Pub Date : 2020-10-01DOI: 10.4018/ijitn.2020100108
Soon Heng Mavric Tan, C. Yeo
This paper makes use of a simple and inexpensive software-defined radio (SDR) to demonstrate the potential threats posed to wireless communication. SDR is a radio communication system where components that are traditionally implemented in hardware are being replaced via software running on computing devices. The authors make use of a simple SDR to demonstrate how local disruption to wireless communication can be easily carried out. In particular, the authors show how FM radio broadcast can be hijacked and the spoofing of GPS location signals using a single SDR on a local basis as well as how Google Maps apps on an Android phone can be fooled by the spoofed GPS data. The authors also show how an ‘autonomous' car can be re-routed via emulation with a rigged up remote control toy car. The spoofing of GPS signals is a potential threat to all GPS-based applications, especially when powerful radios are used. The security threats on GPS-based navigation especially for drones and autonomous vehicles are real.
{"title":"GPS Location Spoofing and FM Broadcast Intrusion Using Software-Defined Radio","authors":"Soon Heng Mavric Tan, C. Yeo","doi":"10.4018/ijitn.2020100108","DOIUrl":"https://doi.org/10.4018/ijitn.2020100108","url":null,"abstract":"This paper makes use of a simple and inexpensive software-defined radio (SDR) to demonstrate the potential threats posed to wireless communication. SDR is a radio communication system where components that are traditionally implemented in hardware are being replaced via software running on computing devices. The authors make use of a simple SDR to demonstrate how local disruption to wireless communication can be easily carried out. In particular, the authors show how FM radio broadcast can be hijacked and the spoofing of GPS location signals using a single SDR on a local basis as well as how Google Maps apps on an Android phone can be fooled by the spoofed GPS data. The authors also show how an ‘autonomous' car can be re-routed via emulation with a rigged up remote control toy car. The spoofing of GPS signals is a potential threat to all GPS-based applications, especially when powerful radios are used. The security threats on GPS-based navigation especially for drones and autonomous vehicles are real.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122720200","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 : 2020-10-01DOI: 10.4018/ijitn.2020100110
Hasita Kaja, C. Beard
Vehicular ad-hoc networks (VANETs) have been an important part of intelligent transport systems (ITS). Developing a reliable network for vehicle-to-vehicle communication is a crucial part of network deployment. In the present paper, the authors are discussing a layered approach towards reliability of VANETs. This paper will consider different layers of the dedicated short-range communications (DSRC) protocol stack and discuss key reliability indicators in each layer. This layered approach towards computing reliability results in more practical probability calculations and improves the minimum probability of reliability achievable by the VANETs. The authors discuss about different techniques to increase the reliability of VANETs. In the future works, the goal is to calculate probability density and distribution functions of reliability at each layer and derive combined reliability and availability of a given vehicular ad-hoc network (VANET).
{"title":"A Multi-Layered Reliability Approach in Vehicular Ad-Hoc Networks","authors":"Hasita Kaja, C. Beard","doi":"10.4018/ijitn.2020100110","DOIUrl":"https://doi.org/10.4018/ijitn.2020100110","url":null,"abstract":"Vehicular ad-hoc networks (VANETs) have been an important part of intelligent transport systems (ITS). Developing a reliable network for vehicle-to-vehicle communication is a crucial part of network deployment. In the present paper, the authors are discussing a layered approach towards reliability of VANETs. This paper will consider different layers of the dedicated short-range communications (DSRC) protocol stack and discuss key reliability indicators in each layer. This layered approach towards computing reliability results in more practical probability calculations and improves the minimum probability of reliability achievable by the VANETs. The authors discuss about different techniques to increase the reliability of VANETs. In the future works, the goal is to calculate probability density and distribution functions of reliability at each layer and derive combined reliability and availability of a given vehicular ad-hoc network (VANET).","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127090314","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 : 2020-10-01DOI: 10.4018/ijitn.2020100103
Sultan Almuhammadi, O. Bawazeer
A cryptographic hash function is an important component used in many applications, such as blockchain, authentication, data integrity, and digital signature. With the rapid increase in usage of mobile devices, more attention goes towards the tradeoffs between performance and security of cryptographic hash functions on mobile devices due to their limited computational power. The researchers in this paper study the most common cryptographic hash functions and highlights the tradeoffs between their performance and security. The hash functions considered in this study are MD4, MD5, Whirlpool, and the hash functions in the SHA family. The security of these hash functions is compared based on recent attacks in terms of collision resistance, preimage attacks, and sensitivity analysis. While the performance is tested on different input block sizes, useful observations and recommendations are made based on the results of this study.
