Inventory Demand Forecasting System for Power Grid Systems

Efficient inventory planning is essential for timely execution of POWERGRID's large-scale power transmission projects, where delays can impact national energy distribution and costs.Traditional manual forecasting methods fail to account for dynamic factors such as seasonal variations, geographic challenges, and fluctuating budgets.This study proposes an AI-Based Inventory Demand Forecasting System that uses machine learning models like Random Forest, XGBoost, and LSTM to predict material requirements with higher accuracy.The system integrates historical data, project attributes, and environmental variables to minimize shortages, overstocking, and procurement delays.A real-time dashboard provides visual forecasts and alerts, enabling informed and proactive decision-making.The proposed solution enhances supply chain efficiency and offers a scalable model for other infrastructure sectors.