Pub Date : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998384
S. Ohta, Daichi Miyamoto
Folded Clos network (FCN) is an important topology as it plays a significant role in building high-performance data center networks. To exchange packets over an FCN, traffic load must be uniformly diffused to fully utilize its high bandwidth. As a method to do this, the rebalancing algorithm was proposed. Previous studies have demonstrated the effectiveness of the method through theoretical analysis and computer simulation. However, its practical feasibility has not been elucidated. Moreover, its performance has not been confirmed on a physical experimental environment. This paper reports how the rebalancing algorithm is implemented on switches built on PCs using software tools supported by the Linux OS. This confirms that it is relatively easy to practically implement the algorithm. In addition, the performance of the implemented algorithm was assessed and compared with that of a conventional method through an experiment. As a result, the rebalancing algorithm was found to be more advantageous in avoiding traffic congestion for heavy traffic and flows with different sizes.
{"title":"Implementation and Experimental Evaluation of the Rebalancing Algorithm for Folded Clos Networks","authors":"S. Ohta, Daichi Miyamoto","doi":"10.1109/ITNAC55475.2022.9998384","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998384","url":null,"abstract":"Folded Clos network (FCN) is an important topology as it plays a significant role in building high-performance data center networks. To exchange packets over an FCN, traffic load must be uniformly diffused to fully utilize its high bandwidth. As a method to do this, the rebalancing algorithm was proposed. Previous studies have demonstrated the effectiveness of the method through theoretical analysis and computer simulation. However, its practical feasibility has not been elucidated. Moreover, its performance has not been confirmed on a physical experimental environment. This paper reports how the rebalancing algorithm is implemented on switches built on PCs using software tools supported by the Linux OS. This confirms that it is relatively easy to practically implement the algorithm. In addition, the performance of the implemented algorithm was assessed and compared with that of a conventional method through an experiment. As a result, the rebalancing algorithm was found to be more advantageous in avoiding traffic congestion for heavy traffic and flows with different sizes.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114564148","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998377
Alexander Frömming, L. Häring, A. Czylwik
A multicarrier transmission system with clipping distortion on the transmitting side, additive white Gaussian noise on the receiving side and a frequency-selective channel is considered with respect to adaptive modulation. The investigations are made based on an optical intensity modulated band-limited DC-offset orthogonal frequency-division multiplexing (DCO-OFDM) system. Usually, the frequency-selective channel transfer function determines the bit allocation. In the present scenario, this approach must be adapted, because the clipping noise is distorted by the same channel as the information signal. Therefore, adaptive modulation can no longer achieve a gain when clipping becomes the dominating source of distortion. In this paper, the total signal-to-interference-and-noise power ratio (SINR), considering clipping noise at the transmitter and additive noise at the receiver, is calculated. Based on this result, the optimal bit allocation table (BAT) for each scenario, ranging from no clipping to very strong clipping, can be determined. It is shown that the error probability of a band-limited DCO-OFDM transmission can be approximately halved based on this concept. Additionally, the optimal transmit power to achieve the lowest error probability in a given system can be theoretically calculated. The results are verified by simulations.
{"title":"Optimizing Adaptive Modulation for Symmetrically Clipped Band-Limited DCO-OFDM","authors":"Alexander Frömming, L. Häring, A. Czylwik","doi":"10.1109/ITNAC55475.2022.9998377","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998377","url":null,"abstract":"A multicarrier transmission system with clipping distortion on the transmitting side, additive white Gaussian noise on the receiving side and a frequency-selective channel is considered with respect to adaptive modulation. The investigations are made based on an optical intensity modulated band-limited DC-offset orthogonal frequency-division multiplexing (DCO-OFDM) system. Usually, the frequency-selective channel transfer function determines the bit allocation. In the present scenario, this approach must be adapted, because the clipping noise is distorted by the same channel as the information signal. Therefore, adaptive modulation can no longer achieve a gain when clipping becomes the dominating source of distortion. In this paper, the total signal-to-interference-and-noise power ratio (SINR), considering clipping noise at the transmitter and additive noise at the receiver, is calculated. Based on this result, the optimal bit allocation table (BAT) for each scenario, ranging from no clipping to very strong clipping, can be determined. It is shown that the error probability of a band-limited DCO-OFDM transmission can be approximately halved based on this concept. Additionally, the optimal transmit power to achieve the lowest error probability in a given system can be theoretically calculated. The results are verified by simulations.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130571394","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998385
Eman Ebaid, K. Navaie
Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.
