The maturity of Grid Computing and the exponential growth in the popularity of mobile and wireless technologies opened the door to new horizons of computing models based on mobile grid infrastructure. This growing demand has led to the need to study and explore new techniques and approaches to adapt the grid computation concepts into the challenging, ad-hoc mobile environment. Mobile grid scheduling has been the center of attention in this research focus. The different scheduling efforts developed so far overcame the mobility challenges by enforcing a direct point-to-point (P2P) communication between the task initiator and the service provider. In this paper, we introduce a dynamic, adaptive scheduler that relies on the prediction of patterns that do not require the P2P connectivity. The proposed approach can achieve similar and in certain situations better results than traditional P2P scheduling approaches. We are proposing a real-time scheduling approach for mobile ad-hoc grid environments that can provide flexibility in dealing with different types of real-time application tasks. The proposed scheduler utilizes two optimization heuristics to address this problem. The first one applies a modified version of the maximum flow problem while the second approach utilizes a multi-dimensional minimum cost function. Both approaches combine real-time scheduling characteristics while accommodating the mobility and battery dependency challenges. This dynamic scheduler provides different parameters that can be modified to control the scheduler QoS, reliability and ability to adapt to mobility and power dependency.

One of the prime-most issues that is faced by the parallel systems in the past and is inherited by the grid systems of today, is the mapping and the execution of jobs on the available machines. Various scheduling approaches that were suggested in classical parallel systems literature are adopted for the grid systems with appropriate modifications. Although these modifications made them suitable for execution in grid environment, these approaches failed to deliver on the performance front. Dynamic availability of resources, data dependence among the tasks and communication latencies are some of the factors that negatively affected the outcome of these scheduling algorithms. Various grid management systems implemented their custom tailored versions of scheduling algorithms for task execution in the grid. These approaches suffer from various shortcomings such as inefficient utilization of the execution queues and/or failure to cater for the dependencies among the tasks in a job. In this paper, we will compare the two prevalent scheduling models in the grid; opportunistic and planned. Opportunistic model is used in DAGMan for scheduling workflow applications, which in-turn is an integral component of Condor and Condor-G. Planned scheduling, on the other hand, is used by the grid management architectures such as GrADS and MARS.

With the increased complexity of platforms coupled with data centers' servers sprawl, power consumption is reaching unsustainable limits. Researchers have addressed data centers' power & performance management at different hierarchies going from server clusters to servers to individual components within the server. This paper presents a novel technique for autonomic power & performance management of a high-performance server platform that consists of multi-core processor and multi-rank memory subsystems. Both the processor and/or the memory subsystem are dynamically reconfigured (expanded or contracted) to suit the application resource requirements. The reconfigured platform creates the opportunity for power savings by transitioning any unused platform capacity (processor/memory) into low-power states for as long as the platform performance remains within given acceptable thresholds. The platform power expenditure is minimized subject to platform performance parameters, which is formulated as an optimization problem. Our experimental results show around 58.33% savings in power as compared to static power management techniques.

Abstract Mobile IPv6 is an enabling platform for creating IP mobility in the evolution path towards next generation service offerings. However, Mobile IPv6 does not provide reliability and load balancing in the network. In this paper, we introduce ‘Virtual HA Reliability Protocol.’ It is an extension to Mobile IPv6 that introduces reliability and load balancing in the Mobile IPv6‐based networks. It also provides solutions to the problems caused due to Home Agent failures in Mobile IPv6. These problems are: delayed failure detection, service interruption in the upper layer applications, increased workload on the Mobile Node, message overhead over the air interface, and IPsec Security Associations re‐establishment. We also present the results of several experiments to assess the performance of our solution. The results show that our solution provides transparent Home Agent failure detection and recovery mechanisms. As a result, there is a significant reduction in message exchange over the air interface. Also, our solution provides high service availability in the upper layer applications. Moreover, there is reduced workload on the Mobile Node. Finally, the load balancing mechanism of our solution provides efficient, dynamic, and transparent load balancing among the multiple Home Agents. Thus our solution improves the overall Mobile IPv6 and upper layer applications performance. Copyright © 2006 John Wiley & Sons, Ltd.

With the rapid growth of servers and applications spurred by the Internet, the power consumption of servers has become critically important and must be efficiently managed. High energy consumption also translates into excessive heat dissipation which in turn, increases cooling costs and causes servers to become more prone to failure. This paper presents a theoretical and experimental framework and general methodology for hierarchical autonomic power & performance management in high performance distributed data centers. We optimize for power & performance (performance/watt) at each level of the hierarchy while maintaining scalability. We adopt mathematically-rigorous optimization approach to provide the application with the required amount of memory at runtime. This enables us to transition the unused memory capacity to a low power state. Our experimental results show a maximum performance/watt improvement of 88.48% compared to traditional techniques. We also present preliminary results of using game theory to optimize performance/watt at the cluster level of a data center. Our cooperative technique reduces the power consumption by 65% when compared to traditional techniques (min-min heuristic).

The problem of optimally deploying a heterogeneous set of sensing devices in environments with differential surveillance requirements is presented. The problem is formulated in the form of integer mathematical program with an objective function that maximizes overall system coverage. The formulation considers several operation capabilities for the sensing devices including reliability, mobility, transfer cost, lifespan and power self-scheduling. Due to the intractability of the problem, optimal solutions obtained using our mathematical programming formulation can be obtained for small problems. In addition to the optimal solution, two heuristic algorithms are presented to solve different versions of the problem. A set of experiments is conducted to test the algorithms performances for different problem settings. Results of these experiments illustrate that near-optimal coverage performance could be achieved in very less running time. 1.

