Variable Step-Size LMS-Based Anti-Jamming Algorithm for Industrial IoT Communications over 2.4 GHz ISM Band

Industrial Internet of Things (IIoT) systems deployed in factory environments face severe narrowband interference in the 2.4 GHz ISM band, where ZigBee-based sensor networks coexist with Wi-Fi and Bluetooth devices operating under strong electromagnetic interference from industrial machinery. Conventional adaptive filters employing fixed step-size Least Mean Squares (LMS) algorithms fail under high Jammer-to-Noise Ratio (JNR) conditions, exhibiting numerical instability and bit error rates (BER) approaching 0.5. This paper proposes a Variable Step-Size LMS (VS-LMS) algorithm integrated with Direct Sequence Spread Spectrum (DSSS) modulation to address this limitation. The proposed step-size update rule adaptively scales the learning rate according to instantaneous filter error: μ(n)=μ min +(μ max -μ min ) · exp(-α·e 2 (n)) , enabling large step-sizes during convergence and small step-sizes under strong interference to maintain numerical stability. Python-based simulations under AWGN plus sinusoidal narrowband interference (JNR=25 dB) demonstrate that the proposed VS-LMS scheme reduces BER by 76.1% compared to conventional fixed-step LMS, recovering communication quality (BER=0.12) in scenarios where fixed-step LMS completely fails. The results confirm that the proposed software-layer approach provides a practical, hardware-agnostic solution for reliable IIoT communications in electromagnetically hostile factory environments.