UrbanInsight: A Distributed Edge Computing Framework with LLM-Powered Data Filtering for Smart City Digital Twins

2025-08-31

AI Summary

To address the challenges of large-scale, high-latency, and fragmented insights arising from multi-source heterogeneous data in smart cities, this paper proposes a distributed edge computing framework tailored for urban digital twins. The framework integrates physics-informed neural networks (PINNs), multimodal data fusion, knowledge graph representation, and large language models (LLMs), introducing a novel intelligent architecture that jointly leverages physical law constraints and semantic understanding. Critically, it enables LLMs to dynamically generate context-aware edge filtering and decision rules. Experimental results demonstrate that the system achieves low latency (<200 ms) and high-consistency situational awareness under resource-constrained edge conditions, improves data processing efficiency by 3.2×, and enhances decision interpretability. Collectively, the framework significantly boosts the responsiveness, trustworthiness, and scalability of digital twin systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Cities today generate enormous streams of data from sensors, cameras, and connected infrastructure. While this information offers unprecedented opportunities to improve urban life, most existing systems struggle with scale, latency, and fragmented insights. This work introduces a framework that blends physics-informed machine learning, multimodal data fusion, and knowledge graph representation with adaptive, rule-based intelligence powered by large language models (LLMs). Physics-informed methods ground learning in real-world constraints, ensuring predictions remain meaningful and consistent with physical dynamics. Knowledge graphs act as the semantic backbone, integrating heterogeneous sensor data into a connected, queryable structure. At the edge, LLMs generate context-aware rules that adapt filtering and decision-making in real time, enabling efficient operation even under constrained resources. Together, these elements form a foundation for digital twin systems that go beyond passive monitoring to provide actionable insights. By uniting physics-based reasoning, semantic data fusion, and adaptive rule generation, this approach opens new possibilities for creating responsive, trustworthy, and sustainable smart infrastructures.

Problem

• Managing massive urban data streams from sensors with scale and latency challenges
• Integrating fragmented sensor insights into unified semantic knowledge representations
• Enabling real-time adaptive decision-making under constrained edge computing resources

Innovation

• Distributed edge computing framework
• LLM-powered adaptive data filtering
• Knowledge graph semantic data fusion