Accurate electricity load forecasting underpins smart-grid operation and broader economic planning. Yet multivariate load series are driven by weather, economic activity, and seasonal effects whose intertwined, scale-dependent dynamics make forecasting challenging. While graph neural networks (GNNs) capture spatio-temporal dependencies, they often underrepresent multi-scale structure. MTSGNN (multi-scale trend–seasonal GNN) is introduced to bridge this gap. MTSGNN couples a multi-scale trend–seasonal GNN module with a Hawkes-enhanced temporal decoder. The former decomposes load signals into multiple temporal scales and models cross-variable interactions at each scale, while the latter embeds a Hawkes process to capture decaying and self-/mutually exciting temporal influences. To effectively combine long-term trends with periodic variations, a Trend–Seasonal Spatio-Temporal Fusion mechanism is proposed, which jointly learns and integrates trend and seasonal representations across both space and time. MTSGNN is designed for multi-step load forecasting with a historical window of 120 time steps and a prediction horizon of 120 future steps. Evaluations on five real-world datasets demonstrate that MTSGNN consistently surpasses existing approaches for multi-step power load prediction, establishing a new benchmark in forecasting accuracy.
Accurate state estimation is essential for the real-time operation and control of modern distribution systems characterized by high renewable energy penetration, bidirectional power flows, and volatile loads. Conventional model-driven approaches such as the Weighted Least Squares (WLS) exhibit limited robustness under noisy and sparse measurements, while existing data-driven methods often neglect critical physical constraints inherent to power systems. To address these limitations, this paper proposes a physics-constrained Graph Attention Network (GAT) framework for distribution system state estimation (DSSE) that synergistically integrates data-driven learning with physical domain knowledge. The proposed method comprises three key components: (1) a Gaussian Mixture Model (GMM)-based data augmentation strategy that captures the stochastic characteristics of loads and distributed generation to generate synthetic samples consistent with actual operating distributions; (2) a GAT-based feature extractor with topology-aware admittance matrix embedding that effectively learns spatial dependencies and structural relationships among network nodes; and (3) a physics-constrained loss function that incorporates nodal power and voltage limit penalties to enforce operational feasibility. Comprehensive evaluations on the real-world 141-bus test system demonstrate that the proposed method achieves mean absolute error (MAE) reductions of 52.4% and 45.5% for voltage magnitude and angle estimation, respectively, compared to conventional Graph Convolutional Network (GCN)-based approaches. These results validate the superior accuracy, robustness, and adaptability of the proposed framework under challenging measurement conditions.
This study proposes dynamic resource allocation and coordinated dispatch based on a source–load association graph for an electric–gas–heat system with wind, photovoltaics, fixed and mobile storage, power-to-gas (P2G), combined heat and power (CHP), and soft open points (SOPs). At each operating update, storage states, mobile-storage location and availability, and forecast profiles determine five typed relations and the subgraph classifications. Capacity-weighted centering then maps the state scores to time-varying device bounds without changing installed capacities or locations. The coordinated dispatch is formulated as a mixed-integer second-order cone program with SOC DistFlow constraints and an SOS2 gas-flow approximation. For the normal operating day, graph-guided dispatch yields an operating cost of 51,996.84 CNY, compared with 52,294.33 CNY for static equal-budget allocation and 52,829.05 CNY for topology-only allocation. The corresponding reductions are 0.5689% and 1.5753%, respectively, while all three policies serve 100% of demand and use 100% of available renewable energy within numerical tolerance. The graph-guided solution reaches a 0.0340% optimality gap, supporting its operating-cost advantage for the tested day.