Smart Mobile Crowdsensing With Urban Vehicles: A Deep Reinforcement Learning Perspective
Authors:
Open Access
- 15 March 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 37334-37341
Abstract
Mobile crowdsensing (MCS) is a promising sensing paradigm based on mobile node which provides solution with cost-effectiveness to perform urban data collection. To monitor the urban environment and facilitate the municipal administration, more and more applications adopt vehicles as participants to carry out MCS tasks. The performance of the applications highly depends on the sensing data which is influenced by the recruiting strategy on vehicles. In this paper, we propose a novel vehicle selection algorithm to maximize the sensing range with limited cost while the vehicle selection problem was proved to be NP-complete. Specifically, we modeled the interaction between MCS server and candidate vehicles as a Markov Decision Process (MDP) and formulated the maximum spatial temporal coverage (STC) optimization as a deep reinforcement learning process. The performance of our deep reinforcement learning based vehicle selection (i.e. DRLVS) algorithm is evaluated with real trajectory dataset. The numerical result indicates that the proposed algorithm achieves an optimal solution and maximizes the STC.Keywords
Funding Information
- National Basic Research Program of China (2017YFC0804404)
This publication has 24 references indexed in Scilit:
- Real-time personalized content catering via viewer sentiment feedback: a QoE perspectiveIEEE Network, 2015
- Mobile Crowd Sensing and ComputingACM Computing Surveys, 2015
- Applications of big data to smart citiesJournal of Internet Services and Applications, 2015
- Truthful Scheduling Mechanisms for Powering Mobile CrowdsensingIEEE Transactions on Computers, 2015
- High quality participant recruitment in vehicle-based crowdsourcing using predictable mobility2015
- Human-level control through deep reinforcement learningNature, 2015
- How to crowdsource tasks truthfully without sacrificing utility: Online incentive mechanisms with budget constraint2014
- From participatory sensing to Mobile Crowd Sensing2014
- Nericell2008
- The BikeNet mobile sensing system for cyclist experience mapping2007