Aerial base stations (ABSs), i.e., unmanned aerial vehicle-mounted base stations, have emerged as an essential technology to expand the coverage and capacity in next-generation wireless networks. Determining the optimal ABS placement that maximizes the communication quality of users is a critical but challenging problem due to complex air-to-ground (A2G) channel characteristics and inter-cell interference. Although various ABS deployment methods have been proposed, existing methods do not consider the actual line-of-sight (LoS) and non-LoS (NLoS) conditions of A2G channels properly, assuming a spatially independent probabilistic LoS model to simplify the problem and analysis. In this study, we propose a distributed ABS deployment method considering the actual LoS/NLoS conditions. We model the ABS deployment space as a 3D grid space in which the LoS/NLoS condition between each grid point is given and formulate the ABS deployment problem as the maximization problem of the expected number of covered users. By applying a potential game to the problem, we develop a distributed ABS deployment algorithm that probabilistically converges to a Nash equilibrium that maximizes the objective function. Furthermore, we demonstrate through simulation that the proposed method can improve the actual communication quality of users.

Handover (HO) management is one of the most crucial tasks in dense cellular networks with mobile users. A problem in the HO management is to deal with increasing HOs due to network densification in the 5G evolution and various HO skipping techniques have so far been studied in the literature to suppress excessive HOs. In this paper, we propose yet another HO skipping scheme, called periodic HO skipping. The proposed scheme prohibits the HOs of a mobile user equipment (UE) for a certain period of time, referred to as skipping period, thereby enabling flexible operation of the HO skipping by adjusting the length of the skipping period. We investigate the performance of the proposed scheme on the basis of stochastic geometry. Specifically, we derive analytical expressions of two performance metrics—the HO rate and the expected downlink data rate—when a UE adopts the periodic HO skipping. Numerical results based on the analysis demonstrate that the periodic HO skipping scenario can outperform the scenario without any HO skipping in terms of a certain utility metric representing the trade-off between the HO rate and the expected downlink data rate, in particular when the UE moves fast. Furthermore, we numerically show that there can exist an optimal length of the skipping period, which locally maximizes the utility metric, and approximately provide the optimal skipping period in a simple form. Numerical comparison with some other HO skipping techniques is also conducted.

Due to the recent growth of network services of telecommunication carriers, their communication networks have become increasingly large and complex, and their network operations have also become complicated. For this problem, fault diagnosis and anomaly detection using log data of network devices (e.g., router syslog) have been extensively studied. However, there has been little research on automating the fault diagnosis of failures that are reported by users and whose causes do not appear in logs. In this paper, we propose a deep reinforcement learning (DRL)-based command control system for automating fault diagnosis of communication services. The proposed system first runs a sequence of device commands (e.g., show interfaces) for fault diagnosis on network devices, and estimates the fault-type based on the output of the commands using a supervised classifier. The sequence of device commands executed on network devices is optimized by DRL to identify the fault type with the least number of device commands. We evaluate the proposed system using real data obtained from a commercial service network and demonstrate its accuracy and effectiveness.

This paper analyzes the packet reception ratio (PRR) of direct communications between unmanned aerial vehicles (UAVs), i.e., UAV-to-UAV (U2U), by using stochastic geometry tools, focusing on UAV heights. In U2U, a receiving UAV (called a UAV-Rx) experiences better line-of-sight (LoS) conditions of its communication and interference links with other UAVs distributed in a three-dimensional space at its higher height. The balance of LoS conditions of these links decides the PRR of U2U. To analyze the characteristics, we derived a closed-form expression of the PRR of U2U. Our analysis highlighted that the PRR of U2U decreased and then increased as the height of a UAV-Rx increased at the distance of the communication link of 100 m in the dense urban model, and the UAV-Rx experienced the bottom PRR at its height of 32.5 m, depending on the building heights.

Network operators in telecom carriers perform failure diagnosis by executing various commands (e.g., show interfaces) on network devices through a command line interface (CLI). The outputs of these CLI commands, which we call command outputs, contain more detailed information than typical one-line system logs but have complex characteristics; thus, existing parsers for system logs are not applicable. In this study, we propose COPA, a parsing method for command outputs for automating time-consuming and labor-intensive failure diagnosis.

