Efficient and Generalized Decentralized Monitoring of Regular Languages
This addresses the challenge of distributed system monitoring for applications requiring real-time detection of specification violations, though it appears incremental as it builds on prior decentralized monitoring approaches.
The paper tackles the problem of decentralized monitoring of regular languages without a central observation point, developing an efficient algorithm that uses state machines to minimize message size and number, with experimental results showing it outperforms the previous most general method on new metrics.
The main contribution of this paper is an efficient and generalized decentralized monitoring algorithm allowing to detect satisfaction or violation of any regular specification by local monitors alone in a system without central observation point. Our algorithm does not assume any form of synchronization between system events and communication of monitors, uses state machines as underlying mechanism for efficiency, and tries to keep the number and size of messages exchanged between monitors to a minimum. We provide a full implementation of the algorithm with an open-source benchmark to evaluate its efficiency in terms of number, size of exchanged messages, and delay induced by communication between monitors. Experimental results demonstrate the effectiveness of our algorithm which outperforms the previous most general one along several (new) monitoring metrics.