Pub Date : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234963
Elif Dilek Salik, S. Coleri
Radio frequency energy harvesting is an alternative solution to power the next generation wireless networks. The vast majority of the existing works focus on continuous rate transmission model, although discrete rate model is more realistic for practical communication networks. We study the joint optimization of energy harvesting and information transmission times with the objective of minimizing the total schedule length of a multi-user, harvest-then-transmit, wireless powered communication network while following discrete Signal-to-Noise Ratio and rate transmission model. The users are required to transmit a minimum amount of data to the access point under a maximum transmit power limit. The formulated problem is mixed integer, non-linear and non-convex. First, we solve the case where the rate allocations are given. Then, we exploit given rate allocation problem’s optimality characteristics to achieve the global optimal solution for the original problem. We propose an exponential time optimal algorithm which exhibits practical superiority to the brute force algorithm, and two polynomial time heuristics, one of which prioritizes minimizing information transmission times, while the other focuses on improving energy harvesting time. Performances of the proposed algorithms are compared both to an algorithm which assigns continuous rates to the user, i.e., best lower bound, and to an algorithm which discretize the former continuous rate solution. Simulation results show that the proposed heuristic algorithms perform close to the optimal solution, and the proposed algorithms outperform the algorithm that discretize the continuous rate solution up to 56.9% for smaller access point power and 46.7% for higher number of users. This proves the importance of optimizing the total schedule length for discrete rate model as the users will be forced to transmit at discrete rates practically.
{"title":"Minimum Length Scheduling for Wireless Powered Communication Networks with Discrete Rates","authors":"Elif Dilek Salik, S. Coleri","doi":"10.1109/BlackSeaCom48709.2020.9234963","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234963","url":null,"abstract":"Radio frequency energy harvesting is an alternative solution to power the next generation wireless networks. The vast majority of the existing works focus on continuous rate transmission model, although discrete rate model is more realistic for practical communication networks. We study the joint optimization of energy harvesting and information transmission times with the objective of minimizing the total schedule length of a multi-user, harvest-then-transmit, wireless powered communication network while following discrete Signal-to-Noise Ratio and rate transmission model. The users are required to transmit a minimum amount of data to the access point under a maximum transmit power limit. The formulated problem is mixed integer, non-linear and non-convex. First, we solve the case where the rate allocations are given. Then, we exploit given rate allocation problem’s optimality characteristics to achieve the global optimal solution for the original problem. We propose an exponential time optimal algorithm which exhibits practical superiority to the brute force algorithm, and two polynomial time heuristics, one of which prioritizes minimizing information transmission times, while the other focuses on improving energy harvesting time. Performances of the proposed algorithms are compared both to an algorithm which assigns continuous rates to the user, i.e., best lower bound, and to an algorithm which discretize the former continuous rate solution. Simulation results show that the proposed heuristic algorithms perform close to the optimal solution, and the proposed algorithms outperform the algorithm that discretize the continuous rate solution up to 56.9% for smaller access point power and 46.7% for higher number of users. This proves the importance of optimizing the total schedule length for discrete rate model as the users will be forced to transmit at discrete rates practically.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130568314","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9235025
Anastasios K. Papazafeiropoulos, P. Kourtessis, M. Renzo, S. Chatzinotas, J. Senior
Despite that ongoing and future networks become denser and increasingly irregular, prior works in the area of cell-free (CF) massive multiple-input-multiple-output (mMIMO) systems relied on the strong assumption of uniformly distributed access points (APs). Actually, this randomness was accounted for only during the simulation and not in the analysis. Consequently, the direction of this paper is towards the application and investigation of a more realistic model for the spatial randomness of the APs in terms of a Poisson point process (PPP). Specifically, we derive the downlink coverage probability (CP) of CF mMIMO systems by means of stochastic geometry and deterministic equivalent tools. Notably, it is the only work having derived the CP for CF mMIMO systems. Among the results, we highlight the outperformance of CF mMIMO systems against small cells (SCs), which increases with the density of the APs due to channel hardening, favorable propagation, and interference suppression. Moreover, we observe the saturation of the CP at high AP density.
