Time filter

Source Type

San Mateo, CA, United States

Wada H.,National ICT Australia | Suzuki J.,University of New South Wales | Yamano Y.,University of Massachusetts Boston | Oba K.,OGIS International Inc.
Software - Practice and Experience | Year: 2011

This paper focuses on service deployment optimization in cloud computing environments. In a cloud, an application is assumed to consist of multiple services. Each service in an application can be deployed as one or more service instances. Different service instances operate at different quality of service (QoS) levels depending on the amount of computing resources assigned to them. In order to satisfy given performance requirements, i.e. service level agreements (SLAs), each application is required to optimize its deployment configuration such as the number of service instances, the amount of computing resources to assign and the locations of service instances. Since this problem is NP-hard and often faces trade-offs among conflicting QoS objectives in SLAs, existing optimization methods often fail to solve it. mathrmE 3-R is a multiobjective genetic algorithm that seeks a set of Pareto-optimal deployment configurations that satisfy SLAs and exhibit the trade-offs among conflicting QoS objectives. By leveraging queueing theory, E 3-R estimates the performance of an application and aids defining SLAs in a probabilistic manner. Moreover, E 3-R automatically reduces the number of QoS objectives and improves the quality of solutions further. Experimental studies demonstrate that E 3-R efficiently obtains quality deployment configurations that satisfy given SLAs. Copyright © 2011 John Wiley & Sons, Ltd.

Wada H.,University of New South Wales | Suzuki J.,University of Massachusetts Boston | Yamano Y.,OGIS International Inc. | Oba K.,OGIS International Inc.
IEEE Transactions on Services Computing | Year: 2012

In Service-Oriented Architecture, each application is often designed as a set of abstract services, which defines its functions. A concrete service(s) is selected at runtime for each abstract service to fulfill its function. Since different concrete services may operate at different quality of service (QoS) measures, application developers are required to select an appropriate set of concrete services that satisfies a given Service-Level Agreement (SLA) when a number of concrete services are available for each abstract service. This problem, the QoS-aware service composition problem, is known NP-hard, which takes a significant amount of time and costs to find optimal solutions (optimal combinations of concrete services) from a huge number of possible solutions. This paper proposes an optimization framework, called E 3, to address the issue. By leveraging a multiobjective genetic algorithm, E 3 heuristically solves the QoS-aware service composition problem in a reasonably short time. The algorithm E 3 proposes can consider multiple SLAs simultaneously and produce a set of Pareto solutions, which have the equivalent quality to satisfy multiple SLAs. © 2012 IEEE.

Wada H.,National ICT Australia | Suzuki J.,University of Massachusetts Boston | Oba K.,OGIS International Inc.
Journal of Database Management | Year: 2011

In Service Oriented Architecture (SOA), each application is designed with a set of reusable services and a business process. To retain the reusability of services, non-functional properties of applications must be separated from their functional properties. This paper investigates a model-driven development framework that separates non-functional properties from functional properties and manages them. This framework proposes two components: (1) a programming language, called BALLAD, for a new per-process strategy to specify non-functional properties for business processes, and (2) a graphical modeling method, called FM-SNFPs, to define a series of constraints among non-functional properties. BALLAD leverages aspects in aspect oriented programming/modeling. Each aspect is used to specify a set of non-functional properties that crosscut multiple services in a business process. FM-SNFPs leverage the notion of feature modeling to define constraints among non-functional properties like dependency and mutual exclusion constraints. BALLAD and FM-SNFPs free application developers from manually specifying, maintaining and validating non-functional properties and constraints for services one by one, reducing the burdens/costs in development and maintenance of serviceoriented applications. This paper describes the design details of BALLAD and FM-SNFPs, and demonstrates how they are used in developing service-oriented applications. BALLAD significantly reduces the costs to implement and maintain non-functional properties in service-oriented applications. Copyright © 2011, IGI Global.

Phan D.H.,University of Massachusetts Boston | Suzuki J.,University of Massachusetts Boston | Omura S.,OGIS International Inc. | Oba K.,OGIS International Inc. | Vasilakos A.,University of Western Macedonia
Proceedings - 14th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, CCGrid 2014 | Year: 2014

This paper focuses on push-pull hybrid communication in a cloud-integrated sensor networking architecture, called Sensor-Cloud Integration Platform as a Service (SC-iPaaS). SC-iPaaS consists of three layers: sensor, edge and cloud layers. The sensor layer consists of wireless body sensor networks, each of which operates several sensors for a homebound patient for a remote physiological and activity monitoring. The edge layer consists of sink nodes that collect sensor data from sensor nodes in the sensor layer. The cloud layer hosts cloud applications that obtain sensor data through sink nodes in the edge layer. This paper formulates an optimization problem for SC-iPaaS to seek the optimal data transmission rates for individual sensor and edge nodes and solves the problem with respect to multiple objectives (e.g., data yield, bandwidth consumption and energy consumption) subject to given constraints. This paper sets up a simulation environment that performs remote multi-patient monitoring with five on-body sensors including ECG, pulse oximeter and accelerometer per a patient. Simulation results demonstrate that the proposed optimizer successfully seeks Pareto-optimal data transmission rates for sensor/sink nodes against data request patterns placed by cloud applications. The results also confirm that the proposed optimizer outperforms an existing well-known optimization algorithm. © 2014 IEEE.

Lee C.,University of Massachusetts Boston | Suzuki J.,University of Massachusetts Boston | Vasilakos A.,University of Western Macedonia | Yamano Y.,OGIS International Inc. | Oba K.,OGIS International Inc.
Proceeding of the 2nd Workshop on Bio-Inspired Algorithms for Distributed Systems, BADS '10 | Year: 2010

This paper studies an evolutionary game theoretic mechanism for adaptive and stable application deployment in cloud computing environments. The proposed mechanism, called Nuage, allows applications to adapt their locations and resource allocation to the environmental conditions in a cloud (e.g., workload and resource availability) with respect to given performance objectives such as response time. Moreover, Nuage theoretically guarantees that every application performs an evolutionarily stable deployment strategy, which is an equilibrium solution under given environ mental conditions. Simulation results verify this theoretical analysis; applications seek equilibria to perform adaptive and evolutionarily stable deployment strategies. Copyright 2010 ACM.

Discover hidden collaborations