Application of neural networks in predictive prefetching

An important issue that affects response time performance in current systems is the I/O involved in moving objects from slow secondary storage device to main memory. A promising way to tackle this problem is to use prefetching, in which we predict the user´s next page requests and get those pages into memory in the background. Current systems perform limited prefetching by locality of reference. A novel idea of using neural networks for predictive prefetching is discussed here.