{"title":"Coverage Probability of Cell-Free Massive MIMO Systems","authors":"Anastasios K. Papazafeiropoulos, P. Kourtessis, M. Renzo, S. Chatzinotas, J. Senior","doi":"10.1109/BlackSeaCom48709.2020.9235025","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9235025","url":null,"abstract":"Despite that ongoing and future networks become denser and increasingly irregular, prior works in the area of cell-free (CF) massive multiple-input-multiple-output (mMIMO) systems relied on the strong assumption of uniformly distributed access points (APs). Actually, this randomness was accounted for only during the simulation and not in the analysis. Consequently, the direction of this paper is towards the application and investigation of a more realistic model for the spatial randomness of the APs in terms of a Poisson point process (PPP). Specifically, we derive the downlink coverage probability (CP) of CF mMIMO systems by means of stochastic geometry and deterministic equivalent tools. Notably, it is the only work having derived the CP for CF mMIMO systems. Among the results, we highlight the outperformance of CF mMIMO systems against small cells (SCs), which increases with the density of the APs due to channel hardening, favorable propagation, and interference suppression. Moreover, we observe the saturation of the CP at high AP density.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122533014","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9235011
B. Rouzbehani, V. Marbukh, K. Sayrafian-Pour
A virtualization platform is responsible for allocation and aggregation of radio resources from different access technologies as well as the distribution of the total capacity among Virtual Network Operators (VNOs). The Radio Resource Management (RRM) employed by each VNO should comply with the requirements specified in the Service Level Agreements (SLAs) of each user. A joint admission control and resource management scheme based on proportionally fair rate allocation among different users was proposed in our previous publication. Although, all SLAs are satisfied in that scheme, users with vastly different QoS requirements might not necessary be treated fairly in terms of the allocated rates. This is especially the case when the available capacities of the VNOs cannot support the maximum requested rates for all such users. This paper attempts to overcome this weakness by replacing the proportional fairness strategy with a more general concept of utility-proportional fairness. The proposed approach is evaluated by simulations under increasing congestion scenarios and the results show improved fairness in the allocated rates.
{"title":"Utility Proportional Resource Allocation for Users with Diverse SLAs in Virtualized Radio Access Networks","authors":"B. Rouzbehani, V. Marbukh, K. Sayrafian-Pour","doi":"10.1109/BlackSeaCom48709.2020.9235011","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9235011","url":null,"abstract":"A virtualization platform is responsible for allocation and aggregation of radio resources from different access technologies as well as the distribution of the total capacity among Virtual Network Operators (VNOs). The Radio Resource Management (RRM) employed by each VNO should comply with the requirements specified in the Service Level Agreements (SLAs) of each user. A joint admission control and resource management scheme based on proportionally fair rate allocation among different users was proposed in our previous publication. Although, all SLAs are satisfied in that scheme, users with vastly different QoS requirements might not necessary be treated fairly in terms of the allocated rates. This is especially the case when the available capacities of the VNOs cannot support the maximum requested rates for all such users. This paper attempts to overcome this weakness by replacing the proportional fairness strategy with a more general concept of utility-proportional fairness. The proposed approach is evaluated by simulations under increasing congestion scenarios and the results show improved fairness in the allocated rates.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132014947","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9235006
Aysun Aslan, Gulce Bal, C. Toker
With the era of the fifth generation (5G) networks, supporting all mobile service users who have different Quality of Service (QoS) requirements becomes the main challenge. To manage and satisfy the heterogeneous requirements, network slicing concept can be a solution over a common physical infrastructure. Splitting the network into slices which have different properties (e.g., bandwidth requirements, delay tolerance, user density, etc.) allows to schedule and optimize the requests under the constraint of limited resources. The network has to decide to accept or reject the requests, and scale up/down the slices by considering the user density in accepted requests, and then, schedule the accepted requests to serve them in an order. In this paper, it is verified that slicing the network and scaling up/down the slices by using deep reinforcement learning (DRL) algorithms with consideration of user density, improve the speed of satisfaction of users with respect to the classical baseline scheduling algorithms.
{"title":"Dynamic Resource Management in Next Generation Networks with Dense User Traffic","authors":"Aysun Aslan, Gulce Bal, C. Toker","doi":"10.1109/BlackSeaCom48709.2020.9235006","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9235006","url":null,"abstract":"With the era of the fifth generation (5G) networks, supporting all mobile service users who have different Quality of Service (QoS) requirements becomes the main challenge. To manage and satisfy the heterogeneous requirements, network slicing concept can be a solution over a common physical infrastructure. Splitting the network into slices which have different properties (e.g., bandwidth requirements, delay tolerance, user density, etc.) allows to schedule and optimize the requests under the constraint of limited resources. The network has to decide to accept or reject the requests, and scale up/down the slices by considering the user density in accepted requests, and then, schedule the accepted requests to serve them in an order. In this paper, it is verified that slicing the network and scaling up/down the slices by using deep reinforcement learning (DRL) algorithms with consideration of user density, improve the speed of satisfaction of users with respect to the classical baseline scheduling algorithms.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122847411","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234998
I. Strelkovskaya, I. Solovskaya, A. Makoganiuk, T. Rodionova
The task of predicting self-similar traffic of IoT network objects with a significant number of pulsations and the property of long-term dependence is considered, which makes it difficult to predict in practice. Using the methods of wavelet- and spline-extrapolation based on Haar-wavelet, quadratic and B-spline function, the results of prediction of multimedia traffic are obtained. We compare the results of traffic prediction based on the Haar-wavelet and the quadratic and B-spline function using wavelet- and spline-extrapolation. This will allow the choice of one or another extrapolation method to improve the accuracy of the prediction, while ensuring scalability and the ability to use it for various IoT applications to prevent network overloads.
