No abstract

No abstract

In this work, we deal with the problem of minimizing the load redistribution cost in parallel implementations for cluster architectures. Due to the importance of the network latency in this kind of systems, the redistribution cost is primarily depending on the maximum number of messages sent or received by a processor. The load redistribution is a NP-hard problem similar to the Multiple Knapsack problems. Three heuristics are proposed to solve the problem in a global context, and a comparison is made to emphasize their characteristics. In a parallel application, it is important to decide whether it is efficient or not to carry out the workload redistribution. This decision is taken comparing the cost of the load imbalance and the communication overheads associated with the load balancing heuristic. Depending on these costs, a theoretic value of imbalance from which the redistribution is profitable is defined. Experimental results show the accurancy of our proposals.

Mobile technology has been under constant growth in last years. The emergence of smartphones has encouraged the development of a wide variety of mobile applications. Some of them are related to daily tasks. In this regard, we propose the Shop&Go mobile application which allows a supermarket customer to do the shopping covering the shortest distance 1) . An analysis of the routing problem applied to an efficient way of doing the shopping is made. A map with items distribution and distances between products is provided by the supermarket. Based on these information two heuristics have been proposed to do the shopping following the optimum path. Both heuristics have been compared, proving that neither of them can be defined as the best one in all cases. The products in the shopping list determine which is the best solution for each case. Therefore, both algorithms have been included in our application, letting the user decide which route he/she wants to follow. Shop&Go has also other functionalities which are extensively described in the paper. Simulations over an HTC Desire mobile are shown to demonstrate the proper tool operation. Finally, a study of consumer acceptance has been made to know its possibilities of success in the mobile technology market.

No abstract