دانلود مقاله ISI انگلیسی شماره 25736
عنوان فارسی مقاله

یک روش برنامه ریزی پویا: بهبود عملکرد شبکه های بی سیم

کد مقاله سال انتشار مقاله انگلیسی ترجمه فارسی تعداد کلمات
25736 2011 13 صفحه PDF سفارش دهید محاسبه نشده
خرید مقاله
پس از پرداخت، فوراً می توانید مقاله را دانلود فرمایید.
عنوان انگلیسی
A dynamic programming approach: Improving the performance of wireless networks
منبع

Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)

Journal : Journal of Parallel and Distributed Computing, Volume 71, Issue 11, November 2011, Pages 1447–1459

کلمات کلیدی
( - (شبکه های حسگر بی سیم ( - برنامه ریزی پویا ( - متعادل کردن بار - ابر رایانه -
پیش نمایش مقاله
پیش نمایش مقاله  یک روش برنامه ریزی پویا: بهبود عملکرد شبکه های بی سیم

چکیده انگلیسی

Traditional wireless networks focus on transparent data transmission where the data are processed at either the source or destination nodes. In contrast, the proposed approach aims at distributing data processing among the nodes in the network thus providing a higher processing capability than a single device. Moreover, energy consumption is balanced in the proposed scheme since the energy intensive processing will be distributed among the nodes. The performance of a wireless network is dependent on a number of factors including the available energy, energy–efficiency, data processing delay, transmission delay, routing decisions, security architecture etc. Typical existing distributed processing schemes have a fixed node or node type assigned to the processing at the design phase, for example a cluster head in wireless sensor networks aggregating the data. In contrast, the proposed approach aims to virtualize the processing, energy, and communication resources of the entire heterogeneous network and dynamically distribute processing steps along the communication path while optimizing performance. Moreover, the security of the communication is considered an important factor in the decision to either process or forward the data. Overall, the proposed scheme creates a wireless “computing cloud” where the processing tasks are dynamically assigned to the nodes using the Dynamic Programming (DP) methodology. The processing and transmission decisions are analytically derived from network models in order to optimize the utilization of the network resources including: available energy, processing capacity, security overhead, bandwidth etc. The proposed DP-based scheme is mathematically derived thus guaranteeing performance. Moreover, the scheme is verified through network simulations. Highlights ► A model which evaluates tradeoff between execution and delegation of tasks. ► Developed a DP-based solution to evaluate tradeoff between user defined metrics. ► Mathematical analysis that guarantees the performance of generic wireless networks.

