Partition histograms based on moving averages

Data streams are data in infinite, continuous, arriving at fast rate and in large amount. Histograms have been widely used to capture attribute value distribution statistics for query optimizers. Recently, histograms have also been considered as a way to produce quick approximate answers to decision support queries. We are interested in an efficient algorithm for choosing the bucket boundaries in a way that either minimizes the estimation error for a given amount of space (number of buckets), or, minimizes the space needed for a given upper bound on the error. In this paper, we present algorithms for computing optimal bucket boundaries is optimal than dynamic programming algorithm. We introduce the concept of moving average to compute SSE (Sum Squared Error). This algorithm can help to split the bucket, which result in more quickly generating the histogram and less storage. Through experiments, we show that the MPA algorithm is better than DPA algorithm.