{"title":"An Efficient Massive Log Discriminative Algorithm for Anomaly Detection in Cloud","authors":"Jian Liu, Jie Li, Chentao Wu","doi":"10.1109/GLOBECOM38437.2019.9013839","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013839","url":null,"abstract":"Log anomaly detection is a critical step towards building a secure and trustworthy cloud system. As more corporations turn to cloud system to store and process their most valuable data, the risk of a potential breach of those systems increases exponentially. However, conventional top-n log candidates anomaly detection methods, such as Deeplog and N-gram, often suffer from the limited scope of the top-n list, which rules out many potentially suitable candidates. In this paper, we propose Discounted Cumulative Gain (DCG) discriminative algorithm that ranks all the log candidates and calculates the dcg score to determine the number of log candidates. To demonstrate the effectiveness of our algorithm, we conduct comprehensive experiments under different log workloads. Experimental evaluations show that DCG has outperformed Deeplog and N-gram methods in cloud systems, and improved the F-score of Deeplog and N-gram by up to 3.8% and 11.6% respectively.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"33 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80137093","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}
{"title":"Secure Edge Caching for Layered Multimedia Contents in Heterogeneous Networks","authors":"Qichao Xu, Zhou Su, Ying Wang, Kuan Zhang","doi":"10.1109/GLOBECOM38437.2019.9014075","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9014075","url":null,"abstract":"To meet the exponentially increasing mobile services and applications, heterogenous networks (HetNets) have been envisioned as a promising technology. In HetNets, multiple caching-enabled small-cell based stations (SBSs) are deployed within the coverage of a macro-cell base station (MBS) to cache multimedia contents for mobile users. However, due to security threats of untrusted SBSs, the cached contents may be illegally accessed by owners of these untrusted SBSs, resulting in the content privacy leakage. To tackle this problem, we propose a secure edge caching scheme for layered multimedia contents in HetNets. Specifically, considering the layered features of contents, we first develop a secure edge caching framework based on the cooperations of SBSs and MBS. In this framework, the critical base layer subfile of the content are directly delivered by the trusted MBS, whereas the enhancement layer subfiles are cached on untrusted SBSs. Furthermore, according to the limited caching capacities of SBSs and dynamic content demands of mobile users, we formulate the enhancement layer subfile caching problem as a non-convex 0-1 integer programming problem. To solve this problem, we devise a distributed alternating direction method of multipliers (ADMM) and secure the edge caching for each SBS to iteratively search the optimal caching strategy. Simulation results show that the proposed scheme provides secure and efficient multimedia content caching for mobile users.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"36 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80147255","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}
{"title":"Multi-Access Edge Computing-Assisted D2D Streaming for Proximity-Based Social Networking","authors":"Shun-Ren Yang, Chang-Jung Shih, P. Lin","doi":"10.1109/GLOBECOM38437.2019.9014163","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9014163","url":null,"abstract":"The mobile data traffic produced by live streaming is expected to see an exploding growth in recent years. To offload live streaming traffic from mobile networks for proximitybased social networking, device-to-device (D2D) communication is considered a promising technology. Unfortunately, the D2D discovery process requires constant signaling and is energyconsuming. One way to improve this drawback of D2D discovery is to exploit the ETSI multi-access edge computing (MEC) technology, where the knowledge of devices in proximity can be maintained in an MEC server and used to simplify the discovery procedure. In this paper, we aim to implement an MEC-assisted D2D live streaming service that offloads data traffic from mobile networks hierarchically with MEC and D2D communication. Specifically, the service includes an MEC App and a User App. The MEC APP can assist D2D discovery and cache live streams in the MEC server to reduce network latency. The User App can establish D2D connections between devices and share live streams over a D2D network using Wi-Fi Direct, offloading data traffic from mobile networks. We further design a rate adaptation heuristic that is capable of determining a suitable quality level in adaptive streaming for a multi-hop D2D network to improve the overall quality of experience (QoE). The experiment results justify that our proposed architecture and rate adaptation heuristic can provide improved network performance and user QoE for the mobile live streaming service.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"22 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80384693","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}
