| 引用本文: | 乔少杰,杨蕾,夏书银,韩楠,苟浩淞,何函,袁冠,唐明靖.粒球计算驱动的智能数据库: 现状和展望.软件学报,,():1-25 |
| |
|
| |
|
|
| 本文已被：浏览 442次 下载 146次 |
码上扫一扫！ |
|
|
| 粒球计算驱动的智能数据库: 现状和展望 |
|
乔少杰1, 杨蕾1, 夏书银2,3, 韩楠4, 苟浩淞5, 何函1, 袁冠6, 唐明靖7
|
|
1.成都信息工程大学 软件工程学院, 四川 成都 610225;2.网络空间大数据智能安全教育部重点实验室(重庆邮电大学), 重庆 400065;3.重庆邮电大学 人工智能学院, 重庆 400065;4.成都信息工程大学 管理学院, 四川 成都 610225;5.中国移动通信集团四川有限公司, 四川 成都 610091;6.中国矿业大学 计算机科学与技术学院, 江苏 徐州 221116;7.云南师范大学 信息学院, 云南 昆明 650500
|
|
| 摘要: |
| 传统关系型数据库的关键优化技术在面对海量数据处理、复杂查询及动态负载场景时, 普遍存在估计精度不足、优化决策效率低下以及环境适应性差等瓶颈. 多粒度粒球计算为提升数据库系统性能开辟了新的解决路径, 展现出巨大的研究潜力和应用前景. 首先, 概述了人工智能在驱动数据库智能优化方面的核心方向, 探讨了现有学习型优化方法在模型泛化能力、可解释性以及处理复杂查询与动态数据分布方面所面临的主要挑战. 在此基础上, 系统地综述了数据库优化的现状及关键技术, 结合多粒度粒球计算, 数据库优化技术的核心聚焦于查询优化与配置优化两个方面. 针对查询优化, 关键技术包括基数估计以及连接顺序选择. 在基数估计方面, 传统方法难以有效支持涉及多表复杂连接及嵌套查询的准确评估, 且常带来巨大的存储开销; 基于学习的方法则能更好地处理高维数据关系, 介绍利用多粒度粒球计算技术提取数据分层分布特征并与树结构神经网络结合的新方法, 能显著提高复杂查询基数估计的鲁棒性与精度. 在连接顺序选择方面, 传统方法在多表连接维度下搜索效率低下; 基于历史经验学习的静态方法对新查询模式适应性有限; 动态学习方法虽能支持运行时调整但开销较大; 相比之下, 将连接计划表达为具有几何关系的多粒度粒球结合, 利用其层次结构优化搜索空间并结合深度强化学习进行决策的方法, 为高效寻找全局近似最优连接顺序提供了新思路. 针对数据库配置优化, 参数调优是提升性能的关键. 基于搜索的传统优化技术难以在合理时间内获得全局最优解; 传统机器学习方法虽然能实现自动化调优, 但高度依赖训练数据的质量与覆盖度; 强化学习方法通过与系统环境交互持续改进策略, 仅需少量样本即可实现强大的自适应性调参, 融合多粒度粒球计算方法能够高效表达参数空间特性, 显著提升调优效率与效果. 虽然应用粒球计算技术优化数据库前景广阔, 但实际应用仍面临与现有数据库模型的有效融合、降低计算开销、动态负载变化下的模型稳定性保障等主要挑战. 未来研究需持续深化理论与技术, 推动数据库系统朝着更智能、高效、鲁棒的方向发展. |
| 关键词: 粒球计算 智能数据库 基数估计 连接顺序选择 查询优化 参数调优 |
| DOI：10.13328/j.cnki.jos.007664 |
| 分类号:TP311 |
| 基金项目:国家自然科学基金(62272066, 62572078); 四川省科技计划(2025ZNSFSC0044, 2025YFHZ0194); 成都市重点研发计划基础研究项目(2025-YF12-00019-RC, 2025-YF12-00012-RC, 2025-YF12-00015-RC); 成都重点研发支撑计划产业链协同创新项目(2025-XT00-00005-GX); 成都市技术创新研发项目重点项目(2025-YF08-00016-GX); 成都市区域科技创新合作项目(2025-YF11-00050-HZ); 网络空间大数据智能安全教育部重点实验室开放基金课题(CBDIS202404) |
|
| Intelligent Database Driven by Granular-ball Computing: Current Status and Prospects |
|
QIAO Shao-Jie1, YANG Lei1, XIA Shu-Yin2,3, HAN Nan4, GOU Hao-Song5, HE Han1, YUAN Guan6, TANG Ming-Jing7
|
|
1.School of Software Engineering, Chengdu University of Information Technology, Chengdu 610225, China;2.Key Laboratory of Cyberspace Big Data Intelligent Security (Chongqing University of Posts and Telecommunications), Ministry of Education, Chongqing 400065, China;3.School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;4.School of Management, Chengdu University of Information Technology, Chengdu 610225, China;5.China Mobile Group Sichuan Co. Ltd., Chengdu 610091, China;6.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;7.School of Information Science and Technology, Yunnan Normal University, Kunming 650500, China
|
| Abstract: |
| The key optimization technologies of traditional relational databases generally face bottlenecks including insufficient estimation accuracy, low efficiency of optimization decisions, and poor environmental adaptability when dealing with massive data processing, complex queries, and dynamic workload scenarios. Multi-granularity granular-ball computing provides a new solution for improving the performance of database systems, showing great research potential and application prospects. The core directions of artificial intelligence in driving intelligent optimization for databases are outlined, and the main challenges faced by existing