Search

Energy harvesting technology has been applied to power nodes in a wireless sensor networks (WSNs). However, it suffers from the dynamic nature of the ambient energy. Wireless charging, on the contrary, offers an additional choice to charge the sensor nodes (SNs) with a mobile charger (MC) which is often implemented to move within the network. Nevertheless, the energy spent on moving among sensors accounts for a considerable proportion of the whole energy the MC can take. To this end, we consider combining these two sources of energy to carry out the energy neutral operation for the WSNs. In this paper, we formulate the problem of minimizing the number of nodes for perpetual coverage of targets under the constraint of the energy capacity of a MC and the distribution of the energy harvesting rate across the monitoring field which generates great difficulty. We designed two approximation algorithms to tackle this problem. We conduct extensive simulations to evaluate the performance of our proposed algorithms. The results showed performance of these two algorithms with respect to impact of different parameters.

Understanding the characteristics of MapReduce workloads in a Hadoop cluster is the key to making optimal configuration decisions and improving the system efficiency and throughput. However, workload analysis on a Hadoop cluster, particularly in a large-scale e-commerce production environment, has not been well studied yet. In this paper, we performed a comprehensive workload analysis using the trace collected from a 2000-node Hadoop cluster at Taobao, which is the biggest online e-commerce enterprise in Asia, ranked 10th in the world as reported by Alexa. The results of the workload analysis are representative and generally consistent with the data warehouses for e-commerce web sites, which can help researchers and engineers understand the workload characteristics of Hadoop in their production environments. Based on the observations and implications derived from the trace, we designed a workload generator Ankus, to expedite the performance evaluation and debugging of new mechanisms. Ankus supports synthesizing an e-commerce style MapReduce workload at a low cost. Furthermore, we proposed and implemented a job scheduling algorithm, Fair4S , which is designed to be biased towards small jobs. Small jobs account for the majority of the workload, and most of them require instant and interactive responses, which is an important phenomenon at production Hadoop systems. The inefficiency of Hadoop fair scheduler for handling small jobs motivates us to design the Fair4S, which introduces pool weights and extends job priorities to guarantee the rapid responses for small jobs. Experimental evaluation verified that the Fair4S accelerates the average waiting times of small jobs by a factor of 7 compared with the fair scheduler.

In order to improve the accuracy of cell selection in heterogeneous cellular systems, this paper proposes a fuzzy multiple-objective decision-based cell selection (FMDCS) strategy. Since heterogeneous cellular systems have different access technologies and multiple traffic classes, the strategy adopts cell type, data rate, coverage, transmission delay, and call arrival rate as evaluation indices, and uses different weight vectors according to the traffic classes of the mobile host. Then, a fuzzy multipleobjective decision algorithm is applied to select the optimal cell from all candidates. This paper also gives an instance analysis and simulation. The instance analysis shows FMDCS makes different selections for different traffic classes. Simulation results of the after-handoff quality-ofservice (QoS) show the selected cell can provide MH optimal service.

Bulk data dissemination is a basic building block for enabling software update and reprogramming in wireless sensor networks. The recent structure based approach looks promising for efficient dissemination since it facilitates transmission and sleep scheduling. However, a number of limitations exist in existing structured protocols. In this paper, we propose a correlated core based solution for efficient bulk data dissemination in wireless sensor networks. We propose an efficient backbone node selection algorithm to construct the core structure by exploiting link correlation. We also design a novel negotiation mechanism which greatly reduces the control message overhead as compared to the existing structured protocols. We conduct both simulation and testbed experiments, and the results show that our proposed solution outperforms the state-of-the-art in terms of both the number of transmissions and the completion time.

