Special issue on Big Data and Cloud of Things (CoT)

Cloud computing and Internet of Things (IoT) are two technologies that are already becoming part of our daily lives and are attracting significant interest from both industry and academia. The Cloud of Things (CoT) is a vision inspired from the IoT paradigm where everyday devices, namely, ‘smart objects’, are fully connected to the internet and are integrated with the cloud. It is expected the IoT will grow to 35 billion units by 2020, making it one of the main sources of ‘Big Data’ with characteristics such as volume, heterogeneity, complexity, velocity, and value. In recent years, IoT has given rise to a number of new CoT paradigms (but not limited to) including: Sensing-as-a-Service, Sensingand Actuation-as-a-Service, Video-Surveillance-as-a-Service, Big Data Analytics-asa-Service, Data-as-a-Service, Sensor-as-a-Service, and Sensor-Event-as-a-Service. Cloud computing is a more mature technology compared to IoT. It can offer virtually unrestricted capabilities (e.g., storage and computation) to support IoT services and application that can exploit the data produced from IoT devices. The cloud essentially acts as a transparent layer between the IoT and applications providing flexibility, scalability, and hiding the complexities between the two layers (IoT and applications). However, the integration of cloud and IoT into Cloud of Things is not straightforward and imposes several challenges. These challenges include IoT device and service discovery, IoT device integration, big data management and analytics, cloud monitoring and orchestration for distributed IoT applications, mobility issues in cloud access, privacy and security, and SLA management for both cloud and IoT. Specific attention must be paid to address a range of issues from IoT data collection, storage, processing, analytics on demand to automatic provision and management of cloud resources to support the growing population of things. Hence, this special issue solicits paper related to topics including CoT architectures and models for smart provision of CoT applications, data management challenges facing CoT applications, software and tools to monitor, manage, deploy and deliver CoT applications, quality of service and related SLA management and policies for CoT applications, and security and privacy challenges facing CoT applications. The call for special issues received a number of submissions. After a two-phase peer review process, we have accepted 10 high-quality papers related to the aforementioned areas of interest. The first paper titled Using adaptive resource allocation to implement an elastic MapReduce framework by Jiaqi Zhao, Changlong Xue, Xinlin Tao, Shugong Zhang, and Jie Tao addresses the runtime resource demand challenge faced by application running on MapReduce frameworks. The proposed approach is capable of making the map reduce application, aware of overloading or under-loading situations with the resources allocated. They have extended the existing Hadoop MapReduce resource manager to implement the proposed strategy and validated the concept on an high-performance computing cluster with standard benchmark applications. Experimental results show a significant performance gain, for example, an up to 45% improvement in execution time for running multiple applications. The second paper titled A traffic hotline discovery method over cloud of things using big taxi GPS data by Xiaolong Xu, Wanchun Dou, Xuyun Zhang, Chunhua Hu, and Jinjun Chen addresses the challenge of discovering traffic hotline in CoT environments. Traffic hotlines are identified as the traffic lines with intensive traffic flows among traffic spots. They propose a hotline discovery method over CoT by establishing a hotline discovery principle. They have implemented their approach on SAP HANA cloud and tested it using big taxi global positioning system data under two application scenarios.