{"title":"Multimedia Traffic Prediction Based on Wavelet-and Spline-extrapolation","authors":"I. Strelkovskaya, I. Solovskaya, A. Makoganiuk, T. Rodionova","doi":"10.1109/BlackSeaCom48709.2020.9234998","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234998","url":null,"abstract":"The task of predicting self-similar traffic of IoT network objects with a significant number of pulsations and the property of long-term dependence is considered, which makes it difficult to predict in practice. Using the methods of wavelet- and spline-extrapolation based on Haar-wavelet, quadratic and B-spline function, the results of prediction of multimedia traffic are obtained. We compare the results of traffic prediction based on the Haar-wavelet and the quadratic and B-spline function using wavelet- and spline-extrapolation. This will allow the choice of one or another extrapolation method to improve the accuracy of the prediction, while ensuring scalability and the ability to use it for various IoT applications to prevent network overloads.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124955607","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234961
I. Altin, Emre Bilican, O. Çelikel, Yağmur Coşkun
Resource utilization is of high importance in Nar-rowband Internet of Things (NB-IoT) due to the large number of users. In this paper, a novel link adaptation method for the downlink control channel (NPDCCH) is proposed. We show that the NPDCCH resource utilization is improved significantly by the proposed link adaptation method compared to the standard system with no link adaptation, while satisfying the required NPDCCH decoding rates in the specifications. The proposed algorithm has very low complexity, and uses the NPDCCH decoding success ratio of the uplink channel which is already calculated in the system.
{"title":"A Novel Link Adaptation Method for NB-IoT Downlink Control Channel","authors":"I. Altin, Emre Bilican, O. Çelikel, Yağmur Coşkun","doi":"10.1109/BlackSeaCom48709.2020.9234961","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234961","url":null,"abstract":"Resource utilization is of high importance in Nar-rowband Internet of Things (NB-IoT) due to the large number of users. In this paper, a novel link adaptation method for the downlink control channel (NPDCCH) is proposed. We show that the NPDCCH resource utilization is improved significantly by the proposed link adaptation method compared to the standard system with no link adaptation, while satisfying the required NPDCCH decoding rates in the specifications. The proposed algorithm has very low complexity, and uses the NPDCCH decoding success ratio of the uplink channel which is already calculated in the system.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132318065","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234967
S. Lembo, H. Kokkoniemi-Tarkkanen, S. Horsmanheimo
We study the feasibility of developing a Communication Supervision Function for a 4G LTE wireless communications network system, to allow a vertical to monitor from its domain the Quality of Service (QoS) of the communication traversing the wireless domain. Communication supervision is performed by detecting traffic anomalies of a reference, healthy, transmission of packets uniformly spaced at intervals with ms resolution, and transmitted in uplink direction. Traffic at the base station is monitored with a LTE Medium Access Control (MAC) layer monitoring tool that aggregates traffic at intervals with seconds resolution. Measurements are performed in an operating LTE network. We use a deep learning method implementing a Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN), to determine if the traffic pattern is the healthy one, or it is anomalous, with missing packets and jitter. We identify key metrics in the monitoring data, that are selected as features in the RNN, which enable the detection of fine time resolution traffic anomalies hidden in the aggregated and coarse measurements reported by the monitoring tool. We find that applying the proposed approach, a vertical is able to determine whether the communication over the wireless network is healthy or anomalous. Finally, we discuss on the use of the proposed monitoring approach in 4G networks, and learning possibilities for 5G standardization in terms of monitoring metrics, features, monitoring resolution, service concepts, etc.
