Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (7): 2139-2151.DOI: 10.11772/j.issn.1001-9081.2025070884
• Data science and technology • Previous Articles
Jintao GAO(
), Zhiyuan HU, Lulu JIANG
Received:2025-08-04
Revised:2025-10-03
Accepted:2025-10-09
Online:2025-11-05
Published:2026-07-10
Contact:
Jintao GAO
About author:HU Zhiyuan, born in 2001, M. S. His research interests include AI for database, causal discovery.Supported by:通讯作者:
高锦涛
作者简介:胡志远(2001—),男,山东日照人,硕士,主要研究方向:智能数据库、因果发现基金资助:CLC Number:
Jintao GAO, Zhiyuan HU, Lulu JIANG. Parameter tuning method based on Monte Carlo tree search[J]. Journal of Computer Applications, 2026, 46(7): 2139-2151.
高锦涛, 胡志远, 姜璐璐. 基于蒙特卡洛树搜索的参数调优方法[J]. 《计算机应用》唯一官方网站, 2026, 46(7): 2139-2151.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2025070884
| 类别 | 旋钮 | 旋钮描述 | 示例 |
|---|---|---|---|
| Server setting parameters | Max_connections | 设置最大并发连接数 | default:100 value:1 767 |
| Deadlock_timeout | 设置在检查死锁之前等待锁定的时间 | default:1 000 value:1 474 | |
| Memory and performance parameters | Shared_buffers | 设置服务器使用的共享内存缓冲区数量 | default:1 024 value:988 856 |
| Work_mem | 设置查询工作区使用的最大内存容量 | default:4 096 value:240 263 | |
| Query optimization parameters | Random_page_cost | 设置计划器对非连续获取磁盘页面成本的估计值 | default:4.0 value:6.055 9 |
| Seq_page_cost | 设置计划编制器对按顺序提取磁盘页面成本的估计值 | default:1.0 value:1.615 0 |
Tab. 1 Examples of parameter tuning in PostgreSQL
| 类别 | 旋钮 | 旋钮描述 | 示例 |
|---|---|---|---|
| Server setting parameters | Max_connections | 设置最大并发连接数 | default:100 value:1 767 |
| Deadlock_timeout | 设置在检查死锁之前等待锁定的时间 | default:1 000 value:1 474 | |
| Memory and performance parameters | Shared_buffers | 设置服务器使用的共享内存缓冲区数量 | default:1 024 value:988 856 |
| Work_mem | 设置查询工作区使用的最大内存容量 | default:4 096 value:240 263 | |
| Query optimization parameters | Random_page_cost | 设置计划器对非连续获取磁盘页面成本的估计值 | default:4.0 value:6.055 9 |
| Seq_page_cost | 设置计划编制器对按顺序提取磁盘页面成本的估计值 | default:1.0 value:1.615 0 |
| 符号 | 说明 | 符号 | 说明 |
|---|---|---|---|
| MCTS | 蒙特卡洛树搜索 | Θi | 参数 |
| BO | 贝叶斯优化 | LHS | 拉丁超立方采样 |
| UCB | 置信区间上界 | SVM | 支持向量机 |
Tab. 2 Explanation of symbols
| 符号 | 说明 | 符号 | 说明 |
|---|---|---|---|
| MCTS | 蒙特卡洛树搜索 | Θi | 参数 |
| BO | 贝叶斯优化 | LHS | 拉丁超立方采样 |
| UCB | 置信区间上界 | SVM | 支持向量机 |
| 指标 | 方法 | YCSB-A | YCSB-B | ||||
|---|---|---|---|---|---|---|---|
| DDPG | SMAC | MTune | DDPG | SMAC | MTune | ||
| 延迟率 | HeSBO-8 | 1.308 426 | 3.846 227 | 0.140 693 | 6.444 842 | 6.610 277 | 0.137 257 |
| HeSBO-16 | 0.197 317 | 0.740 762 | 0.115 921 | 0.204 861 | 0.178 901 | 0.147 307 | |
| HeSBO-24 | 5.463 713 | 5.463 713 | 0.177 297 | 13.664 730 | 2.138 713 | 0.128 634 | |
| 吞吐量 | HeSBO-8 | 47 626.16 | 69 211.06 | 68 485.75 | 70 844.92 | 63 808.64 | 73 138.44 |
| HeSBO-16 | 62 130.96 | 49 175.10 | 71 879.62 | 62 327.85 | 65 151.40 | 67 083.75 | |
| HeSBO-24 | 51 316.63 | 68 176.46 | 57 219.22 | 42 816.90 | 70 757.48 | 78 254.81 | |
| 系统开销 | HeSBO-8 | 61.926 73 | 62.560 89 | 62.584 86 | 62.454 50 | 73.663 17 | 64.820 10 |
