Season-Independent PV Disaggregation Using Multi-Scale Net Load Temporal Feature Extraction and Weather Factor Fusion

2024-11-29

2024 IEEE 8th Conference on Energy Internet and Energy System Integration (EI2)

AI Summary

Accurately isolating distributed photovoltaic (PV) generation from grid net load remains challenging due to seasonal concept drift and dynamic coupling with meteorological variables. To address this, we propose a hierarchical interpolation and multi-head self-attention co-modeling framework. Hierarchical interpolation enables multi-scale temporal feature disentanglement of load series, while weather factor fusion encoding—combined with a dynamic attention mechanism—explicitly captures the nonlinear, time-varying dependencies between PV output and meteorological covariates. The resulting end-to-end time-series regression model significantly enhances cross-seasonal generalization. Evaluated on a real-world distribution network dataset, our method reduces the average PV generation separation error by 32.7% compared to baseline approaches. This improvement provides a scalable, data-driven foundation for fine-grained monitoring and intelligent control of distributed energy resources.

Technology Category

• Search and Optimization: Distributed Search
• Computer Vision: Multi-modal Vision
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

With the advancement of energy Internet and energy system integration, the increasing adoption of distributed photovoltaic (PV) systems presents new challenges on smart monitoring and measurement for utility companies, particularly in separating PV generation from net electricity load. Existing methods struggle with feature extraction from net load and capturing the relevance between weather factors. This paper proposes a PV disaggregation method that integrates Hierarchical Interpolation (HI) and multi-head self-attention mechanisms. By using HI to extract net load features and multi-head self-attention to capture the complex dependencies between weather factors, the method achieves precise PV generation predictions. Simulation experiments demonstrate the effectiveness of the proposed method in real-world data, supporting improved monitoring and management of distributed energy systems.

Problem

• Separating PV generation from net electricity load
• Improving feature extraction from net load data
• Capturing weather factor dependencies for PV prediction

Innovation

• Hierarchical Interpolation for net load feature extraction
• Multi-head self-attention for weather factor dependencies
• Season-independent PV disaggregation with high accuracy