Loosely connected distributedcomputing systems present a changing environment to the programs that they execute. Dynamic load balancing (DLB) algorithms are employed to address the problem of relocating tasks when pa...
详细信息
ISBN:
(纸本)9783642326509
Loosely connected distributedcomputing systems present a changing environment to the programs that they execute. Dynamic load balancing (DLB) algorithms are employed to address the problem of relocating tasks when parts of a distributedcomputing system become unavailable while other parts become idle. this paper presents a novel DLB algorithm based on cemetery formation in ant colonies. the algorithm builds on previous work to formulate ant-inspired DLB algorithms that aim to reduce the time needed to complete the parallel execution of multiple, independent tasks, where resources as well as tasks are diverse with respect to their performances and durations, respectively. the new algorithm is compared with its predecessors, based on division of labour in ant colonies, and pure, opportunistic load balancing, established as the baseline.
Every night, a large number of idle smartphones are plugged into a power source for recharging the battery. Given the increasing computing capabilities of smartphones, these idle phones constitute a sizeable computing...
详细信息
Higher education resources are considered in this paper as a complex heterogeneous hierarchical system. the formal mathematical models for resources evaluation are suggested. the analysis of information and communicat...
详细信息
Higher education resources are considered in this paper as a complex heterogeneous hierarchical system. the formal mathematical models for resources evaluation are suggested. the analysis of information and communication technologies applied in higher education establishments is conducted. the necessity of distributed hardware and software infrastructure for data storage and processing in the evaluation activities is shown and substantiated. the distributed data storage and processing architecture is presented.
One of the major drawbacks of computing with graphics adapters is the limited available memory for relevant problem sizes. To overcome this limitation for the ViennaCL library, we investigate a partitioning approach f...
详细信息
Recommender systems are mechanisms that filter information and predict a user's preference to an item. parallel implementations of recommender systems improve scalability issues and can be applied to internet-base...
详细信息
In this paper we present PCJ - a new library for parallel computations in Java inspired by the partitioned global address space approach. We present design details together withthe examples of usage for basic operati...
详细信息
Wireless interference does not necessarily result in the lost of all the information of the desired signal. In this paper, we study the signature allocation in wireless networks by exploiting the retained signal featu...
详细信息
ISBN:
(纸本)9781612846835
Wireless interference does not necessarily result in the lost of all the information of the desired signal. In this paper, we study the signature allocation in wireless networks by exploiting the retained signal feature under interference. the commonly used node signature includes MAC address and PN sequence. However, both of them take a lot of time to identify the signature when the network scale is large. We propose a novel signature allocation method based on a multi-hash policy, using a set of hash functions and a mapping-table to identify the signature. the proposed method decreases significantly boththe signature identification complexity and the signature conflict probability. We implement the algorithm in GNU Radio and evaluate the performance in a testbed of three USRP nodes. the result shows that, under typical settings, multi-hash policy reduces the time cost by a factor of 100x in large scale wireless networks with very low collision probability.
New applications are motivating and informing the design of sensor/actuator networks, and, more broadly, research in cyber-physical systems (CPS). Our knowledge of many physical systems is uncertain, so that sensing a...
详细信息
ISBN:
(纸本)9780769548654;9781467351461
New applications are motivating and informing the design of sensor/actuator networks, and, more broadly, research in cyber-physical systems (CPS). Our knowledge of many physical systems is uncertain, so that sensing and actuation must be mediated by inference of the structure and parameters of physical-system models. One CPS application domain of growing interest is ecological systems, motivated by the need to understand plant survival and growth as a function of genetics, environment, and climate change. For this effort to be successful, we must be able to infer coupled, data-driven predictive models of plant growth dynamics in response to climate drivers that allow incorporation of uncertainty. We are developing an architecture and implementation for precise fine-scale control of irrigation in an array of geographically-distributed outdoor gardens on an elevational gradient of over 1500 m, allowing design of experiments that combine control of temperature and water availability. this paper describes a system architecture and implementation for this class of cyber-eco systems, including sensor/actuator node design, site-level networking, data assimilation, inference, and distributed control. Among its innovations are a modular, parallel-processing node hardware design allowing real-time processing and heterogeneous nodes, energy-aware hardware/software design, and a networking protocol that builds in trade-offs between energy conservation and latency. throughout, we emphasize the changes in system architecture required as missions evolve from sensing-only to sensing, inference, and control. We also describe our developmental implementation of the architecture and its planned deployment. Future extensions will likely add negative control of precipitation using active rain-out shelters and additional plant-level control of air or soil temperature.
作者：
Best, EikeDarondeau, PhilippeParallel Systems
Department of Computing Science Carl von Ossietzky Universität Oldenburg Oldenburg D-26111 Germany INRIA
Centre Rennes - Bretagne Atlantique Campus de Beaulieu Rennes Cedex F-35042 France
A Petri net is distributed if, given an allocation of transitions to (geographical) locations, no two transitions at different locations share a common input place. A system is distributable if there is some distribut...
详细信息
暂无评论