Cluster Aggregated GAN (CAG): A Cluster-Based Hybrid Model for Appliance Pattern Generation

2025-12-25

AI Summary

To address data scarcity, modeling distortion, and training instability of generative adversarial networks (GANs) in non-intrusive load monitoring (NILM), this paper proposes a behavior-clustering-based hybrid generative framework. Unlike existing GAN approaches that uniformly model all appliances, our method innovatively integrates clustering as an active component—dynamically assigning dedicated generation pathways based on behavioral distinctions between intermittent and continuous appliances. Specifically, we employ a conditional GAN to model switching events for intermittent devices and design an LSTM-based sequence compression generator for continuous devices. This dual-branch architecture significantly improves generation fidelity (reduced Fréchet Inception Distance), diversity (increased Diversity Score), and training stability (fewer convergence steps). Extensive experiments on the UVIC dataset demonstrate consistent superiority over state-of-the-art baselines, validating the framework’s high fidelity, strong generalizability, and interpretability.

Technology Category

• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Synthetic appliance data are essential for developing non-intrusive load monitoring algorithms and enabling privacy preserving energy research, yet the scarcity of labeled datasets remains a significant barrier. Recent GAN-based methods have demonstrated the feasibility of synthesizing load patterns, but most existing approaches treat all devices uniformly within a single model, neglecting the behavioral differences between intermittent and continuous appliances and resulting in unstable training and limited output fidelity. To address these limitations, we propose the Cluster Aggregated GAN framework, a hybrid generative approach that routes each appliance to a specialized branch based on its behavioral characteristics. For intermittent appliances, a clustering module groups similar activation patterns and allocates dedicated generators for each cluster, ensuring that both common and rare operational modes receive adequate modeling capacity. Continuous appliances follow a separate branch that employs an LSTM-based generator to capture gradual temporal evolution while maintaining training stability through sequence compression. Extensive experiments on the UVIC smart plug dataset demonstrate that the proposed framework consistently outperforms baseline methods across metrics measuring realism, diversity, and training stability, and that integrating clustering as an active generative component substantially improves both interpretability and scalability. These findings establish the proposed framework as an effective approach for synthetic load generation in non-intrusive load monitoring research.

Problem

• Generates synthetic appliance data for load monitoring algorithms
• Addresses behavioral differences between intermittent and continuous appliances
• Improves training stability and output fidelity in data generation

Innovation

• Cluster-based hybrid GAN for appliance pattern generation
• Separate branches for intermittent and continuous appliances
• Clustering module groups patterns and allocates dedicated generators