Spatial correlations that appear in mobile wireless networks, such as the correlations of node locations and shadowing effects, significantly affect the characteristics of interference, which may degrade the performance of various wireless network systems. In this paper, we theoretically analyze the statistical and temporal characteristics of interference in a network where the node locations and shadowing are spatially correlated. We model the correlation of the node locations by two types ofnon-Poissonpoint processes: determinantal point processes (DPPs) for modelingrepulsivenessand doubly Poisson cluster processes (DPCPs) for modelingattractiveness. Furthermore, we consider Gudmundson's model for the spatial correlation of shadowing. Using this model and assuming an i.i.d. mobility of nodes, we analyze the variance along with the spatial and temporal correlations of interference. Since the exact expressions are in non-analytical forms, we derive their simple closed-form asymptotic formulas when the variance of the shadowing is large. The results show a readable relationship between the characteristics of interference and various system parameters. This relationship can be used for realistic modeling and better understanding of various wireless network systems under spatially correlated shadowing. Moreover, we discuss various numerical examples and demonstrate that the obtained asymptotic expressions achieve tight approximation.

Owing to the critical role of the domain name system (DNS), its query log data are utilized for various network monitoring purposes. With the diversification of network services, these data have become increasingly complex, making mining useful information challenging. DNS query log data can be considered as the superposition of two types of communication patterns: groups of domains accessed simultaneously (e.g., ad servers and content delivery network (CDN) servers) and time-series access patterns based on user behavior characteristics (e.g., access trends during the night). However, previous studies have not focused on extracting both access patterns hidden in the data. This study proposes a method that extracts both patterns of accessed domains and temporal access patterns as user communication behaviors from DNS query log data and predicts future accesses based on these patterns. The proposed method first aggregates similar fully qualified domain names (FQDNs) associated with the same service. We then present temporal regularized nonnegative tensor factorization (TR-NTF) that extracts both access patterns from a third-order tensor expressing DNS query log data and enables prediction. We evaluate the proposed method using synthetic and actual data and demonstrate that it successfully extracts hidden communication patterns and achieves sufficient prediction accuracy.

This paper analyzes the spatial performance of the autonomous sidelink cellular-vehicle-to-everything (called ASC-V2X) with the sensing-based semi-persistent scheduling (SB-SPS) with the power-domain non-orthogonal multiple access (NOMA), called SPS-NOMA. In SPS-NOMA, multiple users (e.g., cars or pedestrians) simultaneously broadcast their packets, i.e., a packet collision, and each receiver (i.e., each of their surrounding users) aims to decode the packets by using the successive interference cancellation (SIC). However, some re-ceivers may undergo collision errors at collisions even in SPS-NOMA due to spatial location relationships between the receivers and simultaneously transmitting users, called collision users. To reveal such spatial performance characteristics, this paper derives closed-form expressions of the packet reception ratio (PRR) at the receiver deployed on each coordinate point in a spatial area. Our analysis showed the spatial distributions of the PRR in an area, and SPS-NOMA achieved the required PRR in a 50% more wide area than the existing ASC-V2X without SIC. Additionally, our analysis provided the limitations of SPS-NOMA, and specifically, receivers experienced 65 % lower PRRs than the peak around the bisector created by collision users.

An unmanned aerial vehicle (UAV)-mounted aerial base station (ABS) is considered as a promising technology to enhance the capacity and coverage in future mobile networks. However, determining the optimal placement of ABSs that maximizes the overall communication quality of users is a challenging problem because of complicated air-to-ground channel characteristics and inter-cell interference. Moreover, ABSs are faced with the problem of limited available power resources. In this study, we consider an ABS network in which ABSs perform radio frequency (RF) energy harvesting from terrestrial base stations and propose a novel distributed ABS deployment method that optimizes the performance of the energy harvesting and downlink transmission jointly. In our method, each ABS updates its position by using local information only and communicating with its neighboring ABSs; thus, the overhead of information gathering is smaller than that in the centralized method. Simulation results demonstrate that our method improves both the energy harvesting and communication quality of users.