Wireless sensor network (WSN) is a typical distributed storage system, and network coding technology is developed to enhance the data persistence of WSN. However, the traditional distributed coding strategy may cause serious "cliff effect" in the decoding process, that is to say, few source data can be recovered before sufficient encoded packets are received. Moreover, nodes may fail due to the lack of energy or the influence of the switching of external environment, such as a disaster scenario. Such failures may concentrate in a small region or distribute in the whole deployment area which can severely reduced the decoding efficiency of the persistent data in WSN. In this paper, we propose the PLTCDS (prioritized LT codes based distributed storage) algorithm to improve the data decoding efficiency when the data persistence is assured. The main idea of PLTCDS is that the predefined node broadcasts a beacon to stimulate the nodes to form the network with degree distribution priority. To ensure the effectiveness of storage nodes, PLTCDS introduces a class of cumulative counter scheme to avoid empty storage. Also we discuss about the idea of another type of PLTCDS. Experimental results show that PLTCDS algorithm can enhance the network data collection performance and reduce the influence of "cliff effect".

With the scale of computing system increases, system performance and reliability, described by various Quality of Service(QoS) metrics, cannot be guaranteed if only the objective is to minimize the total power consumptions separately, despite of the violations of QoS. In this paper a feedback control based power aware job scheduling algorithm is proposed to minimize power consumption in computing system and to provide QoS guarantees. In the proposed algorithm, jobs are scheduled according to the real-time and historical power consumption as well as the QoS requirements. Simulations show that the proposed algorithm can reduce power consumptions significantly while still providing QoS guarantees and the performance degradation is acceptable. The results also show that fine-grained job-level power aware scheduling can achieve better power/performance balancing between multiple processors or cores than coarse-grained methods. And the results also suggest that conventional hardware based per-component and system-wide power management methods can save more power consumptions if they are in assistance with job-level adaptation.

In grid environment, jobs may be scheduled to multiple machines across different administrative domains. However, grid security is a main hurdle to make the job scheduling decision secure, reliable and fault tolerant. A s ecurity- aware parallel and independent job s cheduling algorithm in grid computing environment based on adaptive job replications was proposed. In risky and failure-prone grids, it is robust due to its adaptive job replications and rescheduling mechanism. Simulation results generated based on the SimGrid package show that a higher scheduling success of 97% rate and higher grid resource utilization of 74% can be achieved. The performance of our algorithm is better than non-security-aware scheduling algorithms based on fixed-number job replications and it is fault tolerant and scalable.

Resource management is one of the main issues in Cloud Computing. In order to improve resource utilization of large Data Centers while delivering services with higher QoS to Cloud Clients, an automatic resource allocation strategy based on market Mechanism ( A RAS-M) is proposed. Firstly, the architecture and the market model of A RAS-M are constructed, in which a QoS-refectitive utility function is designed according to different resource requirements of Cloud Client . T he equilibrium state of A RAS-M is defined and the proof of its optimality is given. Secondly, A Genetic Algorithm (GA) -based automatic price adjusting algorithm is introduced to deal with the problem of achieving the equilibrium state of A RAS-M. Finally, A RAS-M is implemented on Xen. Experiment results show that A RAS-M can approximately achieve the equilibrium state, that is, demand and supply is nearly balanced, which validate s that A RAS-M is effective and practicable , and is capable of achieving resource balance in cloud computing .

With the growth of hardware and software resources, the management of resource scheduling is becoming more and more difficult in multiple virtual machine system. It has become a very difficult problem that how to schedule the system resource and improve the service performance of resource. In order to solve this problem, we propose an adaptive management mechanism for resource scheduling. In the management mechanism, we first propose an adaptive management model for resource scheduling. Then, we present a genetic simulated annealing to resolve the management model. On the basis of the model and the algorithm, we design a management module. All these constitute an adaptive management mechanism for resource scheduling in multiple virtual machine system. In order to justify the feasibility and availability of the adaptive management mechanism for resource scheduling, a series of experiments have been done. The results show that it is feasible to adaptively manage and schedule the system resources and ensure the quality of service of resources in multiple virtual machine system.

