Ehud Altman, Kenneth R. Brown, et al.
PRX Quantum
A simulation environment is very useful in analyzing sensor networks, but the development of a sensor simulation environment which can scale to a very large number of elements is hard to obtain using traditional simulation systems, or customized simulation environments. The desired level of scalability and high volumes are hard to achieve in customized simulation environments. One possible approach to obtain scalable simulation is by using commercially available messaging systems. Such messaging systems, e.g. IBM WebSphere MQ system or OSMQ, are designed to operate at a very high bandwidth of message transfers rate and number of interacting message queue end-points. However, the communications abstractions offered by message queue systems are very different from the communications abstractions required by sensor networks. In this paper, we describe an approach to map the communication abstractions of sensor network simulation systems to those of underlying message queue systems. We describe how issues related to message localization, propagation delays and error rates can be effectively handled, and a highly scalable infrastructure for message simulation be deployed.
Ehud Altman, Kenneth R. Brown, et al.
PRX Quantum
R.B. Morris, Y. Tsuji, et al.
International Journal for Numerical Methods in Engineering
Imran Nasim, Michael E. Henderson
Mathematics
Jianke Yang, Robin Walters, et al.
ICML 2023