فصلنامه تخصصی فناوری اطلاعات و ارتباطات
نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه مهندسی کامپیوتر ،واحد همدان ، دانشگاه آزاد اسلامی، همدان، ایران
2 گروه مهندسی کامپیوتر ،واحد همدان ، دانشگاه آزاد اسلامی ، همدان ، ایران
کلیدواژهها
عنوان مقاله English
نویسندگان English
Wireless Sensor Networks (WSNs) have emerged as one of the key technologies in recent decades due to their rapid deployability, low cost, and wide range of applications in fields such as the Internet of Things (IoT), environmental monitoring, smart agriculture, and critical systems. However, the hardware and software limitations of sensor nodes — including low processing power and limited energy resources — make these networks vulnerable to failures and disruptions, turning reliability into a fundamental challenge.
In this study, a novel framework based on Tiny Machine Learning (TinyML) is proposed to enhance reliability and optimize energy consumption in WSNs. The proposed architecture consists of four key modules — anomaly detection, failure prediction, intelligent data compression, and adaptive routing — which are deployed locally at the node level to enable fast processing, reduce communication overhead, and enable intelligent resource management.
Simulation results demonstrated that the proposed method not only increases the network lifetime and significantly reduces energy consumption but also improves data quality, communication stability, and responsiveness to abnormal events.
The findings of this research indicate that leveraging TinyML can open new horizons in the design of intelligent WSNs and provide a solid foundation for developing future large-scale applications in dynamic environments.
کلیدواژهها English