Cooperative vehicle safety (CVS) systems have been receiving significant attention as key enablers of important intelligent transportation system (ITS) applications, such as cooperative collision warning, emergency braking, and auto driving. In CVS systems, vehicles periodically broadcast short packets that include various types of vehicular information, e.g., position and speed. In this paper, we propose an optimization method for the broadcast rate in vehicle-to-vehicle (V2V) broadcast communications at an intersection based on theoretical analysis. We consider a model in which the locations of vehicles are modeled separately asqueuing, andrunningsegments and derive key performance metrics of V2V broadcast communications through a stochastic geometry approach. We developclosed-formapproximate formulas for the theoretical expressions because they are mathematically intractable. Based on approximate analysis, we optimize the broadcast rate such that the interference at an intersection is mitigated and the overall performance of V2V communications is maximized. Because of the closed-form approximation, the optimal rate can be used as a guideline for areal-timecontrol-method, which cannot be achieved through time-consuming simulations. We evaluate our method through numerical examples and demonstrate its effectiveness.

As video traffic volume increases, video streaming providers are struggling to improve the quality of experience (QoE). On the other hand, video viewers often prefer a lower traffic volume over a QoE that is too high since they contract for data-capped or pay-per-use communication plans. Thus, traffic volume should be reduced as much as possible while achieving the required QoE, which is the minimum QoE that will satisfy users. However, the required QoE depends on the context (e.g., the type of content and the preference of the user), and it is unrealistic and costly for users to set the required quality separately for each possible context. In this paper, we propose a context-aware adaptive bitrate streaming system that reduces the traffic volume while achieving the required QoE. Instead of requiring the required QoE to be configured by users, the proposed system uses the viewing time as implicit feedback on the QoE. By using this feedback, the proposed system automatically controls the QoE with a two-stage approach: it estimates the required QoE and calculates the bitrate to reduce the traffic volume while maintaining a QoE above the required QoE. To determine the required QoE based on few views, the proposed system searches for the required QoE in the mean opinion score space and uses Bayesian optimization. The results of trace-based simulations show that the proposed system can control the QoE close to the context-dependent required QoE based on fewer views than baseline algorithms.

Correlation of interference affects spatio-temporal aspects of various wireless mobile systems, such as retransmission, multiple antennas and cooperative relaying. In this paper, we study the spatial and temporal correlation of interference in mobile ad-hoc networks under a correlated shadowing environment. By modeling the node locations as a Poisson point process with an i.i.d. mobility model and considering Gudmundson (1991)'s spatially correlated shadowing model, we theoretically analyze the relationship between the correlation distance of log-normal shadowing and the spatial and temporal correlation coefficients of interference. Since the exact expressions of the correlation coefficients are intractable, we obtain their simple asymptotic expressions as the variance of log-normal shadowing increases. We found in our numerical examples that the asymptotic expansions can be used as tight approximate formulas and useful for modeling general wireless systems under spatially correlated shadowing.

An aerial base station (ABS), i.e., unmanned aerial vehicle-mounted base station, has a significant potential to effectively boost the coverage of next-generation wireless networks, having capability of adaptively serving traffic increase in temporary events (i.e., hotspots). However, designing an efficient 3D deployment of ABSs is a considerably complicated problem due to its high degree of freedom and inter-cell interference among ABSs. In this paper, we propose a novel distributed 3D ABS deployment method for providing on-demand downlink communications. To consider the spatial and temporal variations of user locations due to user activities, we model them by an inhomogeneous point process. By analyzing the performance metrics under this model and applying a distributed push-sum, we develop an ABS deployment algorithm with theoretical convergence guarantee that solves the maximization problems of the overall communication quality in a distributed and iterative manner. In our method, each ABS updates its position based on its local information by communicating with its neighboring ABSs. Furthermore, we propose an estimation method of the overall user density from partial observation of ground sensors. Simulation results demonstrate that our method can efficiently improve the overall communication quality and can be applied to a dynamic network.

Deployment of unmanned aerial vehicles (UAVs) performing as flying aerial base stations (BSs) has a great potential of adaptively serving ground users during temporary events, such as major disasters and massive events. However, planning an efficient, dynamic, and 3D deployment of UAVs in adaptation to dynamically and spatially varying ground users is a highly complicated problem due to the complexity in air-to-ground channels and interference among UAVs. In this paper, we propose a novel distributed 3D deployment method for UAVBSs in a downlink network for on-demand coverage. Our method consists mainly of the following two parts: sensing-aided crowd density estimation and distributed push-sum algorithm. The first part estimates the ground user density from its observation through on-ground sensors, thereby allowing us to avoid the computationally intensive process of obtaining the positions of all the ground users. On the basis of the estimated user density, in the second part, each UAV dynamically updates its 3D position in collaboration with its neighboring UAVs for maximizing the total coverage. We prove the convergence of our distributed algorithm by employing a distributed push-sum algorithm framework. Simulation results demonstrate that our method can improve the overall coverage with a limited number of ground sensors. We also demonstrate that our method can be applied to a dynamic network in which the density of ground users varies temporally.

