《计算机应用》唯一官方网站 ›› 2020, Vol. 40 ›› Issue (2): 358-362.DOI: 10.11772/j.issn.1001-9081.2019081402

• 2019年全国开放式分布与并行计算学术年会(DPCS 2019)论文 • 上一篇    下一篇

移动群智感知中面向用户区域的分布式多任务分配方法

韩俊樱1,2(), 张振宇1,2, 孔德仕3   

  1. 1.新疆大学 信息科学与工程学院,乌鲁木齐 830046
    2.新疆大学 新疆多语种信息技术实验室,乌鲁木齐 830046
    3.四川大学 计算机学院,成都 610065
  • 收稿日期:2019-07-31 修回日期:2019-09-02 接受日期:2019-09-19 发布日期:2019-09-29 出版日期:2020-02-10
  • 通讯作者: 韩俊樱
  • 作者简介:张振宇(1964—),男,山西太原人,教授,硕士,主要研究方向:机会网络、移动群智感知
    孔德仕(1995—),男,浙江金华人,硕士研究生,主要研究方向:移动群智感知、多智能体强化学习。
  • 基金资助:
    国家自然科学基金资助项目(61262089)

Distributed multi-task allocation method for user area in mobile crowd sensing

Junying HAN1,2(), Zhenyu ZHANG1,2, Deshi KONG3   

  1. 1.College of Information Science and Engineering,Xinjiang University,Urumqi Xinjiang 830046,China
    2.Xinjiang Multilingual Information Technology Key Laboratory,Xinjiang University,Urumqi Xinjiang 830046,China
    3.School of Computer Science,Sichuan University,Chengdu Sichuan 610065,China
  • Received:2019-07-31 Revised:2019-09-02 Accepted:2019-09-19 Online:2019-09-29 Published:2020-02-10
  • Contact: Junying HAN
  • About author:ZHANG Zhenyu, born in 1964, M. S., professor. His research interests include opportunity network, mobile crowd sensing.
    KONG Deshi, born in 1995, M. S. candidate. His research interests include mobile crowd sensing, multi-agent reinforcement learning.
  • Supported by:
    the National Natural Science Foundation of China(61262089)

摘要:

多数群智感知(MCS)任务分配方法针对单个任务,难以适用于多任务实时并发的现实场景,而且往往需要实时获取用户位置,不利于保护参与者隐私。针对上述问题,提出了一种面向用户区域的分布式多任务分配方法Crowd-Cluster。该方法首先通过贪心启发算法将全局感知任务及用户区域进行分簇;其次,基于空间关联性采用Q-learning算法将并发任务组合构成任务路径;接着,构建符合玻尔兹曼分布的用户意愿模型对任务路径进行动态定价;最后,基于历史信誉记录贪心优选参与者实现任务分配。基于真实数据集mobility的实验结果表明,Crowd-Cluster能有效减少参与者总人数及用户总移动距离,并且在低人群密度场景下,还能降低感知资源不足对任务完成度的影响。

关键词: 移动群智感知, 多任务分配, 任务组合, 分布式计算, 动态定价

Abstract:

Most Mobile Crowd Sensing (MCS) task allocation methods are specific to a single task and are difficult to apply to real-world scenarios of real-time concurrent multi-task. And it is often necessary for these methods to obtain user location in real time, which is not conducive to the protection of participant privacy. Concerning the above problems, a distributed multi-task allocation method for user area was proposed, named Crowd-Cluster. Firstly, the global perception task and the user area were clustered by using the greedy heuristic algorithm. Secondly, based on the spatial correlation, the Q-learning algorithm was used to combine the concurrent tasks into the task path. Then, the task path was dynamically priced by constructing user intention model that satisfying the Boltzmann distribution. Finally, based on the historical reputation records, the participants were greedily selected to implement task allocation. Experimental results on the real dataset mobility show that Crowd-Cluster can effectively reduce the total number of participants and the total movement distance of users, and can also reduce the impact of insufficient perception resources on task completion in the low population density scenarios.

Key words: Mobile Crowd Sensing (MCS), multi-task allocation, task combination, distributed computing, dynamic pricing

中图分类号: