A SIMULATION-DRIVEN FRAMEWORK FOR NETWORK-AWARE PERFORMANCE EVALUATION OF IOT SYSTEMS

Abstract

Selecting and deploying an appropriate wireless sensor network (WSN) is an important challenge in IoT system design. Evaluating different WSN configurations through physical deployment can be costly and time-consuming. This study proposes a simulation-driven framework that integrates a simulated WSN with an MQTT-based IoT communication infrastructure to enable network-aware performance evaluation prior to physical deployment. An SDN-WISE-based WSN was implemented using the Cooja simulator, and the generated sensor traffic was forwarded to a Mosquitto-based MQTT cluster via a socket-based integration mechanism. Unlike conventional approaches that use independent traffic generators, the MQTT workload in the proposed framework originates directly from the simulated WSN. Experiments with 24-, 36-, and 48-node scenarios showed that average end-to- end delay increased from 37.51 ms to 138.01 ms, while total application throughput increased from 142.51 bps to 281.12 bps. Packet delivery remained effectively near 100% across all scenarios. The proposed approach provides a controlled, repeatable environment for evaluating various WSN configurations and can reduce the need for multiple physical deployments in the early stages of IoT system design.