In consolidated virtualization systems, hardware resources are shared and multiplexed across multiple virtual machines (VMs) for energy and cost savings, where resources are over-provisioned according to the peak demand of VMs to provide performance guarantees. This over-provisioning manner results in resource waste and contention under heavily load conditions. As a result, there is a need to multiplex resources among VMs in a fine-grained thin-provisioning manner in heavily loaded virtualized system. In this paper we propose such a thin provisioning approach for resource allocation among VMs with minimal performance degradations. Our approach consists of two parts: one is workload characterization, and the other is dynamic resource allocation via prioritization. Experiments on a Xen based virtualized environment are conducted and evaluated. The results show that the proposed approach can support concurrent contending requests with acceptable performance penalties.

In virtualized systems, such as large data centers and cloud computing environments, resources are shared across multiple virtual machines, which results in contentions and conflicting under heavily loaded or consolidated situations. In order to accommodate as many as computing and service capabilities while still delivering performance guarantees, resource utilization and application performance should be tradeoffed such that fewer resources will be utilized for a specific performance requirement. To achieve this goal, in this paper we propose an adaptive resource allocation for tradeoff between resource utilization and upper level application’s performance such as response time and throughput. This approach does not require a highly accurate performance model in a virtualized system where workloads usually change frequently with time in some intervals. Experiments on a Xen based virtualized environment are conducted and evaluated. The results show that the proposed approach utilizes less CPU resources to achieve the same performance goals compared to the fixed over-provisioning of resources.

Growth Codes (GC) enhances the data persistence in dense sensor networks. However, GC exchanges data with neighbors in a completely random way, which may lead to uneven sensor data distribution in sparse sensor network. This significantly reduces the efficiency of GC data acquisition and fault-tolerance in sparse sensor network with less connectivity. In this paper, we propose Regulative Growth Codes (RGC) which use a random sequencing policy in data exchange operation instead of the completely random policy used in GC, and introduce the self-detection mechanism to reduce the redundant exchange. Simulation results show that the performance of RGC is better than GC in sparse sensor networks.

Typical remote sensing image interpretation consists of large number of long-lived independent computation jobs such as calibration, correction, and transformation and computation. These time consuming jobs are suitable for execution in desktop grid with high performance commodity PCs for its lower cost and high management ability. In this paper, a framework of parallel remote sensing image interpretation in desktop grid is proposed. The framework consists of modules such as job partitioning and scheduling, load balancing, communication, and image processing. We also provided an implementation based on java multi threaded programming. The computation results on real application of soil moisture estimation workload show that the average speedup is 6.1 in a 9-node heterogeneous desktop grid environment and failure rate of jobs is less than 5.6%.

With the growth of hardware and software resources, the management of virtual machine system is becoming more and more difficult. It has become a very difficult problem that how to schedule the system resource in real time and improve the service performance of resource in a multiple virtual machine system. In order to solve this problem, the authors propose a real-time scheduling mechanism of resource for multiple virtual machine system. In the real-time scheduling mechanism of resource, the authors first describe the architecture of multiple virtual machine system. Then, the authors present a real-time scheduling strategy of resource. In order to justify the feasibility and the availability of this resource scheduling mechanism, a series of experiments have been done. The results show that it is feasible to schedule the system resources for tasks in multiple virtual machine system.

With the scale of computing system increases, power consumption has become the major challenge to system performance, reliability and IT management costs. Specifically, system performance and reliability, described by various Quality of Service(QoS) metrics, cannot be guaranteed if the objective is to minimize the total power consumption solely, despite of the violations of QoS. Various methods have been developed to control power consumption to avoid system failures and thermal emergencies through coarse-grained designs. However, the existing methods can be improved and more power can be saved if fine-grained job level adaptation is integrated into them. In this paper a feedback control based power aware job scheduling algorithm is proposed to minimize power consumption in computing system and to provide QoS guarantees. In the proposed algorithm, jobs are scheduled according to the realtime and historical power consumption as well as the QoS requirements. Simulations and experiments on real multi core computing system show that the power potential of the system can be deeply explored while still providing QoS guarantees and the performance degradation is acceptable. The experiment results also show that fine-grained job-level power aware scheduling can achieve better power/performance balancing between multiple processors or cores than coarse-grained methods.