| HeSBO-16 | 62.064 48 | 64.808 57 | 61.362 43 | 61.885 66 | 83.879 25 | 61.055 56 | |
| HeSBO-24 | 63.943 36 | 62.516 86 | 65.089 82 | 63.494 96 | 62.291 31 | 60.299 70 | |
Tab. 3 Comparison of DDPG, SMAC and MTune in throughput, latency rate and system overhead using HeSBO dimensionality reduction on PostgreSQL v13.6
| 指标 | 方法 | YCSB-A | YCSB-B | ||||
|---|---|---|---|---|---|---|---|
| DDPG | SMAC | MTune | DDPG | SMAC | MTune | ||
| 延迟率 | HeSBO-8 | 1.308 426 | 3.846 227 | 0.140 693 | 6.444 842 | 6.610 277 | 0.137 257 |
| HeSBO-16 | 0.197 317 | 0.740 762 | 0.115 921 | 0.204 861 | 0.178 901 | 0.147 307 | |
| HeSBO-24 | 5.463 713 | 5.463 713 | 0.177 297 | 13.664 730 | 2.138 713 | 0.128 634 | |
| 吞吐量 | HeSBO-8 | 47 626.16 | 69 211.06 | 68 485.75 | 70 844.92 | 63 808.64 | 73 138.44 |
| HeSBO-16 | 62 130.96 | 49 175.10 | 71 879.62 | 62 327.85 | 65 151.40 | 67 083.75 | |
| HeSBO-24 | 51 316.63 | 68 176.46 | 57 219.22 | 42 816.90 | 70 757.48 | 78 254.81 | |
| 系统开销 | HeSBO-8 | 61.926 73 | 62.560 89 | 62.584 86 | 62.454 50 | 73.663 17 | 64.820 10 |
| HeSBO-16 | 62.064 48 | 64.808 57 | 61.362 43 | 61.885 66 | 83.879 25 | 61.055 56 | |
| HeSBO-24 | 63.943 36 | 62.516 86 | 65.089 82 | 63.494 96 | 62.291 31 | 60.299 70 | |
| 指标 | 方法 | YCSB-A | YCSB-B | ||||
|---|---|---|---|---|---|---|---|
| DDPG | SMAC | MTune | DDPG | SMAC | MTune | ||
| 延迟率 | HeSBO-8 | 0.141 871 | 0.148 446 | 0.136 960 | 0.142 891 | 0.149 792 | 0.137 307 |
| HeSBO-16 | 0.146 970 | 0.140 851 | 0.136 663 | 0.150 950 | 0.140 762 | 0.137 277 | |
| HeSBO-24 | 0.150 277 | 0.137 653 | 0.137 634 | 0.148 059 | 0.138 287 | 0.136 594 | |
| 吞吐量 | HeSBO-8 | 70 527.17 | 67 555.70 | 73 129.01 | 69 985.88 | 66 893.14 | 72 836.29 |
| HeSBO-16 | 65 655.64 | 71 183.57 | 73 289.79 | 66 280.42 | 71 241.95 | 72 736.71 | |
| HeSBO-24 | 66 612.45 | 72 770.46 | 72 658.08 | 67 625.01 | 72 413.22 | 73 146.50 | |
| 系统开销 | HeSBO-8 | 66.170 64 | 61.081 05 | 61.738 81 | 67.447 52 | 61.277 16 | 60.149 42 |
| HeSBO-16 | 67.527 00 | 60.787 09 | 62.227 36 | 60.315 57 | 60.695 90 | 62.134 58 | |
| HeSBO-24 | 60.314 45 | 61.615 15 | 60.142 19 | 61.443 76 | 61.587 73 | 60.158 28 | |
Tab. 4 Comparison of DDPG, SMAC and MTune in throughput, latency rate and system overhead using HeSBO dimensionality reduction on PostgreSQL v9.6
| 指标 | 方法 | YCSB-A | YCSB-B | ||||
|---|---|---|---|---|---|---|---|
| DDPG | SMAC | MTune | DDPG | SMAC | MTune | ||
| 延迟率 | HeSBO-8 | 0.141 871 | 0.148 446 | 0.136 960 | 0.142 891 | 0.149 792 | 0.137 307 |
| HeSBO-16 | 0.146 970 | 0.140 851 | 0.136 663 | 0.150 950 | 0.140 762 | 0.137 277 | |
| HeSBO-24 | 0.150 277 | 0.137 653 | 0.137 634 | 0.148 059 | 0.138 287 | 0.136 594 | |
| 吞吐量 | HeSBO-8 | 70 527.17 | 67 555.70 | 73 129.01 | 69 985.88 | 66 893.14 | 72 836.29 |
| HeSBO-16 | 65 655.64 | 71 183.57 | 73 289.79 | 66 280.42 | 71 241.95 | 72 736.71 | |
| HeSBO-24 | 66 612.45 | 72 770.46 | 72 658.08 | 67 625.01 | 72 413.22 | 73 146.50 | |
