A World Model framework with digital twin for scheduling demand-side resources under systemic complexity

Modern power grids face profound challenges in scheduling massive, heterogeneous demand-side resources (DSRs), whose collective behaviors often lead to systemic unpredictability and scheduling inaccuracies. Traditional methods, often based on simplified models, struggle to manage this emergent complexity. To address this gap, this paper introduces MetaGrid, a novel digital-twin-enhanced World Model framework designed for proactive and prescient DSR scheduling. The MetaGrid architecture is composed of four integral, closed-loop building blocks: a General Simulator for multi-path deduction, a Situational Perceiver for holistic cognition, an Intelligent Decision-Maker for autonomous optimization, and a Unified Verifier for ensuring trustworthy iteration. By integrating principles from complexity science with data-intensive machine learning, MetaGrid creates a high-fidelity metaverse to model and manage DSR ecosystems. The framework’s core capabilities are demonstrated through an energy storage system scheduling case, where an intelligent agent, guided by the World Model, learns to autonomously balance real-time electricity costs against physical battery degradation constraints. This preliminary validation showcases MetaGrid’s potential as a powerful tool for navigating the complexities of future energy systems, transforming scheduling from a reactive control problem into a process of continuous, adaptive learning. • Cross-disciplinary synergy : The framework integrates concepts from complexity science, cyber–physical system modeling, multi-agent reinforcement learning, and data-driven energy control, enabling a unified sandbox to orchestrate planning, operation, and adaptive optimization across temporal and spatial scales. • Field-validated findings : Based on deployments in Anhui and Henan provinces, the platform reveals the extent of DR performance deviation in real-world systems—where declared and actual demand responses differ by up to 16x, with effective accuracy rates below 20%. This confirms the systemic nature of the DR inaccuracy problem. • Quantified improvements : Experimental simulations show that platform-supported control strategies improve effective DR response rates to over 70%, reduce energy arbitrage costs by 12%, and maintain forecasting error margins within 6%.