As the digital and physical worlds continue to converge, Cyber-Physical Systems (CPS) are gaining significant importance due to their transformative potential across diverse industries, including aerospace, automotive, healthcare, and telecommunications. CPS enables effective control of physical-world functionalities through advanced computing and connectivity. Leveraging the virtually unlimited storage and computational resources of the cloud, CPS can support sophisticated control and optimization algorithms for complex, data-intensive applications. While local feedback is essential to ensure stability in individual control applications, cloud-based computing is ideally suited for higher-level control and optimization algorithms in large-scale, networked systems.
This research project is part of ESLAB’s long-term efforts in developing system-level design and optimization strategies tailored for various CPS applications and architectures. The postdoc researcher will develop design and optimization techniques for key system-level decisions, such as functionality mapping, task scheduling, and power management, in order to achieve timeliness, reliability, power efficiency, and high control quality in complex CPS. Some system-level optimizations can also be applied in real-time as adaptive management mechanisms, enabling CPS to respond dynamically to mode changes or criticality-level switches, whether in response to external events or scheduled triggers.
Another research issue of this project is the development of robust, scalable, and secure cloud-based CPS frameworks. By harnessing cloud and edge computing resources, we aim to design a resilient CPS infrastructure that meets real-time data processing needs while optimizing reliability, security, and resource efficiency. We will address challenges in maintaining control loop stability over cloud-based systems, where unpredictable latency and variable computational capacity can impact control quality across hardware and software layers.
We will also establish a CPS architecture to enable continuous operation and adaptability in dynamic environments, accommodating both anticipated and unanticipated fluctuations in system demands. This architecture will incorporate fault-tolerant features to minimize downtime due to hardware or software failures and will include algorithms for optimal resource allocation across cloud and edge layers, balancing computational loads to reduce latency and improve quality of control or service.
PI: Zebo Peng
Funding: Supported by the CUGS Graduate School in Computer Science at Linköping University