Extracting Actionable Insights from Building Energy Data using Vision LLMs on Wavelet and 3D Recurrence Representations
This provides a scalable and interpretable framework for energy analytics, addressing domain-specific problems for building energy management, though it is incremental as it adapts existing VLLMs to new data representations.
The paper tackled the challenge of analyzing complex building energy time-series by fine-tuning visual language large models (VLLMs) on 3D graphical representations, achieving lower validation losses (e.g., 0.0952 with CWTs) compared to raw data for anomaly detection.
The analysis of complex building time-series for actionable insights and recommendations remains challenging due to the nonlinear and multi-scale characteristics of energy data. To address this, we propose a framework that fine-tunes visual language large models (VLLMs) on 3D graphical representations of the data. The approach converts 1D time-series into 3D representations using continuous wavelet transforms (CWTs) and recurrence plots (RPs), which capture temporal dynamics and localize frequency anomalies. These 3D encodings enable VLLMs to visually interpret energy-consumption patterns, detect anomalies, and provide recommendations for energy efficiency. We demonstrate the framework on real-world building-energy datasets, where fine-tuned VLLMs successfully monitor building states, identify recurring anomalies, and generate optimization recommendations. Quantitatively, the Idefics-7B VLLM achieves validation losses of 0.0952 with CWTs and 0.1064 with RPs on the University of Sharjah energy dataset, outperforming direct fine-tuning on raw time-series data (0.1176) for anomaly detection. This work bridges time-series analysis and visualization, providing a scalable and interpretable framework for energy analytics.