When a failure occurs in a network, network operators need to recognize service impact, since service impact is essential information for handling failures. In this paper, we propose Deep learning based Service Impact Prediction (DeepSIP), a system to predict the time to recovery from the failure and the loss of traffic volume due to the failure in a network element using a temporal multimodal convolutional neural network (CNN). Since the time to recovery is useful information for a service level agreement (SLA) and the loss of traffic volume is directly related to the severity of the failures, we regard these as the service impact. The service impact is challenging to predict, since a network element does not explicitly contain any information about the service impact. Thus, we aim to predict the service impact from syslog messages and traffic volume by extracting hidden information about failures. To extract useful features for prediction from syslog messages and traffic volume which are multimodal and strongly correlated, and have temporal dependencies, we use temporal multimodal CNN. We experimentally evaluated DeepSIP and DeepSIP reduced prediction error by approximately 50% in comparison with other NN-based methods with a synthetic dataset.

This paper proposes a theoretical framework for estimating a target-object shape, the location of which is not given. The framework uses mobile distance sensors and speed meters typically mounted on vehicles, the locations of which are also unknown. Each sensor continuously measures the distance from it to the target object. The proposed framework does not require any positioning function, anchor-location information, or additional mechanisms to obtain side information such as angle of arrival of signal. Under the assumption of a convex polygon target object, each edge length and vertex angle and their combinations are estimated and finally the shape of the target object is estimated. To the best of our knowledge, this is the first result in which a target-object shape was estimated using the data of mobile distance sensors without using their locations.

Bitrate-selection algorithms are key to improving the quality of experience (QoE) of adaptive video streaming. Although current bitrate selection algorithms maximize the QoE, video consumers are concerned with QoE and traffic-volume usage due to the pay-per-use or data-capped plans. To balance between the QoE and traffic volume, some commercial video-streaming services enable users to set the upper limit of the selectable bitrate. However, it is difficult for users to set an appropriate limit to obtain sufficient QoE. We propose BANQUET, a novel bitrate-selection algorithm that enables users to control intuitively the balance between the QoE and traffic volume. Assuming a user-set target QoE as a balancing parameter, BANQUET selects the bitrate that minimizes the traffic volume while maintaining the estimated mean opinion score (MOS) above the target QoE. BANQUET calculates the appropriate bitrate based on estimations of the throughput and butter transition. A trace-based simulation shows that BANQUET reduces the traffic volume by up to 47.0% compared to a baseline while maintaining the same average estimated MOS.

Vehicle-to-vehicle (V2V) communication is a key technology for future intelligent transportations systems (ITSs). To support existing dedicated-short-range- protocols (DSRC), cellular-assisted V2V communications have recently been pro- posed, in which cellular base stations (BSs), such as E-UTRAN and eNodeB, relay the transmission from a vehicle to another. In this paper, we theoretically analyze the performance of such cellular-relay V2V communications, in which a vehicle first transmits a packet to its nearest BS in uplink, and then the BS forwards the packet to a destination vehicle in downlink. By modeling the road segments with a Poisson line process and the positions of vehicles with a Poisson point process on the roads, we derive the theoretical expression for the overall success probability of the relay transmission. Based on our analytical results, we reveal the relationship between the performances of the relay and direct V2V communications.

In this paper, we study the temporal correlation of interference in mobile ad-hoc networks under a correlated shadowing environment. By modeling the node locations as a 1-D Poisson point process with an i.i.d. mobility model and considering spatially correlated shadowing that depends on the distance between nodes, we derive a simple asymptotic expression of the temporal correlation coefficient of interference as the variance of log-normal shadowing increases. This shows a readable relationship between the correlation distance of lognormal shadowing and the temporal correlation of interference and thus can be useful for modeling general wireless systems with spatially correlated shadowing.