Problems of Wireless Sensor Networks (WSN）caused in the laboratory are predictable, and easy to resolve. While in the deployment and management phases, a number of factors in the environment raise more problems that are difficult to predict or simulation than in laboratory condition. To effective manage and monitor those problems, an effective management mechanism is needed, which analysis the problems and enables managers configure the networks and deal with exceptions. Wireless sensor networks are application-related systems, different scenarios the network structure and function are quite different. There is no uniform standard of network infrastructure design and implementation of communication protocols, which leading to the present there is no unified network management standards. In this paper, we developed a wireless sensor network visualization management system based on the ZigBee technique, which has data management, data changes and topology visualizing, offline analysis, and the initial network fault detection functions.

BitTorrent(BT)-like P2P traffic which occupy main network bandwidth affect other normal network applications badly. This paper presents a triggered dynamic mechanism for BT-like P2P bandwidth management. According to the variety of utilization percentage of egress router input/output cache, this mechanism could estimate the potential network congestion and be triggered to control the BT-like P2P bandwidth dynamically. This paper puts forward a new way to control BT-like P2P bandwidth by intercepting the massage packets of BT-like P2P. The experiments results verify that the proposed method for BT-like P2P bandwidth management can manage BT-like P2P bandwidth effectively.

How to meet the QoS of the applications and improve resource utilization is an important problem in virtualized environment. In this paper, we propose a Utility based resource allocation policy with QoS constrained in virtualized environment. Firstly, we build a model reflecting the mapping relation between performance metrics and resource allocation through web server benchmarking experiments. Then, we devise a utility function as objective to optimizing the total utility and achieving a reasonable resource allocation. Finally, based on the model and the requirements of the applications QoS, we present an optimized policy for resource allocation in virtualized system. The simulation results show that the utility-based policy is effective to allocate resource from user perspective while improving the resource utilization.

In order to improve the resource utilization of virtual machine and control the resource allocation online effectively, in this paper, we present a grey prediction control model used for dynamic resource allocation in virtual machine as workloads changing. First, we forecast the allocation of virtualized resources by the grey control model. We also adjust the boundary conditions of grey prediction model to make the prediction more accurately. Then, the control theory is used to feedback control resource utilization to obtain desired resource utilization levels by regulating the value of allocation of virtualized resources automatically. Our experimental results show the grey control model is effective in the virtualized resource allocation. The control model and algorithm can be applied to other resource allocation.

Resource management is one of the main issues in Cloud Computing. In order to improve resource utilization of large Data Centers while delivering services with higher QoS to Cloud Clients, a resource allocation strategy based on market (RAS-M) is proposed. Firstly, the architecture and the market model of RAS-M are constructed, in which a QoS-refection utility function is designed according to different resource requirements of the Cloud Client, the equilibrium state of RAS-M is defined and the proof of its optimality is given. Secondly, GA-based price adjusted algorithm is introduced to deal with the problem of achieving the equilibrium state of RAS-M. Finally, RAS-M is implemented upon Xen to reallocate the VM’s weight. Experiments results obtained by setting different parameters show that RAS-M can achieve the equilibrium state approximately, that is, demand and supply is balanced nearly, which validates RAS-M is effective and practicable, and is capable of achieving its goal.

Virtual machine technologies currently receive great interest both in industry and research communities. And it is one of the most important technologies for the coming Cloud Computing. We surveyed the CPU scheduling algorithms in Xen and VMWare systems, and found that both of them use a distinctive VCPUs running queue for each physical CPU, which is referred to Partition Queue Model(PQM) in this paper. As a contrast, a Sharing Queue Model (SQM) of CPU scheduling algorithm is proposed. The simulation experiments results show that the Sharing Queue Model of CPU scheduling achieves better performance than the Partition Queue Model and the deduction from Queue Theory also confirms the results. Moreover, with the CPU utilization increased, the advantage of Sharing Queue Model over Partition Queue Mode is more evident in response time.

