Adaptive Power Management for Mobile Agent-Based Information Retrieval

Jiao, Yu; Hurson, Ali R.

doi:10.1109/aina.2005.77

Cited by 7 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several applications have shown clear evidence of benefiting from the use of MAs [26], including e-commerce and m-commerce trading [33], distributed information retrieval [19], network awareness [2], network & systems management [13,31,32], etc. Network-robust applications are also of great interest in military situations today.…”

Section: Mobile Agentsmentioning

confidence: 99%

An approach for near-optimal distributed data fusion in wireless sensor networks

et al. 2009

View full text Add to dashboard Cite

In wireless sensor networks (WSNs), a lot of sensory traffic with redundancy is produced due to massive node density and their diverse placement. This causes the decline of scarce network resources such as bandwidth and energy, thus decreasing the lifetime of sensor network. Recently, the mobile agent (MA) paradigm has been proposed as a solution to overcome these problems. The MA approach accounts for performing data processing and making data aggregation decisions at nodes rather than bring data back to a central processor (sink). Using this approach, redundant sensory data is eliminated. In this article, we consider the problem of calculating nearoptimal routes for MAs that incrementally fuse the data as they visit the nodes in a WSN. The order of visited nodes (the agent's itinerary) affects not only the quality but also the overall cost of data fusion. Our proposed heuristic algorithm adapts methods usually applied in network design problems in the specific requirements of sensor networks. It computes an approximate solution to the problem by suggesting an appropriate number of MAs that minimizes the overall data fusion cost and constructs nearoptimal itineraries for each of them. The performance gain of our algorithm over alternative approaches both in terms of cost and task completion latency is demonstrated by a quantitative evaluation and also in simulated environments through a Java-based tool.

show abstract

Section: Mobile Agentsmentioning

confidence: 99%

An approach for near-optimal distributed data fusion in wireless sensor networks

et al. 2009

View full text Add to dashboard Cite

show abstract

“…Although the role of MAs in distributed computing is still being debated mainly because security concerns [21], several applications have shown clear evidence of benefiting from the use of MAs [22], including e-commerce and m-commerce trading [23], distributed information retrieval [24], network awareness [25], network and systems management [21,26,27], and so forth. Network-robust applications are also of great interest in military situations today.…”

Section: Mobile Agentsmentioning

confidence: 99%

CBID: A Scalable Method for Distributed Data Aggregation in WSNs

Mpitziopoulos

Gavalas

Konstantopoulos

et al. 2010

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Mobile Agent (MA) technology has been recently proposed in Wireless Sensors Networks (WSNs) literature to answer the scalability problem of client/server model in data fusion applications. Herein we present CBID, a novel algorithm that calculates near-optimal routes for MAs that incrementally fuse the data as they visit the Sensor Nodes (SNs) while also enabling fast updates on the designed itineraries upon changes of network topology. CBID dispatches in parallel a number of MAs that sequentially visit sensor nodes arranged in tree structures and upon visiting an SN with two or more child SNs, the MAs (master MAs) clone of themselves with each clone (slave MA) visiting a tree branch. When all slave MAs return to that SN, they deliver their collected data to the master MA and are then disposed of. This results in a significant reduction of the overall energy expenditure and response time. Simulation results prove the high effectiveness of CBID in data fusion tasks compared to other alternative algorithms.

show abstract

“…Finally at the receiver, the System Prototype decodes the transmitted video data based on generated packet losses and frame arrival times from NS2, and evaluates the energy consumption for decoding (Dec EC) and the video quality measured in PSNR (Peak Signal to Noise Ratio) in Analysis 3. Thus Analysis 3 captures the CPU energy for decoding at the receiver (Power consumption numbers for CPU [6] and WNI [8] are configured as shown in the tables on the right side of Fig. 4 combining Analysis 1, Analysis 2 and Analysis 3, we are able to measure the entire end-to-end energy savings for our proposed scheme.…”

Section: Methodsmentioning

confidence: 99%

Error-Exploiting Video Encoder to Extend Energy/QoS Tradeoffs for Mobile Embedded Systems

Lee

Kim

Dutt

et al.

Distributed Embedded Systems: Design, Middleware and Resources

View full text Add to dashboard Cite

As previously referred, when the number of data elements to be sorted surpasses the number of elements sorted by each execution of the sorting unit, a softwaremerge algorithm is used. In this later case, a degradation in the speed-ups is present (the inflexion points in the chart shown in Figure 8). Note that the software-merge adds a computational time complexity O(n · log n), being n the number of elements to sort. Figure 9 gives estimations for sorting a set of 16K elements with three sorting units. We exploit the case of having support for simultaneous load/store operations to communicate data to the sorting units. For the estimations, we use two completely parallel Sorting Networks (SN-II), able to directly sort 16 and 32 elements. The second machine is a 1024-element Insertion Sorting Unit. The third machine is a FIFO-based Merge Sorting Unit able to output 512 sorted elements using two sets of 256 elements sorted by an Insertion Sorting Unit. The results take into account typical DMA load/store latencies, acquired from experimental measurements. For calculating the execution time when sorting 16K elements, the overhead of a software-merge has been included.These results indicate that the Sorting Network SN-II with size 16 (SN II 16) achieves worse results than software quicksort, even with 16 simultaneous load/store operations. The SN-II with size 32 (SN II 32) surpasses quicksort when considering more than 2 simultaneous load/store operations. The Insertion Sort Unit with size 1024 (Insertion 1024) achieves for all the cases better performance than quicksort, but since the data is fed to the sorting unit sequentially no gain is obtained by performing simultaneous load/store operations. The highest speed-ups are obtained by the Insertion 256 + FIFO-based merge sorting unit with size 512 (Insertion 256 + FIFO 512). In this case, the speed-up increases between 1 to 2 simultaneous load/store operations, as is explained by the fact that this particular unit uses 2 input FIFOs. Sorting Units for FPGA-Based Embedded Systems 21 where T (n) is the total time to sort n elements, considering that n is the maximum number of elements to sort directly on the sorting unit, k represents the simultaneous load/store operations, t load the time to load data from the memory, t store the time to store data in the memory, and t sort unit(n) the time required by the sorting unit to sort n elements, considering the data are been loadedwhere T so f tware merge(N) is the total time to sort N, elements using software merge, and p = log(N). For larges sorts typically the number N is much greater than n. ConclusionsWe describe in this paper three different approaches for hardware sorting units. The sorting units proposed have been coupled to a microprocessor in an FPGAbased embedded system. The sorting units explore different architectures: sorting networks with one or two levels, an insertion sorting array, and a particular sorting unit based on FIFOs. We evaluated these units by coupling them to the peripheral on-chip bus in a sys...

show abstract

Adaptive Power Management for Mobile Agent-Based Information Retrieval

Cited by 7 publications

References 6 publications

An approach for near-optimal distributed data fusion in wireless sensor networks

An approach for near-optimal distributed data fusion in wireless sensor networks

CBID: A Scalable Method for Distributed Data Aggregation in WSNs

Error-Exploiting Video Encoder to Extend Energy/QoS Tradeoffs for Mobile Embedded Systems

Contact Info

Product

Resources

About