{"title":"Optimum NN Algorithms Parameters on the UJIIndoorLoc for Wi-Fi Fingerprinting Indoor Positioning Systems","authors":"Eman Ebaid, K. Navaie","doi":"10.1109/ITNAC55475.2022.9998385","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998385","url":null,"abstract":"Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128809990","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998390
Dongsheng Zheng, Zijiang Zhou, Wenyao Li, B. Jiao
Improving the bit error rate (BER) performance of finite-length block code is required in the scenarios of ultra-reliable and low latency communications. Nonetheless, the complexity of algorithms to find such a high performance block code increases dramatically as blocklength increases. Towards this end, the paper proposes a low-complexity recursive algorithm to search the optimal binary block codes subject to the requirement of the minimum Hamming distance. As a result, two optimal code sets of code-length 16 and 32 are found with code rate of 1/2. The simulation results show that the constructed codes under binary phase shift keying (BPSK) modulation outperform the systematic polar codes in the same blocklength in terms of the BER performance.
{"title":"A Low-Complexity Approach for Constructing the Optimal Binary Finite-Length Block Code","authors":"Dongsheng Zheng, Zijiang Zhou, Wenyao Li, B. Jiao","doi":"10.1109/ITNAC55475.2022.9998390","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998390","url":null,"abstract":"Improving the bit error rate (BER) performance of finite-length block code is required in the scenarios of ultra-reliable and low latency communications. Nonetheless, the complexity of algorithms to find such a high performance block code increases dramatically as blocklength increases. Towards this end, the paper proposes a low-complexity recursive algorithm to search the optimal binary block codes subject to the requirement of the minimum Hamming distance. As a result, two optimal code sets of code-length 16 and 32 are found with code rate of 1/2. The simulation results show that the constructed codes under binary phase shift keying (BPSK) modulation outperform the systematic polar codes in the same blocklength in terms of the BER performance.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128833705","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998404
Yuki Komatsu, Shin Kato, M. Itami
In our research, we developed a method for detecting approaching objects at intersection by focusing on geometric features of point cloud obtained from 3D-LiDAR, without using pre-generated maps to understand the environment. This method can be applied to intersection with diagonal crossings, and can detect approaching vehicles and pedestrians at distances of up to 49 m and 38 m, respectively. The results also showed that the detection was robust and continuous. Furthermore, this process can be used in 50 ms per a frame, so that can be used in real time. This will lead to collision prediction and judgment of starting for automated vehicles.
{"title":"Detecting Approaching Objects at Intersection Using on-Vehicle 3D-LiDAR for Automated Driving Vehicle","authors":"Yuki Komatsu, Shin Kato, M. Itami","doi":"10.1109/ITNAC55475.2022.9998404","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998404","url":null,"abstract":"In our research, we developed a method for detecting approaching objects at intersection by focusing on geometric features of point cloud obtained from 3D-LiDAR, without using pre-generated maps to understand the environment. This method can be applied to intersection with diagonal crossings, and can detect approaching vehicles and pedestrians at distances of up to 49 m and 38 m, respectively. The results also showed that the detection was robust and continuous. Furthermore, this process can be used in 50 ms per a frame, so that can be used in real time. This will lead to collision prediction and judgment of starting for automated vehicles.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128230648","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998340
Ammad Ali Syed, S. Ayaz, T. Leinmüller, Madhu Chandra
Reliability is considered the paramount requirement of the future vehicle which requires a huge amount of safety-critical data traversing through the in-vehicle network (IVN). To achieve reliability in Ethernet-based IVN, time-sensitive network (TSN) proposes a fault-tolerant mechanism called frame replication and elimination for reliability (FRER) in IEEE 802.1 CB standard. In this paper, fault-tolerant joint scheduling and routing of static applications is developed which considers TSN's time-aware shaper (TAS) and FRER standards. The fault-tolerant scheduling and routing problem is formulated as a mixed-integer programming (MIP) model and solved with a CPLEX optimizer. Furthermore, a cuckoo search based meta-heuristic is developed to achieve scalable schedule solutions. Experimental results show that the cuckoo search takes 5.7 min to schedules 90 flows and utilizes 8% more bins as compared to the optimal solution.
