{"title":"Cost-aware virtual machines placement problem under constraints over a distributed cloud infrastructure","authors":"Eya Dhib, K. Boussetta, N. Zangar, N. Tabbane","doi":"10.1109/COMNET.2017.8285591","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285591","url":null,"abstract":"Massively Multi-players Online Gaming (MMOG) presents one of the most popular large scale Cloud Gaming services. However, minimizing the overall MMOG operating cost is viewed as a critical task. The main challenge for MMOG providers is to find the best tradeoff between cost and response delay when allocating resources: in fact, allocating powerful resources lead to an excellent operating delay, but it is costly. However, cheapest resources don't guarantee even acceptable latency especially for high peak periods. In this view, the present paper contributes to optimize, under delay constraint, the resources allocation cost of MMOG service over a distributed Cloud infrastructure. We develop a model to capture the intrinsic trade-off between response delays relative to allocated resources and their corespondent costs. Then, we formulate the optimal VMs placement problem, which is NP-hard. Besides, we propose a Cost-aware Virtual Machines placement algorithm that approximates the best trade-off point between the two compromise terms. We evaluate our contribution comparing to a Random, Greedy Allocation Cost (GAC) and Minimum Allocation Cost (MAC) placement algorithms via Matlab tool. Results show elasticity and effectiveness of our contribution in maintaining the balance between cost and delay.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126663125","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":"A comparative study of RPL objective functions","authors":"Inès Kechiche, Inès Bousnina, A. Samet","doi":"10.1109/COMNET.2017.8285595","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285595","url":null,"abstract":"Smart Grid (SG) is an innovative concept that aims to implement a communication infrastructure for data exchange between the various entities connected to these networks. In this case, Wireless Sensor Networks (WSNs) have recently been considered as a promoting communication technology for SG applications. However, problems such as noise, interference and fading in SG environments, make reliable and energy-efficient multi-hop routing a challenging task for traditional WSNs routing protocols. Thus, IETF has proposed an IPv6 based routing protocol working under stringent low power and low-cost constraints. This Routing Protocol for Low power and Lossy Network (RPL), selects the ideal routes from a source to a destination node based on certain metrics injected into what is called an Objective Function (OF). In this work, we investigate basics OFs namely Objective Function zero (OF0) and Hysteresis Objective Function (MRHOF). We also study the most influential parameters on the performance using Contiki COOJA simulator and then evaluate the RPL performance in terms of latency, packet delivery ratio, control overhead and supported throughput. The simulation results revealed that these parameters have a great impact and indicated that the performance of RPL within high-density networks for OF0 can provide a better RPL behavior than MRHOF.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127390120","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}
M. A. Khan, Sebastian Peters, Xuan-Thuy Dang, Tobias Dörsch, Patrick Engelhard
{"title":"On the approaches for efficient mobility management in SDNized wireless networks","authors":"M. A. Khan, Sebastian Peters, Xuan-Thuy Dang, Tobias Dörsch, Patrick Engelhard","doi":"10.1109/COMNET.2017.8285590","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285590","url":null,"abstract":"In this paper, we study the scalability issues of SDNized wireless networks, specifically those relevant to mobility management. We study the improvements in handover delays: i) when a proposed proactive mobility management algorithm is implemented, ii) when the controller delegates partial control of mobility management to the forwarding entities. For the implementation of the proposed approaches on the OpenFlow network, the paper also suggests potential extensions to OpenFlow protocol. The contributed approaches are validated on a full scale demonstrator and results show that proactive outperforms reactive and the delegated control approach performs better than proactive for smaller topology sizes. Furthermore a proposal for LTE-X2 specific control delegation is discussed as use-case.