PROJECT SUMMARY
The growing capabilities of sensing, computing and communication devices are leading to an explosion of Internet of Things (IoT) infrastructures. The challenges stem from several major aspects in terms of scalability. First, the number of edge devices is enormous, e.g., in the order of millions or even billions, which makes a centralized management infeasible. Second, there are multiple layers of heterogeneity. Third, mission-critical applications have stringent requirements in correctness, resilience, timeliness, security, and safety. It is difficult for a large-scale IoT system to satisfy these requirements due to the increasing adversarial surfaces. To tackle these challenges, this project aims to develop a cross-layer and full hardware/software stack solution for the design and deployment of scalable, secure, and smart mission-critical IoT systems, named S3-IoT framework. The S3-IoT framework will span three different computation layers, data centers, gateways/aggregators, and edge devices with four closely related research foci, i.e., theory/algorithms, resource management, computer architecture/systems and security & privacy. In this project, the S3-IoT framework will (i) leverage a layered structure - data centers, gateways/aggregators, and edge devices to accommodate the huge number of edge devices; (ii) develop cross-layer techniques to deal with the heterogeneity among these layers; and (iii) propose hardware and software co-design approaches that embrace the heterogeneity and scalability among computing components to improve the performance of all components within an individual layer. Two real-world testbeds, a smart transportation system and an industrial automation system, will also be enhanced through this project to help validate and assess the scalability the proposed S3-IoT framework. Keywords: Internet-of-Things; Heterogeneous Computing Devices; Resource Management; Security and Privacy; Attack and Fault Resilience; Machine Learning.
Intellectual Merit:
This project will generate transformative innovations for designing scalable, secure and smart IoT systems through the proposed S3-IoT framework from four research angles. The theory/algorithmic innovations revolve around a novel fusion of approximate simulation and moment-matching model reduction concepts into a hierarchical method that scalably regulates the behavior of large-scale computational systems under overload conditions. The resource management research develops innovative, fully distributed run-time network and computing resource management techniques for handling unavoidable workload uncertainties caused by changes in either the application environment or the IoT infrastructure itself. The computer architecture/systems research introduces a comprehensive, two-tiered approach to tackle faults in scalable IoT systems caused by uncertainty in workload, operating conditions and user demands. From the security & privacy angle, scalable and resilient security solutions will be investigated for analyzing vulnerabilities of scaled hardware and software system, and for distributed cross-validation of sensing data from multiple devices. To assess the success of S3-IoT, two existing testbeds will be significantly enhanced by increasing their sizes and heterogeneity to support scalability study. Benchmarks will be developed on those testbeds and released to further foster collaboration with the industry and serve other researchers in this field.
Broader Impacts: The project outcomes will have broader impacts on the deployment of large-scale, mission-critical IoT systems and infrastructures, particularly in terms of improving resilience to environmental uncertainties, system internal errors and faults, and malicious attacks. Considering the important roles of critical infrastructure to our daily lives, the success of this project will lead to a convincing path to help improve the efficiency and quality-of-service (QoS) of the service providers. In addition, the project will contribute to curriculum development in the IoT area as well as training the next generation researchers and practitioners. The research outcomes will be actively integrated into existing and new undergraduate and graduate courses through collaborative efforts of the PIs. A course website will be created to share the courses based on the project and to help disseminate the educational materials. Further, the project will provide unique opportunities for recruiting and mentoring students from underrepresented groups. The inter-disciplinary nature of the project will be leveraged to provide activities for developing participants' skill in inter-disciplinary collaboration. Webinars and tutorials introducing the scalable S3-IoT framework will be prepared and presented in tutorial sessions and workshops planned through this project.