The growing popularity of multihoming techniques has motivated the rise of multipath protocols. Multipath TCP (MPTCP), as an extension of TCP, can use multiple paths to deliver data in parallel without influencing any...
详细信息
ISBN:
(纸本)9781509006779
The growing popularity of multihoming techniques has motivated the rise of multipath protocols. Multipath TCP (MPTCP), as an extension of TCP, can use multiple paths to deliver data in parallel without influencing any functionality of TCP. Although applying MPTCP to mobile terminals for data transmission can provide many and attractive benefits, including performance improvement and latency reduction, there is still significant ongoing effort addressing many remaining concerns. One major concern is related to handling buffer blocking. Many researchers have attempted to optimize data scheduling way to mitigate this problem. In this paper, we propose a multiple attribute-aware data scheduling strategy for MPTCP (MPTCP-MA 2 ). The proposed MPTCP-MA 2 solution is invoked to undergo three phases: (i) monitor each path's status information constantly, (ii) use an optimized path sorting algorithm to compare and sort all available paths, (iii) adaptively transmit data packets over multiple paths according to the path sorting result. Furthermore, MPTCP-MA 2 focuses on mitigating buffer blocking as well as boosting the robustness of the data transfer. The simulation result shed light on how MPTCP-MA 2 achieves a little higher throughput than existing solutions.
Real-time systems are shifting from single-core to multi-core processors, on which software must be parallelized to fully utilize the additional computation power. Recently different types of scheduling algorithms and...
详细信息
Real-time systems are shifting from single-core to multi-core processors, on which software must be parallelized to fully utilize the additional computation power. Recently different types of scheduling algorithms and analysis techniques have been proposed for parallel real-time tasks modeled as directed acyclic graphs (DAG). However, this field is still much less mature than traditional real-time scheduling of sequential tasks. In this paper, we study the decomposition-based scheduling for parallel real-time tasks, where a task graph is transferred to a set of independent sporadic tasks. In particular, we proposed a new decomposition strategy that better explores the feature of each task, represented by its structure characteristic value, to improve schedulability. The structure characteristic values do not only provide a clear guidance in task decomposition, but also can be directly used for schedulability tests, as well as to quantify the suboptimality of our scheduling algorithm in terms of capacity augmentation bounds. We conduct comprehensive experiments to evaluate the real-time performance of our proposed scheduling algorithm, against the state-of-the-art scheduling and analysis methods of different types. Experiment results show that our method consistently outperforms all of the previous methods under different parameter settings.
The electric vehicle technology intends to mitigate negative impacts of the energy challenge on the current transportation infrastructure. However, integrating a large number of such vehicles imposes a significant add...
详细信息
ISBN:
(纸本)9781509027545
The electric vehicle technology intends to mitigate negative impacts of the energy challenge on the current transportation infrastructure. However, integrating a large number of such vehicles imposes a significant additional load to the grid and may overload it. This paper proposes a hierarchical event-driven multi-agent system framework for coordinated charging scheduling of electric vehicles. Household agents negotiate temporal travel patterns with substation agents to decide when electric vehicles should charge their batteries. A scalable load scheduling algorithm is proposed to schedule charging process of electric vehicles in real-time regardless of using any forecasting method. It aims to permit as many electric vehicles as possible to operate while keeping their aggregated charging energy consumption below continuous electricity-price-dependent thresholds over time. Simulations confirm that the framework benefits from charging flexibilities, reduces the charging cost, and shaves the grid's peak.
In military mobile ad hoc networks, many applications generate broadcast traffic. Examples of such applications include situation awareness and order dissemination. These types of applications typically require robust...
详细信息
ISBN:
(纸本)9781509037827
In military mobile ad hoc networks, many applications generate broadcast traffic. Examples of such applications include situation awareness and order dissemination. These types of applications typically require robust packet delivery and limited delays. Cooperative broadcasting is a promising technique to handle such requirements for broadcast traffic, especially in highly mobile networks. In this paper we propose an algorithm for dynamically assigning transmission rights in a cooperative broadcast framework. The performance of the proposed algorithm is verified for a demanding traffic model using network simulations, in which the algorithm is compared to an algorithm without traffic adaptivity. The results show that the algorithm successfully handles demanding broadcast traffic scenarios with high capacity even under high mobility and in sparse networks.
This paper proposes a novel real-time scheduling algorithm, named the Event-driven Dynamic-priority scheduling Algorithm (EDSA for short), which is developed based on a non-blocking coding style and a Finite State Mac...
