Solving Dynamic Programming Problems on a Computational Grid (original) (raw)

The standard DP (dynamic programming) algorithms are limited by the substantial computational demands they put on contemporary serial computers. In this work, the theory behind the solution to serial monadic dynamic programming problems highlights the theory and application of parallel dynamic programming on a general-purpose architecture (cluster or network of workstations). A simple and well-known technique, message passing, is considered.

In this paper we propose two price-based job allocation schemes for computational grids. A grid system tries to solve problems submitted by various grid users by allocating the jobs to the computing resources governed by different resource owners. The prices charged by these owners are obtained based on a pricing model using a bargaining game theory framework. These prices are then used for job allocation. We present the grid system model and formulate the two schemes as a constraint minimization problem and as a non-cooperative game respectively. The objective of these schemes is to minimize the cost for the grid users. We present algorithms to compute the optimal load (job) fractions to allocate jobs to the computers. Finally, the two schemes are compared under simulations with various system loads and configurations and conclusions are drawn.