{"title":"Performance and Security Tradeoffs in Cryptographic Hash Functions","authors":"Sultan Almuhammadi, O. Bawazeer","doi":"10.4018/ijitn.2020100103","DOIUrl":"https://doi.org/10.4018/ijitn.2020100103","url":null,"abstract":"A cryptographic hash function is an important component used in many applications, such as blockchain, authentication, data integrity, and digital signature. With the rapid increase in usage of mobile devices, more attention goes towards the tradeoffs between performance and security of cryptographic hash functions on mobile devices due to their limited computational power. The researchers in this paper study the most common cryptographic hash functions and highlights the tradeoffs between their performance and security. The hash functions considered in this study are MD4, MD5, Whirlpool, and the hash functions in the SHA family. The security of these hash functions is compared based on recent attacks in terms of collision resistance, preimage attacks, and sensitivity analysis. While the performance is tested on different input block sizes, useful observations and recommendations are made based on the results of this study.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127739795","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 : 2020-10-01DOI: 10.4018/ijitn.2020100107
D. Kanellopoulos, Ali H. Wheeb
Multimedia applications impose different QoS requirements (e.g., bounded end-to-end delay and jitter) and need an enhanced transport layer protocol that should handle packet loss, minimize errors, manage network congestion, and transmit efficiently. Across an IP network, the transport layer protocol provides data transmission and affects the QoS provided to the application on hand. The most common transport layer protocols used by Internet applications are TCP and UDP. There are also advanced transport layer protocols such as DCCP and TFRC. The authors evaluated the performance of UDP, DCCP, SCTP, and TFRC over wired networks for three traffic flows: data transmission, video streaming, and voice over IP. The evaluation criteria were throughput, end-to-end delay, and packet loss ratio. They compared their performance to learn in which traffic flow/service each of these protocols functions better than the others. The throughput of SCTP and TFRC is better than UDP. DCCP is superior to SCTP and TFRC in terms of end-to-end delay. SCTP is suitable for Internet applications that require high bandwidth.
{"title":"Simulated Performance of TFRC, DCCP, SCTP, and UDP Protocols Over Wired Networks","authors":"D. Kanellopoulos, Ali H. Wheeb","doi":"10.4018/ijitn.2020100107","DOIUrl":"https://doi.org/10.4018/ijitn.2020100107","url":null,"abstract":"Multimedia applications impose different QoS requirements (e.g., bounded end-to-end delay and jitter) and need an enhanced transport layer protocol that should handle packet loss, minimize errors, manage network congestion, and transmit efficiently. Across an IP network, the transport layer protocol provides data transmission and affects the QoS provided to the application on hand. The most common transport layer protocols used by Internet applications are TCP and UDP. There are also advanced transport layer protocols such as DCCP and TFRC. The authors evaluated the performance of UDP, DCCP, SCTP, and TFRC over wired networks for three traffic flows: data transmission, video streaming, and voice over IP. The evaluation criteria were throughput, end-to-end delay, and packet loss ratio. They compared their performance to learn in which traffic flow/service each of these protocols functions better than the others. The throughput of SCTP and TFRC is better than UDP. DCCP is superior to SCTP and TFRC in terms of end-to-end delay. SCTP is suitable for Internet applications that require high bandwidth.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125617945","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 : 2020-10-01DOI: 10.4018/ijitn.2020100102
Faten Mashta, Wissam Altabban, Mohieddin Wainakh
Spectrum sensing in cognitive radio has difficult and complex requirements, requiring speed and good detection performance at low SNR ratios. As suggested in IEEE 802.22, the primary user signal needs to be detected at SNR = -21dB with a probability of detection exceeds 0.9. Conventional spectrum sensing methods such as the energy detector, which is characterized by simplicity with good detection performance at high SNR values, are ineffective at low SNR values, whereas eigenvalues detection methods have good detection performance at low SNR ratios, but they have high complexity. In this paper, the authors investigate the process of spectrum sensing in two stages: in the first stage (coarse sensing), the energy detector is adopted, while in the second stage (fine sensing), eigenvalues detection methods are used. This method improves performance in terms of probability of detection and computational complexity, as the authors compared the performance of two-stage sensing scheme with ones where only energy detection or eigenvalues detection is performed.
