Task Scheduling on Crowdsourcing Platforms for Enabling Completion Time SLAs

被引：1

作者：

Hirth, Matthias ^{[1
]}

Steurer, Florian ^{[2
]}

Borchert, Kathrin ^{[2
]}

Dubiner, Dan ^{[3
]}

机构：

[1] TU Ilemnau, Ilmenau, Germany

[2] Univ Wurzburg, Wurzburg, Germany

[3] ScaleHub AG, Norderstedt, Germany

来源：

PROCEEDINGS OF THE 2019 31ST INTERNATIONAL TELETRAFFIC CONGRESS (ITC 31) | 2019年

关键词：

crowdsourcing; task scheduling; performance evaluation;

D O I：

10.1109/ITC31.2019.00026

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Today a diverse crowdsourcing economy has established, and service level agreements (SLAs) become a crucial part of this ecosystem. However, the uncertainty introduced by human workers makes it hard to set completion time guarantees. In this work, we analyze an exemplary task scheduling strategy that helps operators of crowdsourcing-based services to meet completion time SLAs. We use the real-world crowdsourcing-based text digitalization platform ScaleHub as the foundation for our system model and a dataset provided by ScaleHub to obtain a realistic parametrization of the model. We derive a simulation model that enables us to illustrate the potential and limitations of scheduling mechanisms to meet SLA constraints and that helps platform providers to optimize their systems.

引用

页码：117 / 118

页数：2