{"title":"Communication supervision function for verticals in 4G networks and beyond: Traffic anomaly detection from aggregated LTE MAC layer reports using a LSTM-RNN","authors":"S. Lembo, H. Kokkoniemi-Tarkkanen, S. Horsmanheimo","doi":"10.1109/BlackSeaCom48709.2020.9234967","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234967","url":null,"abstract":"We study the feasibility of developing a Communication Supervision Function for a 4G LTE wireless communications network system, to allow a vertical to monitor from its domain the Quality of Service (QoS) of the communication traversing the wireless domain. Communication supervision is performed by detecting traffic anomalies of a reference, healthy, transmission of packets uniformly spaced at intervals with ms resolution, and transmitted in uplink direction. Traffic at the base station is monitored with a LTE Medium Access Control (MAC) layer monitoring tool that aggregates traffic at intervals with seconds resolution. Measurements are performed in an operating LTE network. We use a deep learning method implementing a Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN), to determine if the traffic pattern is the healthy one, or it is anomalous, with missing packets and jitter. We identify key metrics in the monitoring data, that are selected as features in the RNN, which enable the detection of fine time resolution traffic anomalies hidden in the aggregated and coarse measurements reported by the monitoring tool. We find that applying the proposed approach, a vertical is able to determine whether the communication over the wireless network is healthy or anomalous. Finally, we discuss on the use of the proposed monitoring approach in 4G networks, and learning possibilities for 5G standardization in terms of monitoring metrics, features, monitoring resolution, service concepts, etc.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115123080","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234959
Noor Ali Al-Athba Al-Marri, Bekir Sait Ciftler, M. Abdallah
Internet of things (IoT) devices are prone to attacks due to the limitation of their privacy and security components. These attacks vary from exploiting backdoors to disrupting the communication network of the devices. Intrusion Detection Systems (IDS) play an essential role in ensuring information privacy and security of IoT devices against these attacks. Recently, deep learning-based IDS techniques are becoming more prominent due to their high classification accuracy. However, conventional deep learning techniques jeopardize user privacy due to the transfer of user data to a centralized server. Federated learning (FL) is a popular privacy-preserving decentralized learning method. FL enables training models locally at the edge devices and transferring local models to a centralized server instead of transferring sensitive data. Nevertheless, FL can suffer from reverse engineering ML attacks that can learn information about the user's data from model. To overcome the problem of reverse engineering, mimic learning is another way to preserve the privacy of ML-based IDS. In mimic learning, a student model is trained with the public dataset, which is labeled with the teacher model that is trained by sensitive user data. In this work, we propose a novel approach that combines the advantages of FL and mimic learning, namely federated mimic learning to create a distributed IDS while minimizing the risk of jeopardizing users' privacy, and benchmark its performance compared to other ML-based IDS techniques using NSL-KDD dataset. Our results show that we can achieve 98.11% detection accuracy with federated mimic learning.
{"title":"Federated Mimic Learning for Privacy Preserving Intrusion Detection","authors":"Noor Ali Al-Athba Al-Marri, Bekir Sait Ciftler, M. Abdallah","doi":"10.1109/BlackSeaCom48709.2020.9234959","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234959","url":null,"abstract":"Internet of things (IoT) devices are prone to attacks due to the limitation of their privacy and security components. These attacks vary from exploiting backdoors to disrupting the communication network of the devices. Intrusion Detection Systems (IDS) play an essential role in ensuring information privacy and security of IoT devices against these attacks. Recently, deep learning-based IDS techniques are becoming more prominent due to their high classification accuracy. However, conventional deep learning techniques jeopardize user privacy due to the transfer of user data to a centralized server. Federated learning (FL) is a popular privacy-preserving decentralized learning method. FL enables training models locally at the edge devices and transferring local models to a centralized server instead of transferring sensitive data. Nevertheless, FL can suffer from reverse engineering ML attacks that can learn information about the user's data from model. To overcome the problem of reverse engineering, mimic learning is another way to preserve the privacy of ML-based IDS. In mimic learning, a student model is trained with the public dataset, which is labeled with the teacher model that is trained by sensitive user data. In this work, we propose a novel approach that combines the advantages of FL and mimic learning, namely federated mimic learning to create a distributed IDS while minimizing the risk of jeopardizing users' privacy, and benchmark its performance compared to other ML-based IDS techniques using NSL-KDD dataset. Our results show that we can achieve 98.11% detection accuracy with federated mimic learning.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132131678","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9234962
Jamale Benitez Porch, C. Foh, H. Farooq, A. Imran
The capability for a network to self heal itself is a promising feature for future cellular networks. An essential function to achieve self healing is the ability to determine when a network is operating outside of normal state, and perhaps identify potential causes. This paper focuses on applying the supervised machine learning approach to detect fault symptoms and identify the cause. Our method utilizes referenced signal received power (RSRP) reported by users over a certain period of time to detect operational anomaly in a base station. We notice that certain faults at a base station create noticeable change in the RSRP readings and recognizable electromagnetic radiation pattern around the base station. To achieve fault analysis, we develop a framework that differentiates normal and abnormal operations under changing environment to avoid unnecessary fault alarms. Once abnormal operation is detected, the framework uses a supervised machine learning system to classify the detected fault. We develop convolutional neural network and random forest to test the fault classification. We show that both machine learning systems offer high accuracy.
