Scheduling distributed multiway spatial join queries: optimization models and algorithms

Multiway spatial joins are a commonly occurring and fundamental type of query for data processing. This article presents models algorithms to schedule this in distributed database systems while attempting strike balance between makespan communication costs. We propose three based on combinatorial optimization methods: the well-known linear relaxation technique rounding solution generated by programming (LP), more sophisticated Lagrangian Relaxation method (LR), as well greedy heuristic (GR) baseline comparison. Our evaluation shows that built using GR consumes, average, 22% processing resources than elaborate constructed via LR method, when scheduling 64 machines. The provided is also, an order magnitude closer optimal compared GR. show Gigabyte-size multiway queries before execution can reduce its time state-of-the-art frameworks do not have capability, significantly amount shuffled network.