{"title":"Smart Electric Vehicle Charging with Ideal and Practical Communications in Smart Grids","authors":"John W. Heron, Hongjian Sun","doi":"10.1109/GLOBECOM38437.2019.9013481","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013481","url":null,"abstract":"The growing number of electric vehicles (EV) in the automotive market is leading to ever sharper spikes in consumer power demand. Smart EV charging techniques seek to adjust EV charging load to compensate for supply-demand mismatch. However, all schemes are vulnerable to communications inefficiencies. This paper models implications of communications-driven latency in smart EV charging relevant to secondary voltage control in the distribution network. EV charging load and driving pattern data are gathered from verified statistical studies. A smart charging scheme is proposed enabling high EV penetration with no peak load increase and minimal infrastructure additions. Further, it is applicable to all flexible loads and permits power allocation via a number of possible algorithms. A communications structure for this scheme is then developed, and system performance under ideal and practical communications constraints are studied.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"21 3 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80508451","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}
{"title":"Preference-Aware Caching and Cooperative Coded Multicasting Design for Wireless Backhaul Networks","authors":"Aimin Tang, Yao Liu, Xudong Wang","doi":"10.1109/GLOBECOM38437.2019.9013899","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013899","url":null,"abstract":"The joint considering of caching and coded multicasting can significantly improve caching gain, which has become a promising approach to address the explosive growth of wireless traffic demand. In this paper, the design of caching placement and coded multicasting for wireless backhaul networks is explored under heterogeneous file preferences, where the file preference of each small base station (BS) is assumed to be aware at the macro BS. To address the heterogeneous file preferences, a group-based caching and cooperative coded multicasting scheme is developed in this paper. By utilizing the spectral clustering method, the small BSs are first clustered into different groups with similar file preferences. Moreover, a cooperative caching strategy with symmetric file division is designed for each group, where the suboptimal caching proportion of the most popular files is achieved by an approximation analysis. By utilizing the group-based caching structure, an efficient greedy-based two-level cooperative coded multicasting algorithm is then developed. The proposed algorithm not only utilizes the coded multicasting opportunities within each group, but also explores the cooperative coding opportunities among groups. The effectiveness of our proposed scheme is verified by simulation results, which show that our proposed scheme can significantly reduce the traffic load compared to the existing schemes.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"100 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79340271","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}
{"title":"How Is Energy Consumed in Smartphone Deep Learning Apps? Executing Locally vs. Remotely","authors":"Haoxin Wang, Baekgyu Kim, Jiang Xie, Zhu Han","doi":"10.1109/GLOBECOM38437.2019.9013647","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013647","url":null,"abstract":"Applying deep learning to object detection provides the capability to accurately detect and classify complex objects in the real world. However, currently, few mobile applications use deep learning because such technology is computation- and energy-intensive. This paper, to the best of our knowledge, presents the first detailed experimental study of the smartphone's energy consumption and the detection latency of executing deep Convolutional Neural Networks (CNN) optimized object detec- tion, either locally on the smartphone or remotely on an edge server. We experiment with a variety of smartphones, obtaining different levels of computation capacities, in order to ensure that we are not profiling a specific device. Our detailed measurements refine the energy analysis of smartphones and reveal some interesting perspectives regarding the energy consumption of executing the deep CNN optimized object detection. We believe that these findings will guide the design of energy efficient processing pipeline of the CNN optimized object detection.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"34 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81496120","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}
{"title":"Adaptive Multi-Sensing in EH-WSN for Smart Environment","authors":"Vini Gupta, S. De","doi":"10.1109/GLOBECOM38437.2019.9014025","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9014025","url":null,"abstract":"This paper proposes a novel multi-sensing framework for an energy harvesting heterogeneous wireless sensor network. This framework has utility in smart environment application of Internet-of-Things. It considers a network of multiple wireless nodes, each having heterogeneous sensors to sense slowly- varying environment parameters. For monitoring each parameter, the developed strategy adaptively selects the corresponding sensors of a few neighboring nodes for activation, which jointly optimizes the sensing accuracy and energy efficiency. This process effectively activates a subset of sensors at each node. The subset of selected field nodes as well as the activated sensors at each node in the field is dynamically updated, as a function of harvested energy availability and sensing quality. Simulation results demonstrate the energy efficiency and sensing quality of the proposed framework.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"17 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81549470","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}