详细信息
ISBN:
(纸本)9781509009855
This paper proposes a novel real-time scheduling algorithm, named the Event-driven Dynamic-priority scheduling Algorithm (EDSA for short), which is developed based on a non-blocking coding style and a Finite State Machine, for an embedded microchip, i.e., a single processor. Generally, with this algorithm, we only need a few lines of codes for a microchip before a real-time system can be generated, without requiring a commercial off-the-shelf (COTS) real-time operating system.
Cloud computing is part of a highly dynamic market with heterogeneous resource providers and varying consumers needs. This influences the provisioning process for highly scalable Software-as-a-service (SaaS) applicati...
详细信息
ISBN:
(纸本)9781509040537
Cloud computing is part of a highly dynamic market with heterogeneous resource providers and varying consumers needs. This influences the provisioning process for highly scalable Software-as-a-service (SaaS) applications, which depends on both resource providers and consumer needs. Indeed, for scaling purposes, SaaS providers need to rent Virtual Machines (VMs) from Infrastructure-as-a-Service (IaaS) providers. Since the objective of SaaS providers is to optimize their profits, it is very important to efficiently decide when processing clients requests to better assign virtual resources and scaling up if needed. Thus, SaaS providers need efficient scheduling strategies to perform such assignment and take adequate profit-aware scheduling decisions. Current scheduling algorithms use take-it-or-leave-it strategy for request evaluation. Considering customer satisfaction as a fixed input parameter, leads to an increased number of rejected requests and consequently loss in profit. In this paper, we propose a negotiation-based scheduling algorithm, which aims to maximize SaaS provider profit and increase user satisfaction, while dealing with dynamic resources and considering customer negotiable needs. Conducted experiments validate our proposal and show that negotiation improves scheduling performance.
Under the federated approach to multiprocessor scheduling, each individual task is either restricted to execute upon a single processor (as in partitioned scheduling), or has exclusive access to all the processors upo...
详细信息
Under the federated approach to multiprocessor scheduling, each individual task is either restricted to execute upon a single processor (as in partitioned scheduling), or has exclusive access to all the processors upon which it may execute. The federated scheduling of a mixed-criticality collection of independent recurrent tasks is studied here. A model is proposed for mixed-criticality recurrent tasks that extends the (previously-proposed) implicit-deadline sporadic DAG tasks model to account for mixed criticalities. A federated scheduling algorithm for systems of such tasks is presented and proved correct, and a quantitative evaluation of its efficacy derived via the widely-used speedup factor metric.
An operational scheduling algorithm for small-lot radio-electronic production is described. The paper shows that an ant colony algorithm is optimal for operation cycle time minimization. Algorithm test run results fro...
详细信息
An operational scheduling algorithm for small-lot radio-electronic production is described. The paper shows that an ant colony algorithm is optimal for operation cycle time minimization. Algorithm test run results from the automated scheduling system implemented at the small-lot radio-electronic manufacture of Murom Radio Works are included.
Task scheduling for multifunctional radars is an activity that has received and still receives a lot of attention. Although the scheduling theory is extensively used in many fields of application, the case of multifun...
详细信息
ISBN:
(纸本)9781509008643
Task scheduling for multifunctional radars is an activity that has received and still receives a lot of attention. Although the scheduling theory is extensively used in many fields of application, the case of multifunctional radar has its own peculiarities for which it is important to have a proper formulation. In this paper we derive a generalized formulation able to manage both soft and hard time constraints activities taking into account the desired priorities. On that basis, we present an on-line algorithm and its simulation results.
Cloud computing is a computing paradigm where platform, scalable resources, data storage and IT services are provided over the Internet. With the very attractive features, Cloud computing becomes very popular in the I...
详细信息
Cloud computing is a computing paradigm where platform, scalable resources, data storage and IT services are provided over the Internet. With the very attractive features, Cloud computing becomes very popular in the IT market, businesses, government organizations and educational departments. Nowadays, task scheduling problem is the current research topic in cloud computing environment. Achieving deadline and reducing cost is the main objectives when we schedule tasks of workflow application on the resources. In this paper, we propose a critical path based workflow scheduling algorithm for cloud computing environment whose main aim is to meet the deadline by finding critical path tasks and reduce overall execution cost of workflow application. We schedule workflow application tasks on resources in such a way that the total execution cost of workflow application is reduced. Experimental result shows that the proposed algorithm minimizes the execution cost of workflow application as compared to the min-min and max-min scheduling algorithm and complete all tasks of workflow application within deadline.
暂无评论