ISP Constraints: Balancing Storage Budgets and Query Performance

Table of Links

Abstract and 1. Introduction

2. Related Works

   2.1 Traditional Index Selection Approaches

   2.2 RL-based Index Selection Approaches

3. Index Selection Problem

4. Methodology

   4.1 Formulation of the DRL Problem

   4.2 Instance-Aware Deep Reinforcement Learning for Efficient Index Selection

5. System Framework of IA2

   5.1 Preprocessing Phase

   5.2 RL Training and Application Phase

6. Experiments

   6.1 Experimental Setting

   6.2 Experimental Results

   6.3 End-to-End Performance Comparison

   6.4 Key Insights

7. Conclusion and Future Work, and References

3 Index Selection Problem

The Index Selection Problem (ISP) is formalized as the task of identifying an optimal index set, 𝐼∗ , from a set of candidate indexes, 𝐼, for a database, 𝐷, and its workload, 𝑊 , to minimize the execution cost, Cost(𝑊,𝐼), subject to constraints, 𝐶, such as a storage budget. Formally, this can be represented as:

where 𝐶(𝐼) denotes the cost associated with the index configuration 𝐼, including considerations such as storage, and 𝐶max represents the maximum allowable cost under the constraints.