| 系统开销 | HeSBO-8 | 66.170 64 | 61.081 05 | 61.738 81 | 67.447 52 | 61.277 16 | 60.149 42 |
| HeSBO-16 | 67.527 00 | 60.787 09 | 62.227 36 | 60.315 57 | 60.695 90 | 62.134 58 | |
| HeSBO-24 | 60.314 45 | 61.615 15 | 60.142 19 | 61.443 76 | 61.587 73 | 60.158 28 | |
| [1] | Storm A J, Garcia-Arellano C, Lightstone S S, et al. Adaptive self-tuning memory in DB2 [C]// VLDB 2006. [S.l.]: VLDB Endowment, 2006: 1081-1092. |
| [2] | Wang Z, Hutter F, Zoghi M, et al. Bayesian optimization in a billion dimensions via random embeddings [J]. Journal of Artificial Intelligence Research, 2016, 55: 361-387. |
| [3] | Duan S, Thummala V, Babu S. Tuning database configuration parameters with iTuned [J]. Proceedings of the VLDB Endowment, 2009, 2(1): 1246-1257. |
| [4] | Cereda S, Valladares S, Cremonesi P, et al. CGPTuner: a contextual Gaussian process bandit approach for the automatic tuning of IT configurations under varying workload conditions [J]. Proceedings of the VLDB Endowment, 2021, 14(8): 1401-1413. |
| [5] | Li G, Zhou X, Li S, et al. QTune: a query-aware database tuning system with deep reinforcement learning [J]. Proceedings of the VLDB Endowment, 2019, 12(12): 2118-2130. |
| [6] | Wang L, Fonseca R, Tian Y. Learning search space partition for black-box optimization using Monte Carlo tree search [C]// NeurIPS 2020. Red Hook: Curran Associates Inc., 2020: 19511-19522. |
| [7] | Kanellis K, Ding C, Kroth B, et al. LlamaTune: sample-efficient DBMS configuration tuning [J]. Proceedings of the VLDB Endowment, 2022, 15(11): 2953-2965. |
| [8] | Zhou X, Chai C, Li G, et al. Database meets artificial intelligence: a survey [J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(3): 1096-1116. |
| [9] | Trummer I. DB-BERT: a database tuning tool that "reads the manual” [C]// SIGMOD 2022. New York: ACM, 2022: 190-203. |
| [10] | Trummer I. CodexDB: synthesizing code for query processing from natural language instructions using GPT-3 codex [J]. Proceedings of the VLDB Endowment, 2022, 15(11): 2921-2928. |
| [11] | Zhou X, Sun Z, Li G. DB-GPT: large language model meets database [J]. Data Science and Engineering, 2024, 9(1): 102-111. |
| [12] | Li Z, Yuan H, Wang H, et al. LLM-R2: a large language model enhanced rule-based rewrite system for boosting query efficiency [J]. Proceedings of the VLDB Endowment, 2025, 18(1): 53-65. |
| [13] | Shahriari B, Swersky K, Wang Z, et al. Taking the human out of the loop: a review of Bayesian optimization [J]. Proceedings of the IEEE, 2016, 104(1): 148-175. |
| [14] | Zhang X, Chang Z, Li Y, et al. Facilitating database tuning with hyper-parameter optimization [J]. Proceedings of the VLDB Endowment, 2022, 15(9): 1808-1821. |
| [15] | Kanellis K, Alagappan R, Venkataraman S. Too many knobs to tune? towards faster database tuning by pre-selecting important knobs [C]// HotStorage 2020. Berkeley: USENIX Association, 2020: 1-8. |
| [16] | Nayebi A, Munteanu A, Poloczek M. A framework for Bayesian optimization in embedded subspaces [C]// ICML 2019. New York: JMLR.org, 2019: 4752-4761. |