{"title":"Two-Stage Spectrum Sensing for Cognitive Radio Using Eigenvalues Detection","authors":"Faten Mashta, Wissam Altabban, Mohieddin Wainakh","doi":"10.4018/ijitn.2020100102","DOIUrl":"https://doi.org/10.4018/ijitn.2020100102","url":null,"abstract":"Spectrum sensing in cognitive radio has difficult and complex requirements, requiring speed and good detection performance at low SNR ratios. As suggested in IEEE 802.22, the primary user signal needs to be detected at SNR = -21dB with a probability of detection exceeds 0.9. Conventional spectrum sensing methods such as the energy detector, which is characterized by simplicity with good detection performance at high SNR values, are ineffective at low SNR values, whereas eigenvalues detection methods have good detection performance at low SNR ratios, but they have high complexity. In this paper, the authors investigate the process of spectrum sensing in two stages: in the first stage (coarse sensing), the energy detector is adopted, while in the second stage (fine sensing), eigenvalues detection methods are used. This method improves performance in terms of probability of detection and computational complexity, as the authors compared the performance of two-stage sensing scheme with ones where only energy detection or eigenvalues detection is performed.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124000316","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 : 2020-10-01DOI: 10.4018/ijitn.2020100101
I. Lokshina, C. Lanting
Equilibria of queueing networks are a means for performance analysis of real communication networks introduced as Markov chains. In this paper, the authors developed, evaluated, and compared computational procedures to obtain numerical solutions for queueing networks in equilibrium with the use of direct, iterative, and aggregative techniques in steady-state analysis of Markov chains. Advanced computational procedures are developed with the use of Gaussian elimination, power iteration, Courtois' decomposition, and Takahashi's iteration techniques. Numerical examples are provided together with comparative analysis of obtained results. The authors consider these procedures are also applicable to other domains where systems are described with comparable queuing models and stochastic techniques are sufficiently relevant. Several suitable domains of applicability are proposed.
{"title":"Analysis of Queueing Networks in Equilibrium: Numerical Steady-State Solutions of Markov Chains","authors":"I. Lokshina, C. Lanting","doi":"10.4018/ijitn.2020100101","DOIUrl":"https://doi.org/10.4018/ijitn.2020100101","url":null,"abstract":"Equilibria of queueing networks are a means for performance analysis of real communication networks introduced as Markov chains. In this paper, the authors developed, evaluated, and compared computational procedures to obtain numerical solutions for queueing networks in equilibrium with the use of direct, iterative, and aggregative techniques in steady-state analysis of Markov chains. Advanced computational procedures are developed with the use of Gaussian elimination, power iteration, Courtois' decomposition, and Takahashi's iteration techniques. Numerical examples are provided together with comparative analysis of obtained results. The authors consider these procedures are also applicable to other domains where systems are described with comparable queuing models and stochastic techniques are sufficiently relevant. Several suitable domains of applicability are proposed.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134255494","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 : 2020-07-01DOI: 10.4018/ijitn.2020070101
K. Siountri, Emmanouil Skondras, D. Vergados
Building information modeling (BIM) is a revolutionary technology that provides all the necessary mechanisms to achieve end-to-end communication, data exchange and information sharing between project actors, leading to smarter outcomes for communities and more efficient projects for AEC service providers. 3D models generated in the context of engaging in the BIM process and as-delivered physical assets through building management systems (BMS) adopt Internet of Things (IoT) architectures and services. However, the orchestration of IoT devices in a highly modular environment with many moving parts and inter-dependencies between the stakeholders of this environment, lead to many security issues. This article focuses on applying novel technologies in the construction industry, such as BIM, IoT, and Blockchain, but also on examining their interconnection and interoperability on a proposed system architecture on a case of a building (museum), where efficient security, management and monitoring are considered crucial factors for the unobstructed operation of the organization that hosts.
