":"2022 IEEE 27th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122536231","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：