Real-Time Scheduling

A real-time system is a reactive, deterministic system whose proper functioning depends not only on the logical accuracy of the calculated data, but also on the respect of certain temporal constraints. In scheduling theory, a real-time system is usually formalized by a set of tasks to be executed on a platform. A scheduling algorithm must determine the order of tasks that optimizes the use of the platform while respecting the time constraints. We have studied the performance of fixed priority scheduling algorithms at task level and job level as well as the cost of scheduling for sporadic task templates and acyclic task graphs.

We were also interested in real-time scheduling for energy harvesting systems (Energy Harvesting System). We have proposed a task model for this problem and a scheduling algorithm for which we proved optimality in the class of fixed priority algorithms in the case and where the system is composed only of energy consuming tasks and proposed sufficient scheduling tests in a more general case. We have also studied probabilistic approaches for the modeling and analysis of real-time scheduling problems, in the case of mixed criticality systems and for time sensitivity analysis of real-time systems.

We have also studied different interconnection systems and networks such as Network on Chip (NoC) and real-time Ethernet networks in order to characterize the worst end-to-end response time.

We have proposed arbitration mechanisms in the NoC to guarantee the predictability, security and criticality of the flows passing from one core to the other (in context Manycoeur) through a NoC. A first contribution is an adaptation of the trajectory approach traditionally used in avionics networks (AFDX) to calculate the worst crossing time of NoC. The second contribution is a mechanism for detecting DoS attacks and mitigating their impact by a mixed criticality approach where the criticality of a stream reflects its level of security.

Energy Efficiency

Due to rising energy costs and environmental concerns, centralized power generation systems are restructuring to take advantage of decentralized energy production. Microgrids are considered a possible solution for deploying Distributed Energy Resources (DER). We are interested in the problem of energy management in an industrial microgrid, our approach is to divide the energy management of microgrids into two phases: the supply and the demand sides.

  • On the supply side, we have proposed solutions for distributed energy source modeling and for the mitigation of DER fluctuations by proposing a model based on Network Calculus (NC) service curve concepts and Gaussian smoothing. We determine the minimum amount of power that the DERs can generate and their aggregation gives us the total power output in the microgrid with or without a battery to compensate for the prediction errors.
  • On the demand side, the goal is to reduce energy costs through Demand Side Management (DSM) approaches such as Demand Response (DR) and Energy Efficiency (EE). Since industrial processes are energy-hungry consumers, we have been interested in reducing the energy consumption of synchronous / asynchronous production lines so that this has the least impact on the throughput of production. In this framework we have proposed a framework, called DR-Mgmt, which allows to first model the temporal behavior of the production lines by PLCs and waiting queues. Then, it searchs for optimal or near-optimal scheduling based on combinatorial optimization techniques.