مقدمه انگلیسی

Wireless networks have many military and civilian applications including battlefield surveillance, border and fire monitoring, traffic control, and healthcare and body sensor networks. Designing a durable sensor network has always been a challenge due to the limited energy available in battery-operated devices. Moreover, in sensor networks a typical application has to extract information from the raw data. Typically, the information extraction is tasked to the sink node in order to conserve the energy of sensors. However, sensor devices are equipped with ever more capable processors. Additionally, the amount of extracted information is typically much smaller than the amount of raw sensor data. The energy consumption and the communication delay are proportional to the amount of transmitted data. Hence, the network-wide energy consumption and end-to-end delay can potentially be reduced when the data are processed early at the routing path. The proposed cross-layer optimization will dynamically optimize the performance of the networks in different areas: network routing [20], avoiding energy holes [8], prolonging network lifetime [15] and others. A number of related algorithms have been proposed for different application environments. In hierarchical-based algorithms [17] and [9], nodes are partitioned into different levels such that sensing data is transferred from lower to higher, up to the users. In wireless sensor networks, applications will have different requirements for the data collection and dissemination process. For example, a network metric can be short packet delay for time-critical applications. In contrast, better energy utilization is preferred in case of battery operated, long-term monitoring applications. Hence, it is essential that communication protocols are aware of application demands and adopt themselves according to application requirements. The aim of the proposed model is the integration of application requirements in terms of delay associated, security overhead, energy consumption and nodes’ capabilities and the design of a communication protocol for better functioning of the network in terms of user requirements. The proposed scheme improves the performance of the network by distributing the load within the network similar to cloud computing methodology. Cloud computing cost-analysis is utilization-oriented and adapts to changing application demand, topology, and resource availability. In a traditional computing cloud, multiple applications are hosted on a common set of servers, which allows the consolidation of application workloads on a smaller number of servers for better utilization. The clouds virtualize resources for example using virtual machines (VM) in order to efficiently distribute and quickly process multiple user requests. For example, a user starts a processing-intensive image manipulation application. Instead of spending hours on a local desktop or transferring to a specific super-computer, the application is inserted into a VM and sent to the cloud to be executed. The user’s VM is dynamically assigned and if necessary distributed on physical machines inside the cluster without the user’s intervention or awareness [1]. The computing cloud is capable of efficient load balancing and optimization of delay and energy-efficiency beyond what a manual operation would accomplish. A task scheduling problem in the case of cloud computing deals with meeting users’ job QoS requirements and using cloud resources effectively in an economic manner. However, nodes in decentralized wireless networks have to collaborate among themselves to broadcast requests and route data. For example, typical battery-operated sensor nodes have a limited energy supply that limits their lifetime. Hence, such a network has to optimize the available resources in order to increase its lifetime, energy-efficiency, response time, etc. The proposed approach employs the concept of virtualization of resources and virtual machines (VMs) to manage the processing tasks. However, in contrast to traditional, wired computing clouds the wireless variant requires consideration also for communication costs and overhead. The mobile VM calculates the percentage of the task to be completed at a particular node based on the resources available in the network. This methodology applied to sensor networks manages the distribution of tasks among the mobile nodes while reducing the transmission and processing oriented costs including energy and delay metrics. For example, a node can make a decision to either • Execute the entire set of tasks by itself and relay the final result (typically smaller than the input data set). • Perform some tasks and transfer partial results to the next available neighbor for further processing, or • Only transfer the data (and tasks) to the next node. The proposed scheme also examines how a security overhead impacts the performance of the network in terms of energy efficiency, end-to-end delay, task distribution, network lifetime, etc. In order to minimize the security overhead an MKE [14] scheme is adopted for security. The MKE thwarts CPA attacks in wireless networks while reducing energy consumption. Overall, the proposed scheme aims to improve the performance of wireless network considering various metrics that impact the performance. The proposed scheme is studied with respect to various cost optimization metrics using either single or multiple metrics. For example, focusing on equal energy consumption distribution will affect the delay associated with the processing of a task and vice versa. The scheme is also analyzed in terms of various routing patterns of heterogeneous nodes and mobile nodes in the network. In this paper, a mathematical model based on dynamic programming [2] is used to solve the issue of multi-stage decision-making. The decision to perform the task at a particular stage or node of the network depends on various factors as described. Using DPDP methodology the multi stage decision problem is translated to multiple single stage problems that are correlative and solved accordingly.

نتیجه گیری انگلیسی

The proposed DPDP based communication and task-scheduling scheme improves the performance of wireless networks against regular WSN scenarios. It has reduced the energy consumption costs for the data transmission as well as the processing cost by 65% and practically doubled the network lifetime. Also, it reduced the energy inequalities among the network thus improving utilization of the network resources. Additionally, the communication cost in terms of delay is reduced since fewer bits have to be transmitted. Consequently, the communication bottlenecks have less effect on the quality of service. The proposed DPDP based communication model reduces the costs in terms of energy consumption and the overhead from the implementation of the security scheme. The proposed scheme helps in improving the performance of the networks from most of the network metrics’ perspective and it is not focused on improving a performance of the network from a single metric perspective.

خرید مقاله
پس از پرداخت، فوراً می توانید مقاله را دانلود فرمایید.