We propose a design optimization framework for adaptive real-time streaming applications. The main contribution is a hybrid approach for performance analysis combining formal analysis and simulation using a two-phase framework. We formulate the scheduling problem of adaptive streaming applications with ILP analysis, and use the simulation based on the synchronous model of computation to ensure throughput guarantees. We finally illustrate the capabilities of our methodology by experiments. 1.

Over the last few years, Real-Time Calculus has been used extensively to model and analyze embedded systems processing continuous data/event streams. Towards this, bounds on the arrival process of streams and bounds on the processing capacity of resources serve as inputs to the model, which are used to calculate end-to-end delays suffered by streams, maximum backlog, utilization of resources, etc. This “functional ” model, although amenable to computationally inexpensive analysis methods, has limited modeling capability. In particular, “state-based ” processing, e.g. blocking write – where the processing depends on the “state ” or fill-level of the buffer – cannot be modeled in a straightforward manner. This has led to a number of recent proposals on using automata-theoretic models for stream processing systems (e.g. Event Count Automata [RTSS 2005]). Although such models offer better modeling flexibility, they suffer from the usual state-space explosion problem. In this paper we show that a number of complex state-dependencies can be modeled in a lightweight manner, using a feedback control technique. This avoids explicit state modeling, and hence the state-space explosion problem. Our proposed modeling and analysis therefore extend the original Real-Time Calculus-based functional modeling in a very useful way, and cover much larger problem domain compared to what was previously possible without explicit state-modeling. We illustrate its utility through two case studies and also compare our analysis results with those obtained from detailed system simulations (which are significantly more time consuming). 1

The Real-Time Calculus (RTC) framework proposed in [Chakraborty et al., DATE 2003] and subsequently extended in [Wandeler et al., Real-Time Systems 29(2-3), 2005] and a number of other papers is geared towards the analysis of real-time systems that process various types of streaming data. The main strength of RTC is a count-based abstraction, where arrival patterns of event streams are specified as constraints on the number of events that may arrive over any specified time interval. In this framework, algebraic techniques can be used to compute system properties in a compositional way. However, the main drawback of RTC is that it cannot model state information in a natural way. For example, when a scheduling policy depends on the fill-level of a certain buffer or there is a shift from one type of data stream into another. In this paper, we extend RTC in a manner that enables state information to be easily captured while limiting the state-space explosion caused by fine grained state-based models such as timed automata. Our model, called multi-mode RTC, specifies event streams as finite automata whose states are annotated with functions that specify constraints on the arrival patterns of event streams or the service available to process them. Our new framework combines the expressiveness of state-based models with the algebraic and compositional features of the RTC formalism. In particular, system properties within a single mode can be analyzed using the RTC-based algebraic techniques and state-space exploration can be used to piece together the results obtained algebraically for the individual modes. We show how to determine typical system properties with the focus on efficient approximate techniques and illustrate the advantages of multi-mode RTC using two case studies. 1

Automotive architectures consist of multiple electronic control units (ECUs) which run distributed control applications. Such ECUs are connected to sensors and actuators and communicate via shared buses. Resource arbitration at the ECUs and also in the communication medium, coupled with variabilities in execution requirements of tasks results in jitter in the signal/data streams existing in the system. As a result, buffers are required at the ECUs and bus controllers. However, these buffers often implement different semantics – FIFO queuing, which is the most straightforward buffering scheme, and data refreshing, where stale data is overwritten by freshly sampled data. Traditional timing and schedulability analysis that are used to compute, e.g., end-to-end delays, in such automotive architectures can only model FIFO buffering. As a result, they return pessimistic delay and resource estimates because in reality

Over the last few years, Real-Time Calculus has been used extensively to model and analyze embedded systems processing continuous data/event streams. Towards this, bounds on the arrival process of streams and bounds on the processing capacity of resources serve as inputs to the model, which are used to calculate end-to-end delays suffered by streams, maximum backlog, utilization of resources, etc. This “functional ” model, although amenable to computationally inexpensive analysis methods, has limited modeling capability. In particular, “state-based ” processing, e.g. blocking write – where the processing depends on the “state ” or fill-level of the buffer – cannot be modeled in a straightforward manner. This has led to a number of recent proposals on using automata-theoretic models for stream processing systems (e.g. Event Count Automata [RTSS 2005]). Although such models offer better modeling flexibility, they suffer from the usual state-space explosion problem. In this paper we show that a number of complex state-dependencies can be modeled in a lightweight manner, using a feedback control technique. This avoids explicit state modeling, and hence the state-space explosion problem. Our proposed modeling and analysis therefore extend the original Real-Time Calculus-based functional modeling in a very useful way, and cover much larger problem domain compared to what was previously possible without explicit state-modeling. We illustrate its utility through two case studies and also compare our analysis results with those obtained from detailed system simulations (which are significantly more time consuming). 1