Optimal Selection of Crowdsourcing Workers Balancing Their Utilities and Platform Profit

Document Type

Article

Publication Date

10-1-2019

Abstract

In a mobile crowdsourcing system (MCS), a platform outsources sensing tasks to numerous mobile worker devices. The collected data are analyzed and the processed information is shared among many other interested users. The platform pays the workers for the sensing data and earns money from the users receiving processed information services. Distributing the sensing workloads among the potential workers so as to maintain the required data quality and to make a reasonable amount of profit is a challenging problem for such a platform. In this paper, we develop a workload allocation policy that makes a reasonable tradeoff between worker utilities and platform profit. It quantifies the utility (i.e., the quality of sensed data) of a worker as a function of worker mobility, current location, and past sensing records. The workload allocation problem is formulated as a multiobjective nonlinear programming (MONLP) problem which aims to make the desired tradeoff between worker utilities and platform profit. The allocation problem is shown to be NP-hard and thus we develop two greedy algorithms with relaxed constraints to achieve polynomial time solutions. Performance of the proposed workload allocation policy is evaluated in a distributed computation environment using MATLAB. The results show its effectiveness compared to state-of-the-art methods in terms of platform profit, quality of sensing data, and request service satisfaction.

Identifier

85073448063 (Scopus)

Publication Title

IEEE Internet of Things Journal

External Full Text Location

https://doi.org/10.1109/JIOT.2019.2921234

e-ISSN

23274662

First Page

8602

Last Page

8614

Issue

5

Volume

6

Grant

119/2014/A3

Fund Ref

Fundo para o Desenvolvimento das Ciências e da Tecnologia

This document is currently not available here.

Share

COinS