| [17] | Zhang X, Wu H, Chang Z, et al. ResTune: resource oriented tuning boosted by meta-learning for cloud databases [C]// SIGMOD 2021. New York: ACM, 2021: 2102-2114. |
| [18] | Browne C B, Powley E, Whitehouse D, et al. A survey of Monte Carlo tree search methods [J]. IEEE Transactions on Computational Intelligence and AI in Games, 2012, 4(1): 1-43. |
| [19] | Zhu Y, Liu J, Guo M, et al. BestConfig: tapping the performance potential of systems via automatic configuration tuning [C]// SoCC 2017. New York: ACM, 2017: 338-350. |
| [20] | Cai B, Liu Y, Zhang C, et al. HUNTER: an online cloud database hybrid tuning system for personalized requirements [C]// SIGMOD 2022. New York: ACM, 2022: 646-659. |
| [21] | Ge J K, Chai Y F, Chai Y P. WATuning: a workload aware tuning system with attention-based deep reinforcement learning [J]. Journal of Computer Science and Technology, 2021, 36(4): 741-761. |
| [22] | van Aken D, Pavlo A, Gordon G J, et al. Automatic database management system tuning through large-scale machine learning [C]// SIGMOD 2017. New York: ACM, 2017: 1009-1024. |
| [23] | Zhang J, Zhou K, Li G, et al. CDBTune+: an efficient deep reinforcement learning based automatic cloud database tuning system [J]. The VLDB Journal, 2021, 30(6): 959-987. |
| [24] | Wang J, Immanuel I, Basu D. UDO: universal database optimization using reinforcement learning [J]. Proceedings of the VLDB Endowment, 2021, 14(13): 3402-3414. |
| [25] | Hutter F, Hoos H H, Leyton-Brown K. Sequential model-based optimization for general algorithm configuration [C]// LION 2011. Berlin: Springer, 2011: 507-523. |
| [26] | Silver D, Huang A, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search [J]. Nature, 2016, 529(7587): 484-489. |
| [27] | Rakotoarison H, Schoenauer M, Sebag M. Automated machine learning with Monte-Carlo tree search [C]// IJCAI 2019. California: ijcai.org, 2019: 3296-3303. |
| [28] | Song L, Xue K, Huang X, et al. Monte Carlo tree search based variable selection for high dimensional Bayesian optimization [C]// NeurIPS 2022. Red Hook: Curran Associates Inc., 2022: 28488-28501. |
| [29] | Zhou X, Li G, CHAI C, et al. A learned query rewrite system using Monte Carlo tree search [J]. Proceedings of the VLDB Endowment, 2021, 15(1): 46-58. |
| [30] | Lao J, Wang Y, Li Y, et al. GPTuner: a manual-reading database tuning system via GPT-guided Bayesian optimization [J]. Proceedings of the VLDB Endowment, 2024, 17(8): 1939-1952. |
| [31] | Cooper B F, Silberstein A, Tam E, et al. Benchmarking cloud serving systems with YCSB [C]// SoCC 2010. New York: ACM, 2010: 143-154. |
| [32] | Zhang J, Liu Y, Zhou K, et al. An end-to-end automatic cloud database tuning system using deep reinforcement learning [C]// SIGMOD 2019. New York: ACM, 2019: 415-432. |
| [1] | Chao JING, Yutao QUAN, Yan CHEN. Improved multi-layer perceptron and attention model-based power consumption prediction algorithm [J]. Journal of Computer Applications, 2025, 45(8): 2646-2655. |
