Jae Hyeok Son

A proximal algorithm for joint resource allocation and minimizing carbon footprint in geo-distributed fog computing

Large-scale Internet applications, such as content distribution networks, are deployed in a geographically distributed manner and emit massive amounts of carbon footprint at the data center. To provide uniform low access latencies, Cisco has introduced Fog computing as a new paradigm which can transform the network edge into a distributed computing infrastructure for applications. Fog nodes are geographically distributed and the deployment size at each location reflects the regional demand for the application. Thus, we need to control the fraction of user traffic to data center to maximize the social welfare. In this paper, we consider the emerging problem of joint resource allocation and minimizing carbon footprint problem for video streaming service in Fog computing. To solve the largescale optimization, we develop a distributed algorithm based on the proximal algorithm and alternating direction method of multipliers (ADMM). The numerical results show that our algorithm converges to near optimum within fifteen iterations, and is insensitive to step sizes.

Forwarding strategy on SDN-based content centric network for efficient content delivery

Content Centric Networking (CCN) paradigm has been proposed to solve the problems of current Internet Protocol (IP) communication. However there is one significant drawback in existing CCN, which is that interest packets are broadcasted to all over the network. This may not only result in slow in delivery of data but it is also causing a lot of network traffics due to a large number of interest packets. For this reason, it is obviously not suitable in a large-scale network. To address the problem we propose a novel packet forwarding strategy using Software Defined Networking (SDN) controller and application. There mainly consists of two processes in CCN. One is for interest packets and the other is for data packets. In this paper, we show how the forwarding mechanisms for the two types of packets are operated under SDN-based CCN in order to improve the efficiency of content delivery and utility of network resources.

Traffic offloading via Markov approximation in heterogeneous cellular networks

The use of heterogeneous small cell-based networks to offload the traffic of existing cellular systems has recently attracted significant attention. One main challenge is solving the joint problems of user association, resource allocation, and interference mitigation. The goal of this paper is to design a self-organizing algorithm that can solve these problems, simultaneously. To this end, this joint resource allocation problem is formulated as an optimization problem which is then solved using log-sum-exp approximation. This solution is then shown to require complete information of the whole network which is not scalable with the network size. To address this scalability issue, a novel Markov chain approach is proposed and its transition probabilities are shown to eventually converge to the near optimal solution without complete information. Furthermore, the gap between the optimal and converged solutions is shown to be bounded. Simulation results show that our proposed algorithm effectively offloads the traffic from macro-cell base station to small-cell base stations. Moreover, the results also show that this algorithm converges very quickly independent of the number of possible configurations.

Congestion prevention mechanism based on Q-leaning for efficient routing in SDN

SDN (Software-Defined Networking) has been proposed to solve problems caused by difficulties in central management, vendor dependency, and increase in complexity of network due to individual process. In current SDN, however, routing algorithm is mainly based on Dijkstras Algorithm and the shortest Flow Path is selected to deliver packets. This may result in network congestion since bandwidth overhead is not considered when a lot of traffic enters in the network. Therefore, we propose a mechanism to prevent network congestion based on Q-learning for efficient routing in SDN. In this paper, we show the network congestion can be improved by reselecting the path and changing Flow Table using predefined threshold and Q-learning routing algorithm.

Defense technique against spoofing attacks using reliable ARP table in cloud computing environment

Recently cloud service has been introduced in order for many enterprises to achieve purposes such as improvement in efficiency, cost reduction and revolution in business process. However spoofing or poison attacks on VM inside the cloud cause the deterioration of cloud system and those attacks can make the huddle for spreading the cloud services. Many researches are now under way to solve such problems but most of these seem to be passive and limited in terms of detecting attacks and applying to large scale of networks. In this paper, we propose a defense technique for loss of VM resources against the network attacks called spoofing of poison on OpenStack environment. In our proposal, we use reliable ARP table which makes our proposal more reliable in cloud computing environment. Finally we conclude this paper showing that the proposed mechanism is an effective way to defend the ARP spoofing attack.

Hosting Virtual Machines on Distributed Datacenters

Almost of cloud services nowadays are built at top geographically distributed infrastructure for better reliability and performance. These cloud providers need an efficient method to control and direct user workload to suitable datacenter, depending on many factors such as: network traffic cost, operation cost budget, energy consumption, etc. In the virtual machine placement problem, current works mainly focus on the efficiency of packing virtual machines into servers and ignore the distributed scenario of datacenters. In this paper, we consider the problem of placing virtual machines to host applications on a shared resource pool based on distributed cloud platforms. We formulate the problem of hosting virtual machines on distributed datacenters as an optimization problem, and propose a distributed framework DHC that can dynamically direct workload between datacenters to maximize total utility of entire datacenters. We also conduct many case studies to validate our method, and evaluate its effectiveness and practicality, using real-workload traffic traces. The simulation results show that our algorithm can dynamically optimize the total utility, depending on various workload of users.

Delivering Scalable Video Streaming in ICN enabled Long Term Evolution networks

Information Centric Networking (ICN) is envisioned to be the future Internet architecture and mobile access network e.g., Long Term Evolution (LTE), and 5G will be the major access networks. In this paper, we present a cache management and cooperative request forwarding schemes for Scalable Video Streaming (SVS) in Information Centric Networking (ICN) enabled mobile access networks. H.264/SVC encoded video is consisted a mandatory baselayer and multiple optional enhancement layers. Baselayer, which is enough to decode the video, though with the lowest quality, is needed by every user who want to watch the video while enhancement layers are used to improve the video quality. Only a subset of users download enhancement layers of the video. Therefore, caching the baselayer nearer to the users will increase their Quality of Experience. Furthermore, we introduce cooperative request forwarding for the baselayer of video to take more benefits from cache of neighboring base stations. We have intensively simulated our proposed schemes by extending chunk level simulator ccnsim which is developed over Omnet++. Our experimental results show that, cache hit rate can be improved significantly by adopting our proposed caching and Interest forwarding schemes.

Online learning-based clustering approach for news recommendation systems

Recommender agents are widely used in online markets, social networks and search engines. The recent online news recommendation systems such as Google News and Yahoo! News produce real-time decisions for ranking and displaying highlighted stories from massive news and users access per day. The more relevant highlighted items are suggested to users, the more interesting and better feedback from users achieve. Therefore, the distributed online learning can be a promising approach that provides learning ability for recommender agents based on side information under dynamic environment in large scale scenarios. In this work, we propose a distributed algorithm that is integrated online K-Means user contexts clustering with online learning mechanisms for selecting a highlighted news. Our proposed algorithm for online clustering with lower bound confident clustering approximates closer to offline K-Means clusters than greedy clustering and gives better performance in learning process. The algorithm provides a scalability, cheap storage and computation cost approach for large scale news recommendation systems.

Resources management in virtualized Information Centric Wireless Network

Information-Centric Networking (ICN) and Wireless Network Virtualization (WNV) are two emerging technologies for the next-generation network infrastructure. ICN provides the key technology to reduce the network traffic by caching the contents temporarily and aggregating the same content requests. WNV enables the resources sharing among Infrastructure Providers (InPs) and Mobile Virtual Network Operators (MVNOs), to reduce capital expenditures and operating expenses. Also, the network resource management becomes easier because of WNV. In this paper, we combine these two technologies to improve the performance of the network and the profit of the MVNOs. We formulate the optimization problem to solve the cache allocation problem and maximize the profit of MVNOs by controlling the usage of cache space, backhaul link, and radio resources. Finally, we validate our proposed scheme using a chunk-level simulator. The simulation results show that the proposed mechanism can improve the profit of MVNOs and users QoS.