learning-based optimization methods in terms of model generalization ability, interpretability, and handling complex queries and dynamic data distributions are explored. On this basis, the current status and key technologies of database optimization are systematically reviewed. Combined with multi-granularity granular-ball computing, database optimization techniques primarily focus on two aspects: query optimization and configuration optimization. For query optimization, the key techniques include cardinality estimation and join order selection. In terms of cardinality estimation, traditional methods are difficult to effectively support accurate estimation of complex joins and nested queries involving multiple tables, and often result in huge storage overhead. Learning-based methods can better handle high-dimensional data relationships, and a new method that uses multi-granularity granular-ball computing techniques to extract hierarchical distribution features of data and combines them with tree-structured neural networks is introduced, which can significantly improve the robustness and accuracy of complex query cardinality estimation. In terms of join order selection, traditional methods have low search efficiency in multi-table join scenarios. Static methods based on historical experience learning have limited adaptability to new query patterns. Although dynamic learning methods can support runtime adjustments, they incur a high cost. In contrast, representing the join plan as a combination of multi-granularity granular-balls with geometric relationships, optimizing the search space through a hierarchical structure, and integrating deep reinforcement learning for decision-making provides an efficient approach to finding a globally approximate optimal join order. For database configuration optimization, parameter tuning plays a key role in improving performance. Traditional optimization techniques based on search are difficult to obtain the global optimal solution within a reasonable time. Although traditional machine learning methods can achieve automated tuning, they highly rely on the quality and coverage of training data. Reinforcement learning methods continuously improve strategies by interacting with the system environment, requiring only a small number of samples to achieve strong adaptive parameter tuning. By integrating multi-granularity granular-ball computing methods, the characteristics of the parameter space can be efficiently represented, thus significantly improving tuning efficiency and effectiveness. Although the prospects of optimizing intelligent databases using granular-ball computing techniques are broad, practical applications still face major challenges such as effective integration with existing database models, reduction of computational overhead, and ensuring model stability under dynamic workload changes. Future research requires continuous development of theories and technologies to promote database systems toward more intelligent, efficient, and robust directions. |
| Key words: granular-ball computing (GBC) intelligent database cardinality estimation join order selection query optimization parameter tuning |
|
|
|
|