{"title":"Developing Smart Buildings Using Blockchain, Internet of Things, and Building Information Modeling","authors":"K. Siountri, Emmanouil Skondras, D. Vergados","doi":"10.4018/ijitn.2020070101","DOIUrl":"https://doi.org/10.4018/ijitn.2020070101","url":null,"abstract":"Building information modeling (BIM) is a revolutionary technology that provides all the necessary mechanisms to achieve end-to-end communication, data exchange and information sharing between project actors, leading to smarter outcomes for communities and more efficient projects for AEC service providers. 3D models generated in the context of engaging in the BIM process and as-delivered physical assets through building management systems (BMS) adopt Internet of Things (IoT) architectures and services. However, the orchestration of IoT devices in a highly modular environment with many moving parts and inter-dependencies between the stakeholders of this environment, lead to many security issues. This article focuses on applying novel technologies in the construction industry, such as BIM, IoT, and Blockchain, but also on examining their interconnection and interoperability on a proposed system architecture on a case of a building (museum), where efficient security, management and monitoring are considered crucial factors for the unobstructed operation of the organization that hosts.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123562655","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 : 2020-07-01DOI: 10.4018/ijitn.2020070102
Opeoluwa Tosin Eluwole, M. Ojo
Fascinating technologies, such as software defined networking (SDN), network function virtualization (NFV) and mobile edge computing (MEC) among others, have introduced software-enabling capabilities to telecommunications, mobile and wireless communications. To depict this systemic evolution, various terminologies, such as system cloudification, network programmability, advanced computing and most popularly, softwarization, have been used by numerous scholars. Softwarization is now becoming a fully established phenomenon, especially in the new era of the rapidly evolving Internet of Things (IoT), artificial intelligence (AI) and the looming 5G technology. Away from the research and development (R&D) focus on the technological capabilities of softwarization, this article highlights the main stakeholders in softwarization and underlines a tripartite influence of the systemic evolution i.e. technical, social and economic impacts, all of which will be vital in ensuring a sustainable 5G technology and beyond.
{"title":"The Key Impacts of Softwarization in the Modern Era of 5G and the Internet of Things","authors":"Opeoluwa Tosin Eluwole, M. Ojo","doi":"10.4018/ijitn.2020070102","DOIUrl":"https://doi.org/10.4018/ijitn.2020070102","url":null,"abstract":"Fascinating technologies, such as software defined networking (SDN), network function virtualization (NFV) and mobile edge computing (MEC) among others, have introduced software-enabling capabilities to telecommunications, mobile and wireless communications. To depict this systemic evolution, various terminologies, such as system cloudification, network programmability, advanced computing and most popularly, softwarization, have been used by numerous scholars. Softwarization is now becoming a fully established phenomenon, especially in the new era of the rapidly evolving Internet of Things (IoT), artificial intelligence (AI) and the looming 5G technology. Away from the research and development (R&D) focus on the technological capabilities of softwarization, this article highlights the main stakeholders in softwarization and underlines a tripartite influence of the systemic evolution i.e. technical, social and economic impacts, all of which will be vital in ensuring a sustainable 5G technology and beyond.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121162648","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 : 2020-07-01DOI: 10.4018/ijitn.2020070103
Fatma Gumus, Derya Yiltas-Kaplan
Software Defined Network (SDN) is a programmable network architecture that provides innovative solutions to the problems of the traditional networks. Congestion control is still an uncharted territory for this technology. In this work, a congestion prediction scheme has been developed by using neural networks. Minimum Redundancy Maximum Relevance (mRMR) feature selection algorithm was performed on the data collected from the OMNET++ simulation. The novelty of this study also covers the implementation of mRMR in an SDN congestion prediction problem. After evaluating the relevance scores, two highest ranking features were used. On the learning stage Nonlinear Autoregressive Exogenous Neural Network (NARX), Nonlinear Autoregressive Neural Network, and Nonlinear Feedforward Neural Network algorithms were executed. These algorithms had not been used before in SDNs according to the best of the authors knowledge. The experiments represented that NARX was the best prediction algorithm. This machine learning approach can be easily integrated to different topologies and application areas.
