Chang-Woo Yoon

Efficient Service Recommendation System for Cloud Computing Market

In recent years, Cloud computing is gaining much popularity as it can efficiently utilize the computing resources and hence can contribute to the issue of Green IT to save energy. So to make the Cloud services commercialized, Cloud markets are necessary and are being developed. As the increasing numbers of various Cloud services are rapidly evolving in the Cloud market, how to select the best and optimal services will be a great challenge. In this paper we present a Cloud service selection framework in the Cloud market that uses a recommender system (RS) which helps a user to select the best services from different Cloud providers (CP) that matches user requirements. The RS recommends a service based on the network QoS and Virtual Machine (VM) platform factors of difference CPs. The experimental results show that our Cloud service recommender system (CSRS) can effectively recommend a good combination of Cloud services to consumers.

Efficient service recommendation system for cloud computing market

In recent years, Cloud computing is gaining much popularity as it can efficiently utilize the computing resources and hence can contribute to the issue of Green IT to save energy. So to make the Cloud services commercialized, Cloud markets are necessary and are being developed. As the increasing numbers of various Cloud services are rapidly evolving in the Cloud market, how to select the best and optimal services will be a great challenge. In this paper we present a Cloud service selection framework in the Cloud market that uses a recommender system (RS) which helps a user to select the best services from different Cloud providers (CP) that matches user requirements. The RS recommends a service based on the network QoS and Virtual Machine (VM) platform factors of difference CPs. The experimental results show that our Cloud service recommender system (CSRS) can effectively recommend a good combination of Cloud services to consumers.

Multi-objective Optimization Model for Partner Selection in a Market-Oriented Dynamic Collaborative Cloud Service Platform

In this paper, we propose a promising multi-objective (MO) optimization model for partner selection in a market-oriented dynamic collaboration (DC) platform of Cloud providers (CPs) to minimize the conflicts among providers that may happen when negotiating among providers. The model not only uses their individual information (INI) but also past collaborative relationship information (PRI) for partner selection which is seldom considered in existing approaches. A multi-objective genetic algorithm (MOGA) called MOGA-IC is also proposed to solve the model as the model is NP-hard. The algorithm is developed using two popular MOGAs- NSGAII and SPEA2. The experimental results show that MOGAIC with NSGA-II outperformed the MOGA-IC with SPEA2 in finding useful Pareto optimal solution sets. In addition, other simulation experiments are conducted to verify the effectiveness of the MOGA-IC in terms of satisfactory partner selection and conflicts minimization.

A Novel Market Oriented Dynamic Collaborative Cloud Service Infrastructure

In this paper, we present a novel combinatorial auction (CA) based Cloud market model that facilitates dynamic collaboration (DC) among Cloud providers (CPs) for providing composite/collaborative Cloud services to consumers and hence can address the interoperability and scalability issues for Cloud computing. Also to minimize the conflicts that may happen when negotiating among providers in a DC platform, we propose a new auction policy in CA that allows a CP to dynamically collaborate with suitable partner CPs to form a group before joining the auction and to publish their group bids as a single bid to fulfill the service requirements completely. But to find a good combination of CP partners is a NP-hard problem. So we propose a promising multi-objective (MO) optimization model for CP partner selection that not only uses their individual information (INI) but also their past collaborative relationship information (PRI) which is seldom considered in existing approaches. A multi-objective genetic algorithm (MOGA) called MOGA-IC is also developed to solve the model. We implemented our proposed CACM model and the MOGA-IC in a simulated environment and study their economic efficiency and performance with existing model and algorithm. The experimental results show that the proposed MOGA-IC can support satisfactory and high quality partner selection in CACM model.

A Hybrid Algorithm for Partner Selection in Market Oriented Cloud Computing

In our previous paper (2), we proposed a novel combinatorial auction (CA) based Cloud market model for trading services that allows Cloud providers (CPs) to make groups and submit their bids collaboratively as a single bid for winning the auction. But to find a good combination of CP partners and make groups is a NP-hard problem. Since each provider only has limited information about other providers, past collaborative task information (i.e. no. of times collaboratively win the auctions, failed to make groups, etc.) needs to be analyzed and utilized for partner selection. We call it multi-task and multi-objective optimization problem. To solve this problem, in this paper, we propose a hybrid algorithm that utilizes artificial neural network (ANN) for gathering and analyzing information about previous tasks and then uses multi-objective genetic algorithm (MOGA) to solve the partner selection problem. Simulation results show that our proposed algorithm is effective.

Classification of N-Screen services, scenarios and its standardization

By the advent of IPTV and smart TV, the broadcasting is transmitted using Internet. Bi-directional programs are appeared on broadcasting services. The convergence service combining with communication, information and web service are appeared too. N-Screen service is a killer service of smart TV. It uses several terminals, either fixed or mobile, to provide bi-directional, convergence and personal services with broadcasting service. N-Screen service can be classified into three categories: first, OSMU (One Source Multi Use) case, providing same contents to terminals having different capabilities such as screen size, CPU speed, memory, codec, network speed, etc. Second case is a vertical handover, continuous watching of content using different terminal. Third case is a collaborative service among multiple terminals. For example, a customer is watching soap opera using TV, while watching a specific scene related information or advertisement using his PAD or smart phone. In ITU-T SG13, the Y.sof (Service Scenario over FMC) was standardized. It defined detailed overall service scenarios using feature extraction of seamless mobile convergence service on several networks such as WiFi, 3G, WiMAX/WiBro. This standard extracts key features of five key elements: person, terminal, network, content, and service. Then, it analyzes relationships among key elements and suggests overall service scenario model. The service scenario model can be easily adopted on describing N-Screen service scenario because Y.sof handles scenario cases among several fixed or mobile terminals. In this paper, I will introduce Y.sof and classification of N-Screen service scenarios described using the standard. Also I will refer the standardization issues of N-Screen and its technologies.

A Platform as a Service for Smart Home

to the convergence of home network, smart home technologies have been developing rapidly. However, all data generated from smart homes which might imply valuable information and be able to bring value-added outcome are not well utilized. Since it contains very private information, smart home users might want to avoid the chance to expose data from their living place. Moreover, few work concerns with how to deal with those valuable tentative but private data for further use. Motivated by this, we adapt cloud computing technology to smart home domain and design a framework which delivers a platform as a cloud computing service. The integrated framework we propose stores data generated from smart homes and provides these data for various services on the platform in a safer way to protect private data.