可靠性被认为是未来车辆的首要要求，这需要通过车载网络(IVN)传输大量安全关键数据。为了实现基于以太网的IVN的可靠性，时间敏感网络TSN (time-sensitive network)在IEEE 802.1 CB标准中提出了帧复制和消除可靠性(frame replication and elimination for reliability, FRER)的容错机制。考虑TSN的时间感知整形器(TAS)和FRER标准，研究了静态应用的容错联合调度和路由问题。将容错调度和路由问题表述为一个混合整数规划(MIP)模型，并用CPLEX优化器进行求解。在此基础上，提出了一种基于布谷鸟搜索的元启发式算法。实验结果表明，与最优方案相比，布谷鸟搜索调度90个流需要5.7 min，使用的箱数增加了8%。
{"title":"Fault-Tolerant Static Scheduling and Routing for In-vehicle Networks","authors":"Ammad Ali Syed, S. Ayaz, T. Leinmüller, Madhu Chandra","doi":"10.1109/ITNAC55475.2022.9998340","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998340","url":null,"abstract":"Reliability is considered the paramount requirement of the future vehicle which requires a huge amount of safety-critical data traversing through the in-vehicle network (IVN). To achieve reliability in Ethernet-based IVN, time-sensitive network (TSN) proposes a fault-tolerant mechanism called frame replication and elimination for reliability (FRER) in IEEE 802.1 CB standard. In this paper, fault-tolerant joint scheduling and routing of static applications is developed which considers TSN's time-aware shaper (TAS) and FRER standards. The fault-tolerant scheduling and routing problem is formulated as a mixed-integer programming (MIP) model and solved with a CPLEX optimizer. Furthermore, a cuckoo search based meta-heuristic is developed to achieve scalable schedule solutions. Experimental results show that the cuckoo search takes 5.7 min to schedules 90 flows and utilizes 8% more bins as compared to the optimal solution.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"9 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999131","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998406
Camilo Anzola-Rojas, R. J. D. Barroso, I. de Miguel, J. Aguado, N. Merayo, P. Fernández, R. Lorenzo, E. Abril
The upcoming Connected and cooperative and automated mobility paradigm (CCAM) requires the deployment of road-side units (RSUs) beside the roads to provide wireless communication to connected-vehicle on board units. The deployment of RSUs along the highways provide low-latency communication, suitable for applications where high-speed response is needed, such as autonomous driving and crash avoidance. These RSUs must be connected to the Internet through a high-bandwidth and reliable access network being the optical fiber technologies the most convenient technology for that. In this paper, we propose a planning scheme for enabling RSUs with optical access networks. The method starts choosing the locations of the access network headers (the connection points to the local service provider facilities), and then defines the connections between the headers and the RSUs in a convenient manner considering the road infrastructure. Then, two deployment technologies based on optical fibers are compared: Point to Point (P2P) and Passive Optical Network (PON). A techno-economic analysis was performed, and results show that P2P and PON approaches are very similar in terms of cost, therefore, due to technical advantages, P2P is recommended as deployment strategy for the described scenario.
{"title":"Enabling Road Side Units with Optical Access Networks: Planning and Techno-Economic Analysis","authors":"Camilo Anzola-Rojas, R. J. D. Barroso, I. de Miguel, J. Aguado, N. Merayo, P. Fernández, R. Lorenzo, E. Abril","doi":"10.1109/ITNAC55475.2022.9998406","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998406","url":null,"abstract":"The upcoming Connected and cooperative and automated mobility paradigm (CCAM) requires the deployment of road-side units (RSUs) beside the roads to provide wireless communication to connected-vehicle on board units. The deployment of RSUs along the highways provide low-latency communication, suitable for applications where high-speed response is needed, such as autonomous driving and crash avoidance. These RSUs must be connected to the Internet through a high-bandwidth and reliable access network being the optical fiber technologies the most convenient technology for that. In this paper, we propose a planning scheme for enabling RSUs with optical access networks. The method starts choosing the locations of the access network headers (the connection points to the local service provider facilities), and then defines the connections between the headers and the RSUs in a convenient manner considering the road infrastructure. Then, two deployment technologies based on optical fibers are compared: Point to Point (P2P) and Passive Optical Network (PON). A techno-economic analysis was performed, and results show that P2P and PON approaches are very similar in terms of cost, therefore, due to technical advantages, P2P is recommended as deployment strategy for the described scenario.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123184295","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998341
S. Alsemairi
Wireless sensor networks (WSNs) have become one of the most interesting research areas in recent years. A WSN is mainly composed of a set of homogeneous sensor nodes and an in-situ base-station (BS) that are randomly deployed within a delimited area of interest. These sensor nodes sense the area and transmit the sensed data to the BS through multiple wireless communication hops. In addition to data collection, the BS performs highly complex management functions and controls the entire network. The importance of the BS in a WSN makes the BS a high-value target for an adversary that wants to disable the network. To launch a denial-of-service attack on the BS, an adversary intercepts the data transmissions sent to the BS and uses evidence theory as a technique of traffic analysis to find the BS. This paper proposes a technique to counter the attack and increase the BS's anonymity by creating cells and choosing HoneyCells from the created cells; the HoneyCells mimic the BS cell and attract the adversary's attention. Simulation results show that the proposed technique provides better BS anonymity.