The reliability of wireless sensor networks is affected by faults that may occur due to various reasons. In ZigBee sensor networks, ZigBee specification presents a self-healing process which relies on its tree topology. When a ZigBee node failed, all of the descendants of the fault node should rejoin the network. Instead, we present an efficient scheme for repair itself after node failure that just one or some of the descendants should rejoin the network. It allows a subnet of fault node rejoin the network with minimum message exchanges and, therefore, saves energy. Simulation results show that most of subnet rejoin the network in the first level of sub-tree, and confirm the efficiency of the proposed scheme.

In Wireless Sensor networks (WSNs), most existing routing protocols do not consider a node mobility problem, because nodes in sensor network are generally assumed to be static.The network may get partitioned, due to the mobility of some nodes will cause other nodes to lose their connection with the network. Network partitioning poses significant challenges to the provisioning of continuous data streaming services in WSNs. In this paper, we propose a routing scheme which supports node Mobility and Energy-Efficient based on Directed Diffusion (MEDD) for WSNs. In MEDD, we design a gradient model which considers energy consumption balance and real-time requirement. Based on this, we mainly propose a mechanism which makes node be able to localize the gradient reconfiguration whenever its movement occurs. It ensures the robustness of network transmission. Simulation results show that our proposed method decreases the network overhead and prolongs the lifetime of network efficiently.

In wireless sensor network (WSN), sensor node is limited in energy, thus energy efficiency is an important concern in routing protocol design. And some applications in sensor networks have the requirement of timely delivery, real-time also become needed for routing. Directed diffusion (DD) is a data centric dissemination protocol for sensor networks, but DD cannot support time-sensitive traffic nor perform balance of energy consumption to increase network lifetime. To solve this issue, we design a new kind of gradient mechanism, which considers residual energy of node and the number of hops from the sink to an intermediate node synchronously. It can find a best-effort optimal path in sensor networks for data transfer. Simulation results show that our proposed method achieves more globally energy balancing and lower delay for data transfer than originally DD. It prolongs the lifetime of network efficiently.

Clustering routing protocols have prominent advantages over flat routing protocols in terms of scalability, which is very useful for wireless mesh network with dense nodes distribution. However, clustering schemes will add large extra overhead in order to select cluster-heads and collect neighbor nodes information during the phase of cluster construction. At present, there exist a lot of excellent clustering schemes, and in this paper, we propose different classification criteria according to clustering charateristics. Then, we present a comprehensive review of several representatives, and especially focus on cluster formation mechanism. At last, we sum up with three typical problems we have to seriously consider when analyzing or design a clustering routing protocol.

Different from traditional networks, wireless sensor networks (WSNs) are highly dependent on specific applications and are severely constrained by energy, storage capacity and computing power. To prolong the lifetime of the whole networks, energy awareness is an essential consideration when we design or analyze routing protocols. In this paper, we present a review of recent routing protocols in WSNs and classify them into three categories based on the network structure in WSNs. Then we describe the existing routing protocols and discuss their advantages and disadvantages of each routing algorithm. Finally we conclude this paper with open research issues and challenges.

Dynamic address assignment is a desirable feature for deploying wireless sensor network. Typically, a distributed address assignment mechanism is accomplished by ZigBee alliance, whereas, sensors join a network is unpredictable, it may engender uneven node density, so it is possible that one node exhausts its list of addresses while another node has addresses go unused. Therefore, a preemptive approach is needed for ZigBee addressing mechanism. This paper presents a preemptive distributed address assignment to provide a preemptive scheme for ZigBee addressing mechanism. In addition, we give an autorouting algorithm. Simulation results show that nodes can acquire an address even in high node density area, and the scheme increases the total number of nodes in a sensor network.

Grids provide infrastructures and solutions to solve large scale cooperative problems such as large scale distributed virtual environment simulation, multi-institutional scientific computing and data analysis, etc. In this paper, the key techniques for grid computing based large scale distributed cooperative virtual environment simulation (GDCVES) are discussed and a hierarchical architecture of GDCVES is proposed. The solutions of GDCVES, such as resource management, massive data management, security aware task scheduling, and fault-tolerance are also discussed. To evaluate the feasibility and scalability of GDCVES, a prototype was implemented and the simulation workflow framework is also analyzed.

