Acquiring and incorporating state-dependent timing requirements

Some real-time systems are designed to deliver services to objects that are controlled by external sources. Their services must be delivered on a timely basis, and the system fails when some services are delivered too late. In general, the timing requirements of the system may change when the states of the objects monitored by the system change. Such a system may fail if the timing requirements which it is designed to meet are erroneous. It may underutilize resources and consequently be costly or unreliable if the requirements are too stringent. Hence, one must identify how changes in object states call for changes in system requirements and how these changes should be incorporated into the design and implementation of the system. This paper first describes a methodology to determine timing requirements and to take into account requirement changes at runtime. The method is based on several timing requirement determination schemes. Simulation data show that these schemes are effective for applications such as mobile IP hand-offs. The paper then discusses how to incorporate this methodology in the system architecture and in the development process.