Enhancing QoS with LSTM-Based Prediction for Congestion-Aware Aggregation Scheduling in Edge Federated Learning

초록

The advancement of the sensing capabilities of end devices drives a variety of data-intensive insights, yielding valuable information for modelling intelligent industrial applications. To apply intelligent models in 5G and beyond, edge intelligence integrates edge computing systems and deep learning solutions, which enables distributed model training and inference. Edge federated learning (EFL) offers collaborative edge intelligence learning with distributed aggregation capabilities, promoting resource efficiency, participant inclusivity, and privacy preservation. However, the quality of service (QoS) faces challenges due to congestion problems that arise from the diverse models and data in practical architectures. In this paper, we develop a modified long short-term memory (LSTM)-based congestion-aware EFL (MLSTM-CEFL) approach that aims to enhance QoS in the final model convergence between end devices, edge aggregators, and the global server. Given the diversity of service types, MLSTM-CEFL proactively detects the congestion rates, adequately schedules the edge aggregations, and effectively prioritizes high mission-critical serving resources. The proposed system is formulated to handle time series analysis from local/edge model parameter loading, weighing the configuration of resource pooling properties at specific congestion intervals. The MLSTM-CEFL policy orchestrates the establishment of long-term paths for participant-aggregator scheduling and follows the expected QoS metrics after final averaging in multiple industrial application classes.

키워드