{"title":"Congestion Prediction System With Artificial Neural Networks","authors":"Fatma Gumus, Derya Yiltas-Kaplan","doi":"10.4018/ijitn.2020070103","DOIUrl":"https://doi.org/10.4018/ijitn.2020070103","url":null,"abstract":"Software Defined Network (SDN) is a programmable network architecture that provides innovative solutions to the problems of the traditional networks. Congestion control is still an uncharted territory for this technology. In this work, a congestion prediction scheme has been developed by using neural networks. Minimum Redundancy Maximum Relevance (mRMR) feature selection algorithm was performed on the data collected from the OMNET++ simulation. The novelty of this study also covers the implementation of mRMR in an SDN congestion prediction problem. After evaluating the relevance scores, two highest ranking features were used. On the learning stage Nonlinear Autoregressive Exogenous Neural Network (NARX), Nonlinear Autoregressive Neural Network, and Nonlinear Feedforward Neural Network algorithms were executed. These algorithms had not been used before in SDNs according to the best of the authors knowledge. The experiments represented that NARX was the best prediction algorithm. This machine learning approach can be easily integrated to different topologies and application areas.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131594742","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 : 2020-07-01DOI: 10.4018/ijitn.2020070104
Mohamed S. Hassan, M. H. Ismail, M. El-Tarhuni, Fatema Aseeri
The recently proposed extension of the LTE operation to the unlicensed spectrum, known as LTE-Unlicensed (LTE-U), is not only expected to alleviate the congestion in the licensed band but is expected to result in an increase in the network capacity, as well. Unfortunately, such extension is challenged by a coexistence problem with wireless technologies operating in the unlicensed spectrum, especially Wi-Fi. Therefore, this article employs time series forecasting methods to enable efficient LTE coexistence with Wi-Fi. This is done by enabling the LTE-U Home eNodeB (HeNB) to avoid collisions with Wi-Fi by predicting the state of the unlicensed channels prior to using them. Specifically, this research proposes a recurrent neural network-based algorithm that utilizes Long Short Term Memory (LSTM) networks with time series decomposition to predict the state of the channels in the unlicensed spectrum. The authors investigate the performance of the proposed approach using extensive simulations. The results show that the proposed LSTM-based method outperforms the classical Listen Before Talk (LBT) and duty-cycling approaches in terms of improved coexistence of LTE-U with Wi-Fi.
{"title":"On the Enabling of Efficient Coexistence of LTE With WiFi: A Machine Learning-Based Approach","authors":"Mohamed S. Hassan, M. H. Ismail, M. El-Tarhuni, Fatema Aseeri","doi":"10.4018/ijitn.2020070104","DOIUrl":"https://doi.org/10.4018/ijitn.2020070104","url":null,"abstract":"The recently proposed extension of the LTE operation to the unlicensed spectrum, known as LTE-Unlicensed (LTE-U), is not only expected to alleviate the congestion in the licensed band but is expected to result in an increase in the network capacity, as well. Unfortunately, such extension is challenged by a coexistence problem with wireless technologies operating in the unlicensed spectrum, especially Wi-Fi. Therefore, this article employs time series forecasting methods to enable efficient LTE coexistence with Wi-Fi. This is done by enabling the LTE-U Home eNodeB (HeNB) to avoid collisions with Wi-Fi by predicting the state of the unlicensed channels prior to using them. Specifically, this research proposes a recurrent neural network-based algorithm that utilizes Long Short Term Memory (LSTM) networks with time series decomposition to predict the state of the channels in the unlicensed spectrum. The authors investigate the performance of the proposed approach using extensive simulations. The results show that the proposed LSTM-based method outperforms the classical Listen Before Talk (LBT) and duty-cycling approaches in terms of improved coexistence of LTE-U with Wi-Fi.","PeriodicalId":120331,"journal":{"name":"Int. J. Interdiscip. Telecommun. Netw.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128205601","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：