In this paper, we analyze the performance of vehicle-to-infrastructure (V2I) communications on a highway, in which the transmission distance between a road side unit (RSU) and a vehicle rapidly changes due to movement of vehicles. By theoretically analyzing the interference received at an RSU, we derive a closedform expression of a desired performance metric of V2I communications. Furthermore, by considering the trade-off between the interference at an RSU and the transmission range of a running vehicle, we obtain a closed-form optimal transmission-range for V2I communications. We evaluate our analysis results by conducting numerical simulations and show the effectiveness of the optimal transmissionrange.

Interference problems caused by congestion of vehicles at intersections or on highways may significantly affect vehicle-to-vehicle (V2V) communications, especially for active-safety assistance systems due to the importance of emergency information. In this paper, we propose a theoretical interference model of V2V communications at an intersection that uses transmission power control method. To evaluate and address the interference problem at an intersection, we derived an analytical expression of the outage probability of a typical vehicle at an intersection and provide guidelines for an optimal power control method, which cannot be obtained through simulations. We model the location of vehicles in queueing segments and running segments separately and analyze their interference based on a stochastic geometry approach. In our model, a simple power control method is used: the transmission power of each vehicle is determined by the status of the vehicle, i.e., stopping or running. By changing the transmission power of vehicles in queueing segments, we can mitigate the interference received at vehicles running closer to an intersection. By using the theoretical results, we obtain an optimal power control method, which can balance the trade-off between the outage probabilities of vehicles in queueing segments and running segments. We validated our analytical results and the effect of the power control on V2V communications through numerical experiments.

In current large scale networks, troubleshooting has become more complicated task due to the diversification in the causes of network failures. The increase in the operational costs has become a serious problem. Thus, manualization of the troubleshooting process also becomes important task though it is time-consuming. We propose a method that automatically extracts a workflow for troubleshooting using multiple trouble tickets. Our method extracts an operator's actions from free-format texts and aligns relative sentences between multiple trouble tickets. Finally, we show a novel approach to visualizing a workflow by mining conditional branches using clustering. We validated our method using real trouble ticket data captured from a network operation and showed that it can extract the workflow to identify the cause of failure.

In this paper, we propose a mathematical model for intelligent transportation systems (ITS) in an urban environment, which takes into account both the urban structure and vehicles. Using the stochastic geometry approach, we model the locations of vehicles with a Poisson point process on roads whose interval is a fixed value. We consider typical vehicle-to-infrastructure and vehicle-to-vehicle communication scenarios and derive theoretical values of the probability of successful transmission. Our results from numerical experiments reveal how the urban structure can affect wireless communications in ITS.

With the growth of services in IP networks, network operators are required to perform proactive operation that quickly detects the signs of critical failures and prevents future problems. Network log data, including router syslog, are rich sources for such operations. However, it has become impossible to find genuinely important logs that lead to serious problems due to the large volume and complexity of log data. We propose a log analysis system for proactive detection of failures. Our key observation is that the abnormality of logs depends on not just the keywords in the messages (e.g. ERROR, FAIL), but generation patterns such as burstiness. Our system consists of three functions: (i) extracting log templates automatically and quickly from a massive amount of unstructured log data; (ii) constructing log feature vectors to characterize the generation patterns of logs; and (iii) using a supervised machine learning approach to associate failures with the log data that appeared before them. We validated our system using real log data collected from a large network and determined its effectiveness.

Understanding the impacts and patterns of network events such as link flaps or hardware errors is crucial for diagnosing network anomalies. In large production networks, analyzing the log messages that record network events has become a challenging task due to the following two reasons. First, the log messages are composed of unstructured text messages generated by vendor-specific rules. Second, network equipment such as routers, switches, and RADIUS severs generate various log messages induced by network events that span across several geographical locations, network layers, protocols, and services. In this paper, we have tackled these obstacles by building two novel techniques: statistical template extraction (STE) and log tensor factorization (LTF). STE leverages a statistical clustering technique to automatically extract primary templates from unstructured log messages. LTF aims to build a statistical model that captures spatial-temporal patterns of log messages. Such spatial-temporal patterns provide useful insights into understanding the impacts and root cause of hidden network events. This paper first formulates our problem in a mathematical way. We then validate our techniques using massive amount of network log messages collected from a large operating network. We also demonstrate several case studies that validate the usefulness of our technique.