{"title":"Multiuser MISO Broadcast Channels with Imperfect CSI: Discrete Signaling without SIC","authors":"Min Qiu, Yu-Chih Huang, Jinhong Yuan","doi":"10.1109/GLOBECOM38437.2019.9014142","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9014142","url":null,"abstract":"In this paper, we study the communication problem of multiuser multiple-input single-output (MISO) broadcast channels with imperfect channel state information (CSI) at the transmitter. Zero-forcing precoding based on the imperfect CSI is adopted so that the channel can be transformed into a Gaussian interference channel. We consider a practical setting where only discrete input signalings are employed and all the receivers adopt single-user treating-interference-as-noise (TIN) decoding, as opposed to rate-splitting and successive interference cancellation. Under this setting, we first use the deterministic model to approximate the original channel model and develop communication schemes to achieve the entire capacity region. By translating the results of the deterministic model back to the MISO model, we develop a systematic way to design discrete input signalings for the original problem. Our simulation results show that our scheme is capable of approaching the (outer bound of) capacity region of the Gaussian interference channel.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"63 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84332208","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}
Bodong Shang, Lingjia Liu, Hao Chen, Jianzhong Zhang, Scott M. Pudlewski, E. Bentley, J. Ashdown
{"title":"Spatial Spectrum Sensing-Based D2D Communications in User-Centric Deployed HetNets","authors":"Bodong Shang, Lingjia Liu, Hao Chen, Jianzhong Zhang, Scott M. Pudlewski, E. Bentley, J. Ashdown","doi":"10.1109/GLOBECOM38437.2019.9013184","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013184","url":null,"abstract":"This paper develops a novel framework for the modeling and analysis of spatial spectrum sensing (SSS) for device-to-device (D2D) communications in uplink two- tier user-centric deployed heterogeneous networks (HetNets), where small cell base stations (SBSs) are deployed in the places with high user density termed hotspots introduced by 3GPP. We study the average transmit power of uplink users, the probability of spatial false alarm and the probability of spatial miss detection of a typical D2D transmitter (D2D-Tx) during SSS. Based on the results, we further characterize the coverage probability of a typical D2D user and the area spectral efficiency (ASE) of D2D networks. Simulation results verify our analysis and demonstrate the advantages of SSS-based D2D communications in future wireless networks.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"41 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85233122","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}
{"title":"Edge eXchange: eNB with Wireless Backhaul Communication among Carriers","authors":"Kengo Sasaki, S. Makido, A. Nakao","doi":"10.1109/GLOBECOM38437.2019.9013198","DOIUrl":"https://doi.org/10.1109/GLOBECOM38437.2019.9013198","url":null,"abstract":"Recently, Mobile/Multi-access Edge Computing (MEC) has attracted significant attention as a key component for executing cooperative driving systems that exhibit low latency. However, achieving low latency communication among evolved Node Bs (eNBs) is a critical challenge while implementing cooperative driving systems using MEC. The Edge Server (ES) deployed at the eNB is required to collect various sensor data from physically close vehicles, although the vehicles may not be connected to the eNB attached to the ES. If the vehicle and the ES belong to different mobile carriers, the sensor data of the vehicle is required to pass through a network of multiple carriers and the Internet. In this paper, we propose the ''Edge eXchange (EX).'' The EX is a conceptual eNB, which is equipped with ''wireless backhaul communication'' between eNBs regardless of the carriers. Here, the wireless backhaul communication indicates a direct communication between eNBs using wireless communication. To evaluate the EX, we propose an ES deployment method and consider two types of distances as alternatives to communication latency. The first is the communication distance between adjacent eNBs. The second is the communication distance between the vehicle and the closest computational nodes. Using the Japanese network model, we analyze the above distances and evaluate the effect of the EX. From the result of the analysis, the EX can dramatically suppress communication latency between eNBs for small range wireless backhaul communication. Furthermore, the EX can suppress the number of ESs required for achieving low latency by using the wireless backhaul communication.","PeriodicalId":6868,"journal":{"name":"2019 IEEE Global Communications Conference (GLOBECOM)","volume":"9 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85611645","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}