Narrow Results

The deployment of fog computing has not only helped in task offloading for the end-users toward delay-sensitive task provisioning but also reduced the burden for cloud back-end systems to process variable workloads arriving from the user equipment. However, due to the constraints on the resources and computational capabilities of the fog nodes, processing the computational-intensive task within the defined timelines is highly challenging. Also, in this scenario, offloading tasks to the cloud creates a burden on the upload link, resulting in high resource costs and delays in task processing. Existing research studies have considerably attempted to handle the task allocation problem in fog–cloud networks, but the majority of the methods are found to be computationally expensive and incur high resource costs with execution time constraints. The proposed work aims to balance resource costs and time complexity by exploring collaboration among host machines over fog nodes. It introduces the concept of task scheduling and optimal resource allocation using coalition formation methods of game theory and pay-off computation. The work also encourages the formation of coalitions among host machines to handle variable traffic efficiently. Experimental results show that the proposed approach for task scheduling and optimal resource allocation in fog computing outperforms the existing system by 56.71% in task processing time, 47.56% in unused computing resources, 8.33% in resource cost, and 37.2% in unused storage.

The minimum latency data aggregation schedule is one of the fundamental problems in wireless sensor networks. Most existing works assumed that the transmission ranges of sensor nodes cannot be adjusted. However, sensors with adjustable transmission ranges have advantages in energy saving, reducing transmission interference and latency. In this paper, we study the minimum latency conflict-aware data aggregation scheduling problem with adjustable transmission radii: given locations of sensors along with a base station, all sensors could adjust their transmission radii and each sensor's interference radius is α times of its transmission radius, we try to find a data aggregation schedule in which the data from all sensors can be transmitted to the base station without conflicts, such that the latency is minimized. We first partition the set of all nodes into two parts: the major set and the minor set. Then, we design different scheduling strategies for the two sets, respectively. Finally, we propose an approximation algorithm for the problem and prove the performance ratio of the algorithm is bounded by a nearly constant. Our experimental results evaluate the efficiency of the proposed algorithm.

A wide variety of ways to analyze the end-to-end latency emerges due to the feature of component-based software. The researchers began to see that the latency is more sensitive to the data and control flows than the software architecture. However, for an embedded software, the latency depends upon the hardware heavily. To illuminate the feature clearly, we extend the atomic model of component-based software first. A way to specify the flows involved is further developed to identify the end-to-end latency. What is more, a novel methodology that bridges the gap between a constraint on latency and an execution platform is proposed for the embedded software. By constructing a hierarchical architecture, it is available to consider the methodology as a decision problem where the satisfiability module theory (SMT) can be applied. Experimental results demonstrate how the latency analysis conducts with the proposed model and methodology for the complex software architecture.

In recent times, many MAC protocols were implemented for boosting and improving energy efficiency (EE) in WSNs. Moreover, the cooperative MIMO method is found to be much capable of enhancing the EE of WSNs if configured properly. This paper intends to propose cross-layer design for multihop virtual MIMO system to enhance the end-to-end (ETE) reliability, EE, and QoS of the adopted WSN. The protocol is set here to focus on the energy utilization for transmission of data packets by optimal selection of transmission constraints for each node of the network. Moreover, the protocol’s ETE latency and throughput are also modeled as the dependent variables of BER performance of every link. To discover the improved BER criteria of each link that meets the ETE QoS requirement in reduced energy utilization, this paper employs a new hybrid optimization algorithm named Lion Mutated Dragonfly Algorithm (LM–DA) that is a hybrid variant of both Lion Algorithm (LA) and Dragonfly Algorithm (DA). Finally, the performance of the adopted scheme is validated over other state-of-the-art models. The results state that the energy consumed by the adopted LM–DA approach is about 2.65%, 1.77%, and 1.77% reduced over LA, PSO, and DA schemes, respectively.

In IEEE 802.11 based WLAN system; the mobile nodes (MN) are connected through access points (APs). During mobility a MN leaves one AP and is associated to new APs, A handoff process will occur. To provide a better seamless connectivity, Handoff process latency should be very small. Handoff latency is a combination of scanning, re authentication and reassociation latency. Reauthentication latency is major contributing factor that affects the performance of handoff and increase the handoff latency. In this paper we present a novel approach for reducing the Reauthentication latency, and network overhead. For reducing the re-authentication latency we apply pre-authentication mechanism which is preceded by the mobility prediction to consider the user mobility behavior as the contributing factor in the pre-authentication. With the help of mobility predication the central server sends a pre authentication key to the APs and also sends the Ids of AP to the MN and MN store into their buffer. The simulation results show a good factor of improvement over the latency values in WLAN environment.