Distributed Virtual Environments (DVEs) are geographically distributed computing systems which allow multiple users to interact simultaneously in computer-generated, shared virtual environments. DVEs are widely applied in many fields, such as online role playing games, synthesis military simulations, virtual cities, and virtual shopping malls. To support large-scale DVEs with high fidelity and satisfied interactive performance among various distributed clients, massive computing resources, storage resources, and highly efficient distributed server architectures are needed. In this paper, the key techniques of the system design and implementation for large scale Distributed Virtual Environment on the Grid (DVE-G) are discussed and a hierarchical architecture of DVE-G is proposed. Some aspects of DVE-G, such as resource management, massive data management, scene synchronization, and fault-tolerance are also discussed. A work-in-progress DVE-G prototype (e.g., the Virtual Hangzhou Dianzi University tourism system) is provided as a testbed scenario and the present evaluation results show that the architecture of DVE-G is feasible and scales well.

In this paper, we analyze the current clustering algorithms and introduce the cluster-tree network model; then benefiting from the good organization of cluster-tree networks, we propose a novel clustering mechanism that conceptually separate the whole networks into clusters according to several formulas. Then we not only make use of the advantages of cluster routing but avoid the computation and memory usage for forming and maintaining clusters. We also exploit the proposed novel clustering mechanism in well-known AODV routing. Simulation results that our clustering mechanism largely reduces routing overhead and average end-to-end delay, and performs better in terms of packets delivery ratio than AODV routing without logical clusters for cluster-tree networks, which will make the real-time and dense mesh networks more efficient and scalable.

Network delays can cause serious usability problems in real-time collaborative environment. Network resources such as bandwidth, etc. are still the bottleneck in real-time collaborative environment. In addition, collaborative messages in groupware system may have different requirements for network QoS and different network protocols behave distinct performances on reliability and network delay aspects. Thus, it seems unreasonable to use a single protocol to send all interaction data. We did some experiments to investigate the impact on collaborating process which produced by packet size and network QoS requirement of different message type in collaborative graphics editing environment. According to the message characteristic, all messages are divided into several different types and for each type, suitable network protocols are used for exchanging information. Some experiments are made to test the usability of this integrated transmitting model.

In this paper, a Customizable and Dynamic Locking (CDL) scheme is proposed for concurrency control in Internet-based real-time collaborative editors. The idea of dynamic-locking is that: locking mechanism dynamically determines locking set according to locking policies and latest collaborative activities happened in the shared workspace, and pre-locks objects for succeeding editing and preventing from other user’s edit. Dynamic locking is optional: user decides whether and when to use locking mechanism. In the proposed scheme, locking policy is separated from locking mechanism. Locking policies can be customized for different collaboration tasks. Locking scope is dynamically determined according to locking policies and collaborative activities among users. Multiple users can select different policies in the same collaborative session, and change locking policies at different phases of collaboration as well. Protocols and algorithms for locking conflict resolution and consistency maintenance are also presented in this paper.

In virtualization environments, resources are shared across multiple virtual machines(VMs), which results in contentions and even conflicting under heavily loaded or consolidated situations. In order to accommodate as many as service instances while still delivering performance guarantees, resource allocation should be optimized in a just adequate manner such that less resources will be utilized for a specific performance requirement. To achieve this goal, in this paper we propose a try-before-buy approach for allocating contending resources. This approach firstly does a try of minor resource allocation to find the performance feedback and search for the optimal amount of resource that should be allocated to the target virtual machine. This approach does not require a highly accurate performance model in a virtualized system where workloads usually change frequently with time in some intervals. Experiments on a Xen based virtualized environment are conducted and evaluated for its effectiveness. The results show that the proposed approach utilizes less CPU and memory resources to achieve the same performance goals compared to default Xen configuration with over-provisioning.