Comparative Assessment and Evaluation of Jitter Control Methods
Giorgio Buttazzo, Anton Cervin · 2007
Most control systems involve the execution of periodic activities, which are automatically activated by the operat-ing system at the specified rates. When the application con-sists of many concurrent tasks, each control activity may ex-perience delay and jitter, which depend on several factors, including the scheduling algorithm running in the kernel, the overall workload, the task parameters, and the task in-teractions. If not properly taken into account, delays and jitter may degrade the performance of the system and even jeopardize its stability. In this paper, we evaluate three methodologies for reduc-ing the jitter in control tasks: the first one consists of forc-ing the execution of inputs and outputs at the period bound-aries, so trading jitter with delay; the second method re-duces jitter and delay by assigning tasks shorter deadlines; whereas, the third method relies on non preemptive execu-tion. We compare these techniques by illustrating examples, pointing out advantages and disadvantages, and evaluat-ing their effects in control applications by simulation. It is found that the deadline advancement method gives the bet-ter control performance for most configurations. 1