A computational grid is a hardware and software infrastructure that provides consistent, dependable, pervasive and expensive access to high-end computational capabilities in a multi-institutional virtual organization. Computational grids provide computing power needed for execution of tasks. Scheduling the task in computing grid is an important problem. To select and assign the best resources for task, we need a good scheduling algorithm in grids. As grids typically consist of strongly varying and geographically distributed resources, choosing a fault-tolerant computational resource is an important issue. The main scheduling strategy of most fault-tolerant scheduling algorithms depends on the response time and fault indicator when selecting a resource to execute a task. In this paper, a scheduling algorithm is proposed to select the resource, which depends on a new factor called Scheduling Success indicator (SSI). This factor consists of the response time, success rate and the predicted Experience of grid resources. Whenever a grid scheduler has tasks to schedule on grid resources, it uses the Scheduling Success indicator to generate the scheduling decisions. The main scheduling strategy of the Fault-tolerant algorithm is to select resources that have lowest tendency to fail and having more experience in task execution. Extensive experiment simulations are conducted to quantify the performance of the proposed algorithm on GridSim. GridSim is a Java based discrete-event Grid simulation toolkit. Experiments have shown that the proposed algorithm can considerably improve grid performance in terms of throughput, failure tendency and worth.

No abstract

Cloud computing helps in providing the applications with a few number of resources that are used to unload the tasks. But there are certain applications like coordinated lane change assistance which are helpful in cars that connects to internet has strict time constraints, and it may not be possible to get the job done just by unloading the tasks to the cloud. Fog computing helps in reducing the latency i.e the computation is now done in local fog servers instead of remote datacentres and these fog servers are connected to the nearby distance to clients. To achieve better timing performance in fog computing load balancing in these fog servers is to be performed in an efficient manner.The challenges in the proposed application includes the number of tasks are high, client mobility and heterogeneous nature of fog servers. We use mobility patterns of connected cars and load balancing is done periodically among fog servers. The task model presented here in this paper solves scheduling problem and this is done at the server level and not on the device level. And at last, we present an optimization problem formulation for balancing the load and for reducing the misses in deadline, also the time required for running the task in these cars will be minimized with the help of fog computing. It also performs better than some common algorithms such as active monitoring, weighted round robin and throttled load balancer.

Human validation of computer vision systems increase their operatingcosts and limits their scale. Automated failure detection canmitigate these constraints and is thus of great importance to thecomputer vision industry. Here, we apply a deep neural networkto detect computer vision failures on vehicle detection tasks. Theproposed model is a convolution neural network that estimates theoutput quality of a vehicle detector. We train the network to learnto estimate a pixel-level F1 score between the vehicle detector andhuman annotated data. The model generalizes well to testing data,providing a mechanism for identifying detection failures.

No abstract