Real-time processing and networking

For many applications, the value of data diminishes over time. For example, in situations where data-informed decisions need to be made in a fraction of a second, data that take ten seconds to be processed would have little value. It’s also necessary to get data processing results to the right people at the right time.

CSL researchers are looking to develop next-generation technology that could be hundreds of times faster than what is possible today. In a different vein, multimodal Internet-of-Things (IoT) data can be expected to be highly variable, and processing needs for different applications are expected to have very different time scales. It is imperative to have resource management tools for such networks that can adapt and prioritize the assignment of resources to meet a variety of application needs. This is challenging in any networking environment, but is even more so at a large scale, over wireless and heterogeneous networks, and where time sensitivities and accurate synchronization of data are vital. CSL researchers are exploring potential solutions based on fundamental communication theory and quality-of-service and quality-of-experience paradigms to arrive at answers for network configurations.