AQD: Online Adaptive Query Dispatcher for HTAP Databases
Summary: AQD combines cost-aware LightGBM with a LinTS-Delta bandit for drift-adaptive row/column dispatch, while Mahalanobis regulation balances CPU/memory. In PolarDB, it cuts latency over 90% versus cost-threshold dispatching and raises HyBench 15% (9% over BRAD). (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Yang Wu (Tsinghua University)
- 2. Tongliang Li (Alibaba)
- 3. Xuanhe Zhou (Shanghai Jiao Tong University)
- 4. Jianying Wang (Alibaba)
- 5. Xinjun Yang (Alibaba)
- 6. Wenchao Zhou (Alibaba)
- 7. Chunxiao Xing (Beijing Institute of Technology; Tsinghua University)
- 8. Yong Zhang (Beijing Institute of Technology; Tsinghua University)
BibTeX Citation
@article{wu_vldb26,
title = {{AQD: Online Adaptive Query Dispatcher for HTAP Databases}},
author = {Wu, Yang and Li, Tongliang and Zhou, Xuanhe and Wang, Jianying and Yang, Xinjun and Zhou, Wenchao and Xing, Chunxiao and Zhang, Yong},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {7},
pages = {1586--1599},
doi = {10.14778/3801059.3801071},
url = {https://doi.org/10.14778/3801059.3801071},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 19 of 19 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,310 | veDB-HTAP: a Highly Integrated, Efficient and Adaptive HTAP System | 2025 | VLDB |
| 2 | 5,288 | PolarDB-IMCI: A Cloud-Native HTAP Database System at Alibaba | 2023 | SIGMOD |
| 3 | 4,399 | Adaptive HTAP through Elastic Resource Scheduling | 2020 | SIGMOD |
| 4 | 5,348 | Adaptive and Robust Query Execution for Lakehouses at Scale | 2024 | VLDB |
| 5 | 11,287 | AQETuner: Reliable Query-level Configuration Tuning for Analytical Query Engines | 2025 | VLDB |
| 6 | 9,301 | Rethink Query Optimization in HTAP Databases | 2023 | SIGMOD |
| 7 | 11,079 | Efficient Approximate Query Processing with Block Sampling | 2025 | CIDR |
| 8 | 8,223 | PilotDB: Database-Agnostic Online Approximate Query Processing with A Priori Error Guarantees | 2025 | SIGMOD |
| 9 | 4,781 | Learned Approximate Query Processing: Make it Light, Accurate and Fast | 2021 | CIDR |
| 10 | 10,982 | A Portable Middleware for Plan-Based Adaptive Query Processing | 2026 | VLDB |