{"title":"AAiBA: Attracting an Adversary for Increasing Base-Station Anonymity in Wireless Sensor Networks","authors":"S. Alsemairi","doi":"10.1109/ITNAC55475.2022.9998341","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998341","url":null,"abstract":"Wireless sensor networks (WSNs) have become one of the most interesting research areas in recent years. A WSN is mainly composed of a set of homogeneous sensor nodes and an in-situ base-station (BS) that are randomly deployed within a delimited area of interest. These sensor nodes sense the area and transmit the sensed data to the BS through multiple wireless communication hops. In addition to data collection, the BS performs highly complex management functions and controls the entire network. The importance of the BS in a WSN makes the BS a high-value target for an adversary that wants to disable the network. To launch a denial-of-service attack on the BS, an adversary intercepts the data transmissions sent to the BS and uses evidence theory as a technique of traffic analysis to find the BS. This paper proposes a technique to counter the attack and increase the BS's anonymity by creating cells and choosing HoneyCells from the created cells; the HoneyCells mimic the BS cell and attract the adversary's attention. Simulation results show that the proposed technique provides better BS anonymity.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127459480","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 : 2022-10-21DOI: 10.1109/ITNAC55475.2022.9998427
Arjun Parthasarathy, B. Krishnamachari
Edge inference has become more widespread, as its diverse applications range from retail to wearable technology. Clusters of networked resource-constrained edge devices are becoming common, yet no system exists to split a DNN across these clusters while maximizing the inference throughput of the system. We present an algorithm which partitions DNNs and distributes them across a set of edge devices with the goal of minimizing the bottleneck latency and therefore maximizing inference throughput. The system scales well to systems of different node memory capacities and numbers of nodes. We find that we can reduce the bottleneck latency by 10× over a random algorithm and 35% over a greedy joint partitioning-placement algorithm. Furthermore we find empirically that for the set of representative models we tested, the algorithm produces results within 9.2% of the optimal bottleneck latency.
{"title":"Partitioning and Placement of Deep Neural Networks on Distributed Edge Devices to Maximize Inference Throughput","authors":"Arjun Parthasarathy, B. Krishnamachari","doi":"10.1109/ITNAC55475.2022.9998427","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998427","url":null,"abstract":"Edge inference has become more widespread, as its diverse applications range from retail to wearable technology. Clusters of networked resource-constrained edge devices are becoming common, yet no system exists to split a DNN across these clusters while maximizing the inference throughput of the system. We present an algorithm which partitions DNNs and distributes them across a set of edge devices with the goal of minimizing the bottleneck latency and therefore maximizing inference throughput. The system scales well to systems of different node memory capacities and numbers of nodes. We find that we can reduce the bottleneck latency by 10× over a random algorithm and 35% over a greedy joint partitioning-placement algorithm. Furthermore we find empirically that for the set of representative models we tested, the algorithm produces results within 9.2% of the optimal bottleneck latency.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113998944","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 : 2022-10-06DOI: 10.1109/ITNAC55475.2022.9998371
Liam Daly Manocchio, S. Layeghy, Marius Portmann
Internet of Things (IoT) devices are progressively being utilised in a variety of edge applications to monitor and control home and industry infrastructure. Due to the limited compute and energy resources, active security protections are usually minimal in many IoT devices. This has created a critical security challenge that has attracted researchers' attention in the field of network security. Despite a large number of proposed Network Intrusion Detection Systems (NIDSs), there is limited research into practical IoT implementations, and to the best of our knowledge, no edge-based NIDS has been demonstrated to operate on common low-power chipsets found in the majority of IoT devices, such as the ESP8266. This research aims to address this gap by pushing the boundaries on low-power Machine Learning (ML) based NIDSs. We propose and develop an efficient and low-power ML-based NIDS, and demonstrate its applicability for IoT edge applications by running it on a typical smart light bulb. We also evaluate our system against other proposed edge-based NIDSs and show that our model has a higher detection performance, and is significantly faster and smaller, and therefore more applicable to a wider range of IoT edge devices.
{"title":"Network Intrusion Detection System in a Light Bulb","authors":"Liam Daly Manocchio, S. Layeghy, Marius Portmann","doi":"10.1109/ITNAC55475.2022.9998371","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998371","url":null,"abstract":"Internet of Things (IoT) devices are progressively being utilised in a variety of edge applications to monitor and control home and industry infrastructure. Due to the limited compute and energy resources, active security protections are usually minimal in many IoT devices. This has created a critical security challenge that has attracted researchers' attention in the field of network security. Despite a large number of proposed Network Intrusion Detection Systems (NIDSs), there is limited research into practical IoT implementations, and to the best of our knowledge, no edge-based NIDS has been demonstrated to operate on common low-power chipsets found in the majority of IoT devices, such as the ESP8266. This research aims to address this gap by pushing the boundaries on low-power Machine Learning (ML) based NIDSs. We propose and develop an efficient and low-power ML-based NIDS, and demonstrate its applicability for IoT edge applications by running it on a typical smart light bulb. We also evaluate our system against other proposed edge-based NIDSs and show that our model has a higher detection performance, and is significantly faster and smaller, and therefore more applicable to a wider range of IoT edge devices.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122561376","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：