{"title":"Machine Learning Approach for Automatic Fault Detection and Diagnosis in Cellular Networks","authors":"Jamale Benitez Porch, C. Foh, H. Farooq, A. Imran","doi":"10.1109/BlackSeaCom48709.2020.9234962","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9234962","url":null,"abstract":"The capability for a network to self heal itself is a promising feature for future cellular networks. An essential function to achieve self healing is the ability to determine when a network is operating outside of normal state, and perhaps identify potential causes. This paper focuses on applying the supervised machine learning approach to detect fault symptoms and identify the cause. Our method utilizes referenced signal received power (RSRP) reported by users over a certain period of time to detect operational anomaly in a base station. We notice that certain faults at a base station create noticeable change in the RSRP readings and recognizable electromagnetic radiation pattern around the base station. To achieve fault analysis, we develop a framework that differentiates normal and abnormal operations under changing environment to avoid unnecessary fault alarms. Once abnormal operation is detected, the framework uses a supervised machine learning system to classify the detected fault. We develop convolutional neural network and random forest to test the fault classification. We show that both machine learning systems offer high accuracy.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124847819","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 : 2020-05-26DOI: 10.1109/BlackSeaCom48709.2020.9235026
Uygar Demir, C. Toker, Özgür Ekici
Unmanned aerial vehicles (UAV) take place in the communication field more and more. Since the energy efficiency will be one of the most important issues in regard to smart city applications, energy-efficient deployment of the UAVs becomes a critical topic. Besides, V2X communication stands out in smart city applications and has its own unique problems such as latency. In this paper, we have investigated the energy-efficient deployment problem of UAV as flying roadside unit (RSU) with considering latency of vehicular users (VUs) and backhaul link capacity constraints while making power control of VUs as well. First, we proposed a junction scenario that a UAV is integrated as RSU to provide V2I links in a region while connecting the core network with a backhaul link. Then, when the number of vehicular users is given, we propose a communication problem that aims to minimize the total power consumption including both hovering and communicating powers. In our scenario, the probability of that the latency of the vehicular users is greater than a given value is kept below a certain violation probability. In the numerical results, it is stated that communication packet size is an essential parameter for the latency constraint in the network configurations. It is also observed that as the delay constraint tightens and the average packet size increases, the sum of the data rates of VUs converges to the backhaul link capacity. At the end of the paper, results for the proposed communication problem are provided.
{"title":"Energy-Efficient Deployment of UAV in V2X Network Considering Latency and Backhaul Issues","authors":"Uygar Demir, C. Toker, Özgür Ekici","doi":"10.1109/BlackSeaCom48709.2020.9235026","DOIUrl":"https://doi.org/10.1109/BlackSeaCom48709.2020.9235026","url":null,"abstract":"Unmanned aerial vehicles (UAV) take place in the communication field more and more. Since the energy efficiency will be one of the most important issues in regard to smart city applications, energy-efficient deployment of the UAVs becomes a critical topic. Besides, V2X communication stands out in smart city applications and has its own unique problems such as latency. In this paper, we have investigated the energy-efficient deployment problem of UAV as flying roadside unit (RSU) with considering latency of vehicular users (VUs) and backhaul link capacity constraints while making power control of VUs as well. First, we proposed a junction scenario that a UAV is integrated as RSU to provide V2I links in a region while connecting the core network with a backhaul link. Then, when the number of vehicular users is given, we propose a communication problem that aims to minimize the total power consumption including both hovering and communicating powers. In our scenario, the probability of that the latency of the vehicular users is greater than a given value is kept below a certain violation probability. In the numerical results, it is stated that communication packet size is an essential parameter for the latency constraint in the network configurations. It is also observed that as the delay constraint tightens and the average packet size increases, the sum of the data rates of VUs converges to the backhaul link capacity. At the end of the paper, results for the proposed communication problem are provided.","PeriodicalId":186939,"journal":{"name":"2020 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127129299","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：