Development of an Agentic AI Framework for Power Infrastructure Monitoring and Resiliency

Abstract

Monitoring critical infrastructure (CI), particularly national power distribution networks in developing countries such as Uganda, remains a significant challenge due to the limited deployment, high operational costs, and maintenance requirements of conventional monitoring technologies, including Supervisory Control and Data Acquisition (SCADA) systems, field sensors, and roadside surveillance infrastructure. These limitations often result in inadequate real-time situational awareness during service disruptions, delaying incident detection and response. Meanwhile, social media platforms such as X (formerly Twitter) have emerged as valuable sources of real-time, user-generated information that can provide rapid insights into infrastructure-related events. However, the unstructured, noisy, multilingual, and context-dependent nature of social media data presents significant challenges for traditional artificial intelligence and data analytics approaches. This study proposes a fully automated situational awareness framework that leverages Generative Artificial Intelligence, specifically Large Language Models (LLMs), to extract, analyse, and synthesise actionable information from social media streams. The proposed pipeline integrates Twitter API-based data collection, LLM-driven relevance filtering and event classification, geolocation inference for identifying affected areas, and visualisation tools for presenting incident information in an accessible format. Given the limitations of the free-tier Twitter API, a synthetic dataset of 150 tweets was constructed to support system development, prompt tuning, and evaluation. Synthetic data generation was carried out using Grok, a generative AI model with web search integration, which was instructed to search for current infrastructure conditions and generate realistic tweets that reflected those conditions. By combining natural language understanding with automated information extraction, the system transforms dispersed social media posts into meaningful intelligence that can support infrastructure operators and emergency response teams. A case study focusing on power disruption monitoring in Uganda was used to evaluate the effectiveness of the proposed approach. The study also addresses key challenges, including ambiguous location references, local language expressions, informal communication styles, and variations in outage-related terminology. The findings suggest that the proposed framework offers a scalable, cost-effective, and adaptable solution for enhancing real-time monitoring and situational awareness of critical infrastructure in resource-constrained environments.