Energy-Efficient Wake-Up Signalling for Machine-Type Devices Based on Traffic-Aware Long Short-Term Memory Prediction

Reducing energy consumption is a pressing issue in low-power machine-type communication (MTC) networks. In this regard, the Wake-up Signal (WuS) technology, which aims to minimize consumed by radio interface of devices (MTDs), stands as promising solution. However, state-of-the-art WuS mechanisms use static operational parameters, so they cannot efficiently adapt system dynamics. To overcome this, we design simple but efficient neural network predict MTC traffic patterns and configure accordingly. Our proposed forecasting (FWuS) leverages an accurate long-short term memory (LSTM)- based prediction that allows extending sleep time MTDs avoiding frequent page monitoring occasions idle state. Simulation results show effectiveness our approach. The errors are shown be below 4%, being false alarm miss-detection probabilities respectively 8.8% 1.3%. terms reduction, FWuS can outperform best benchmark mechanism up 32%. Finally, certify ability dynamically density changes, promoting scalability