Individualized Federated Learning for Traffic Prediction with Error Driven Aggregation

TL;DR

NeighborFL introduces a real-time, individualized Federated Learning framework for traffic prediction that forms dynamic, location-aware local model groups using a haversine-distance heuristic and error-driven evaluation. By replacing a single global model with per-device Aggregated Models that include selected Favorite Neighbors, NeighborFL mitigates non-IID data issues and enhances adaptation to changing traffic conditions. Experimental results on the PEMS-BAY dataset show that NeighborFL, especially with pretrained initialization, reduces average device MSE and outperforms NaiveFL in the majority of devices, with gains up to $16.9\%$ in some settings. The approach enables scalable, privacy-preserving, edge-assisted TP with potential for handling non-recurrent events and malfunctioning detectors in smart city deployments.

Abstract

Low-latency traffic prediction is vital for smart city traffic management. Federated Learning has emerged as a promising technique for Traffic Prediction (FLTP), offering several advantages such as privacy preservation, reduced communication overhead, improved prediction accuracy, and enhanced adaptability to changing traffic conditions. However, majority of the current FLTP frameworks lack a real-time model updating scheme, which hinders their ability to continuously incorporate new incoming traffic data and adapt effectively to the changing dynamics of traffic trends. Another concern with the existing FLTP frameworks is their reliance on the conventional FL model aggregation method, which involves assigning an identical model (i.e., the global model) to all traffic monitoring devices to predict their individual local traffic trends, thereby neglecting the non-IID characteristics of traffic data collected in different locations. Building upon these findings and harnessing insights from reinforcement learning, we propose NeighborFL, an individualized real-time federated learning scheme that introduces a haversine distance-based and error-driven, personalized local models grouping heuristic from the perspective of each individual traffic node. This approach allows NeighborFL to create location-aware and tailored prediction models for each client while fostering collaborative learning. Simulations demonstrate the effectiveness of NeighborFL, offering improved real-time prediction accuracy over three baseline models, with one experimental setting showing a 16.9% reduction in MSE value compared to a naive FL setting.

Figures (4)

• Figure 1: A high-level overview of NeighborFL and its comparison with the Conventional FL approach.
• Figure 2: Map of PEMS-BAY and the study region containing our 26 selected devices for experiments.
• Figure 3: Prediction curves of 26 devices in the last 24 rounds among baseline methods and NeighborFL L1
• Figure 4: Smoothed MSE curves of real-time predictions of 26 devices throughout the entire simulation