A mobile ad hoc network (MANET) is a set of mobile nodes that agreed upon forming a temporary, spontaneous network in spite of the lack of any infrastructure or centralized administration. MANET topology changes frequently and arbitrarily due to node mobility. Therefore, an efficient routing protocol is required to cope with the dynamic change of MANET topology, which requires discovering and maintaining new routes, in this paper we propose a route discovery protocol based on location information, which could be provided to MANET nodes by a Global Positioning System (GPS). Our route discovery protocol utilizes the essential features of Voronoi diagrams in order to reduce the search space of routes by allowing only a small subset of MANET nodes, called authorized forwarders, to forward a route request. This results in a restrictive, selective route discovery protocol, which significantly reduces the routing overhead compared to other location-based routing protocol, such as LAR.

Summary form only given. Mobile ad hoc networks (MANET) and the Internet exhibit differences in their network architecture. These differences concern the various sorts of assumptions imposed not only on the structure and topology of the underlying networks, but also on communication patterns of mobile nodes in both networks. Integrating MANET and the Internet into a hybrid network is a challenging problem due to these differences. We propose a three-layer approach that uses both mobile IP and dynamic destination-sequenced distance vector (DSDV) to integrate these two types of networks into a hybrid environment, in order to provide MANET nodes with Internet connectivity and access to the Internet resources. Our approach is based on the use of mobile gateways as an interface between MANET and the Internet. These mobile gateways can use mobile IP when they communicate with the Internet and DSDV when they interact with MANET. We also show the results of several simulation experiments that were conducted to study the integrated environment.

To combine the advantages of mobile ad hoc networks (MANETs) and the Internet, we propose an approach that will integrate them into a hybrid, unified network enabling MANET nodes to have Internet connectivity regardless of their location in MANET. In order to best benefit MANET from Internet resources access, we introduce mobile gateways, which are moving around the boundary of fixed Internet gateways' coverage range, to act as an interface between MANET and the Internet. Mobile gateways are designed in a way to overcome the network architectural mismatches that exist between MANET and the Internet and widen the coverage range affixed Internet gateways. More specifically, mobile gateways are equipped with two interfaces allowing them to communicate simultaneously with MANET and the Internet using an ad hoc routing protocol and Mobile IP, respectively. Our experiments, which were conducted using the network simulator ns2, adopted Mobile IP protocol and dynamic source distance vector (DSDV) routing protocol, and showed that density and mobility of gateways as well as time-to-live of agent advertisements have an impact on the performance of the hybrid network.

The quality of service (QoS) of wireless Internet access that could be provided to multihop wireless networks, so-called mobile ad hoc networks (MANETs), is highly dependent on the quality of the design of the intermediate facility that will integrate MANET and the Internet. This facility is equipped with a hybrid mechanism being able to fulfill the working requirements of MANET and the Internet so that it can connect to either one of these orthogonal network architectures. The architecture that we propose in order to provide MANET nodes with Internet access utilizes fixed gateways (or access points) and exploits the mobility capability of additional mobile ones. Since Internet access to MANET nodes is provided through mobile gateways, the quality of such service depends on the selection procedure used by MANET nodes to choose the most convenient mobile gateways and register with. In this paper, we suggest to use a hybrid criterion based on the weighted sum of the Euclidean distance between MANET nodes and mobile gateways, and the load of mobile gateways, defined as the number of MANET nodes currently registered with them. Moreover, the sum of the weights is normalized to one, where each weight measures the level of interest of the corresponding criterion in the hybrid one. Simulation results show that the hybrid criterion has an impact on the quality of wireless Internet access service depending on the level of interest assigned to each of the Euclidean distance and load criteria in the weighted sum.

In a mobile environment, each mobile host should have a home agent on its home network that maintains a registry of the current location of the mobile host. This registry is normally updated when a mobile host moves from one subnet to another. We study the tradeoff between the cost of updating the registry and the cost of searching for a mobile host. Using a set of special agents, called proxy agents, which implement a two-tier update process, the cost of updates could be reduced; however, the search cost might increase. We introduce a mathematical programming approach to identify a set of proxy agents that minimizes the cost of search. We formulate the minimization of the cost as Min-Sum, Min-Max, and Min-P problems. For situations when fast solutions that are not necessarily optimal are more desirable, we propose using clustering heuristics. Results of many experiments are presented.

The paper addresses the problem of scheduling MPI tasks on the processing nodes of an MPI environment. The authors introduce a static scheduling system, in which program requirements are gathered, dependencies among the tasks are figured out, the computing environment is characterized, and a task assignment is generated. They introduce a tool, called the sniffer which utilizes MPI to benchmark an existing computing environment. The sniffer collects information regarding the network performance, the power of the processing nodes, and the system load in general. They also present a scheduling system, which heuristically produces an allocation of MPI tasks onto processing nodes. The objective is to minimize the total completion time of the MPI program. The scheduling system uses program characterization in terms of processing, communication, synchronization, and dependencies; and the environment information collected by the sniffer to make scheduling decisions.