Optimal placement of processing and storage for IoT systems
The Internet of Things (IoT) is an important part of the future Internet with its many useful applications. However, IoT devices often have limited computation and storage capacity. We therefore need the computation to take place elsewhere.
Cloud computing and edge computing are practices that may help solve the issue of low computing capacity in IoT devices. In cloud computing, you use a network of remote servers hosted on the Internet to store, manage, and process data, rather than on a local server or in an IoT device. Edge computing, on the other hand, is about processing data near the edge of your network, where the data is being generated, instead of in a centralized data-processing warehouse.
Cloud computing is increasingly being used for IoT applications, but there are challenges concerning, for example, privacy, latency and energy consumption. Edge computing can address those problems by performing computations directly in devices at the edge of the network such as gateways, routers, switches and base stations. To go further, a hybrid edge–cloud architecture may provide more secure and robust services and communications through distributed data storage and processing.
Research questions in this project includes:
- What are the most important quality attributes to consider when determining how to distribute IoT application components, and how can they be measured?
- What are the trade-offs among the attributes and the relation between quality attributes and different IoT application component distributions?
- How can designers be supported for deciding about how to distribute IoT application components?
One of the aims of the project is to develop guidelines for when cloud, edge or a hybrid solution should be used.
Project period: 2018–2022
Funding: The project is currently funded by Malmö University (part of Majid Ashouri’s PhD studies).
Contact: The project is coordinated by Paul Davidsson, IOTAP, Malmö University.