| [2] | Ruifeng BAI, Guanglei GOU, Lang WEN, Wanyu MIAO. Granular-ball prototypical network for few-shot image classification [J]. Journal of Computer Applications, 2025, 45(7): 2269-2277. |
| [3] | Lin SUN, Menghan LIU. K-means clustering based on adaptive cuckoo optimization feature selection [J]. Journal of Computer Applications, 2024, 44(3): 831-841. |
| [4] | Xueran XU, Geng YANG, Yuxian HUANG. Differential privacy clustering algorithm in horizontal federated learning [J]. Journal of Computer Applications, 2024, 44(1): 217-222. |
| [5] | Jing ZHONG, Chen LIN, Zhiwei SHENG, Shibin ZHANG. Quantum K-Means algorithm based on Hamming distance [J]. Journal of Computer Applications, 2023, 43(8): 2493-2498. |
| [6] | Jun LIANG, Zehong HONG, Songsen YU. Image segmentation model based on improved particle swarm optimization algorithm and genetic mutation [J]. Journal of Computer Applications, 2023, 43(6): 1743-1749. |
| [7] | Ran ZHAI, Xuebin CHEN, Guopeng ZHANG, Langtao PEI, Zheng MA. Improved K-anonymity privacy protection algorithm based on different sensitivities [J]. Journal of Computer Applications, 2023, 43(5): 1497-1503. |
| [8] | Xia HUA, Zhenghao ZHU, Cong XU, Xihuang ZHANG, Zhilei CHAI, Wenjie CHEN. Workload automatic mapper for spiking neural network based on precise communication modeling [J]. Journal of Computer Applications, 2023, 43(3): 827-834. |
| [9] | Dawei ZHANG, Xuchong LIU, Wei ZHOU, Zhuhui CHEN, Yao YU. Real-time traffic sign detection algorithm based on improved YOLOv3 [J]. Journal of Computer Applications, 2022, 42(7): 2219-2226. |
| [10] | Youzhi LI, Zhihua HU, Chun CHEN, Peibei YANG, Yajing DONG. Prediction model of transaction pricing in internet freight transport platform based on combination of dual long short-term memory networks [J]. Journal of Computer Applications, 2022, 42(5): 1616-1623. |
| [11] | Xiangju LIU, Xiaobao LU, Xianjin FANG, Linsong SHANG. Low-rate denial-of-service attack detection method under software defined network environment [J]. Journal of Computer Applications, 2022, 42(4): 1301-1307. |
| [12] | Lei GAO, Guanfeng LUO, Dang LIU, Fan MIN. First-arrival automatic picking algorithm based on clustering and local linear regression [J]. Journal of Computer Applications, 2022, 42(2): 655-662. |
| [13] | Le ZHAO, En ZHANG, Leiyong QIN, Gongli LI. Multi-party privacy preserving k-means clustering scheme based on blockchain [J]. Journal of Computer Applications, 2022, 42(12): 3801-3812. |
| [14] | YIN Fei, LONG Lingli, KONG Zheng, SHAO Han, LI Xin, QIAN Zhuzhong. Deployment method of dockers in cluster for dynamic workload [J]. Journal of Computer Applications, 2021, 41(6): 1581-1588. |
| [15] | ZOU Zhiwen, QIN Cheng. Method of dynamically constructing spatial topic R-tree based on k-means++ [J]. Journal of Computer Applications, 2021, 41(3): 733-737. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||