Batch Query Memory Prediction Using Deep Query Template Representations

This thesis introduces a novel approach called LearnedWMP for predicting the memory cost demand of a batch of queries in a database workload. Existing techniques focus on estimating the resource demand of individual queries, failing to capture the net resource demand of a workload. LearnedWMP leverages the query plan and groups queries with similar characteristics into pre-built templates. A histogram representation of these templates is generated for the workload, and a regressor predicts the resource demand, specifically memory cost, based on this histogram. Experimental results using three database benchmarks demonstrate a 47.6% improvement in memory estimation compared to the state-of-the-art. Additionally, the approach outperforms various machine and deep learning techniques for individual query prediction, offering a 3x to 10x faster and at least 50% smaller model size.