In this paper, we propose a dynamic data transmission strategy for smart home environments that aims to optimize the Quality of Experience (QoE) by adaptively adjusting the data upload frequency based on the predicted trends in sensor data. Using the home wireless sensors monitoring dataset, we implement a deep learning model for accurate time series forecasting. In addition, an anomaly detection mechanism is used to identify critical events, requiring more frequent data uploads when important changes are detected. The QoE is quantified through a weighted average of several influencing factors, including data timeliness, timely upload of critical events, and transmission frequency. Our optimization objective is to maximize QoE while minimizing the number of transmissions, with an emphasis on reducing energy consumption through intelligent scheduling. The results demonstrate that our approach effectively balances data timeliness, transmission efficiency, and energy savings, leading to improved user satisfaction in smart home applications.

Low-power wireless networks are widely used to monitor crop growth in smart agriculture. However, there is a growing need for more fine-grained monitoring to improve the yield of certain fruits and vegetables. The system must maintain low power consumption of peripheral devices while still providing a satisfactory quality of experience (QoE) for more frequent queries. Conventional fixed-time communication between central and peripheral devices fails to offer a well-rounded solution to this trade-off problem. To achieve a better balance, we propose an LSTM-driven transmission scheduling method. By learning the user’s past query patterns, the LSTM predicts the time of future queries initiated by the users, allowing the system to plan data transmission between the central and peripheral nodes ahead of time. Our method also predicts the future pattern of collected data to ensure that significant changes are actively recorded, even if not queried. Compared to other machine learning methods, our LSTM prediction results have a smaller error. The simulation results demonstrate that our approach can greatly improve QoE while achieving lower power consumption.