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121883185","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":"QoE-based vertical handover decision management for cognitive networks using ANN","authors":"A. B. Zineb, M. Ayadi, S. Tabbane","doi":"10.1109/COMNET.2017.8285600","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285600","url":null,"abstract":"The main goal of 5G cognitive radio in heterogeneous networks is to maintain seamless connectivity and provide satisfying Quality of Service (QoS) by switching from one network to another using Vertical Handovers (VHO). The accuracy and the quickness of VHO decision is the key feature to improve and maintain high QoS levels. Recently, many works have been interested to Artificial Neural Networks (ANN) as decisional algorithm for VHO. It was considered efficient since it can handle a decision based on prior knowledge acquired during a learning process and takes into account many criteria of QoS. This efficiency can be more improved while considering the Quality of Experience (QoE) in the ANN inputs set. This paper proposes a modified multi-criteria vertical handoff decision algorithm based on ANN with QoE prediction scheme. The proposed mechanism concept serves to improve the accuracy of the vertical handoff decision for radio heterogeneous networks. Developed algorithm is compared to classical Fuzzy Logic (FL) and Multi Attribute Decision-Making (MADM) ones. Obtained results show that QoE based ANN improve final QoS/QoE satisfaction metrics while reducing delays and the number of executed handoffs.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"590 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123940319","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":"SODV speed based ad hoc on demand vector link routing protocol: A routing protocol for VANET networks","authors":"Kchaou Manel, C. Lamia","doi":"10.1109/COMNET.2017.8285587","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285587","url":null,"abstract":"ITS intelligent transportation systems represent one of the most desirable technologies, when the safety, efficiency, and comfort of everyday road travel need to be improved when a great number of people are dying because of road accidents. Vehicular Ad-hoc Network, VANET, is one of the emerging technologies, which will make the life easier. VANET provide an important knowledge to drivers. This knowledge is provided by one vehicle to another using vehicle to vehicle communications. To make VANET successful, routing protocols should be given a greater attention. In this paper, we present SODV Speed based On Demand Vector link routing protocol which is an AODV based routing protocol. SODV improve the routing process and make the choice of neighboring vehicles more and more relevant by taking into consideration the vehicle velocity in packet transmission procedure. Performance analysis illustrates that SODV outperform AODV routing protocol especially in transmission delay.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126718075","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":"Mobile user association for heterogeneous networks using optimal transport theory","authors":"Hakim Ghazzai, H. Tembine, Mohamed-Slim Alouini","doi":"10.1109/COMNET.2017.8285588","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285588","url":null,"abstract":"This paper investigates the mobile user association problem for heterogeneous networks. More specifically, it applies the optimal transport (OT) concept to determine the cells corresponding to each base station (BS) that minimize the total transmit power consumption of orthogonal frequency-division multiple access (OFDMA) cellular networks. This is performed by respecting the network quality of service and by taking into account the resource limitation per BS (e.g., power budget and number of resource blocks). Starting from given BS locations and user distributions, a fixed point algorithm is employed to find the optimal solution for the formulated problem. Selected numerical results investigate various practical scenarios with different user distributions and show that the cell boundaries obtained using OT solution provide a significant energy saving compared to the classical Voronoi cell boundaries.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128902937","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":"PDAS: PLR-delay aware scheduler for real time application in LTE-A","authors":"Saloua Hendaoui, N. Zangar, S. Tabbane","doi":"10.1109/COMNET.2017.8285594","DOIUrl":"https://doi.org/10.1109/COMNET.2017.8285594","url":null,"abstract":"The importance of Long Term Evolution-Advanced (LTE-A) comes from its support to Real Time (RT) applications. A robust scheduler is crucial to guarantee advanced services. Despite variations, in terms of LTE-A downlink schedulers, time sensitive applications are not yet satisfied. In fact, the requests to access LTE-A services are enormous and it exceed the network capabilities. Real time flows must be satisfied in term of Quality of Service (QoS) requirements. Delay is a key feature that should be considered by a scheduler. The RT flows must be scheduled before their deadline. Otherwise, they will be dropped. In this paper, we propose a novel LTE-A downlink scheduler based on delay-PLR (Packet Loss Ratio) prediction. It aims at providing a balance between low delays and acceptable PLR for the RT traffic. We evaluate our proposal by launching several simulations. Further, we compare the captured results with schedulers from the literature. Results show that our proposal do better than the benchmarks we considered and it guarantees the QoS of the Non RT (NRT) flows.","PeriodicalId":192985,"journal":{"name":"2017 Sixth International Conference on Communications and Networking (ComNet)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133253096","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}