S4ConvD: Adaptive Scaling and Frequency Adjustment for Energy-Efficient Sensor Networks in Smart Buildings

TL;DR

S4ConvD is a novel convolutional model that improves energy consumption prediction in smart buildings by capturing complex patterns efficiently, with enhanced runtime and resource efficiency suitable for real-time deployment.

Contribution

The paper introduces S4ConvD, a new convolutional variant of Deep State Space Models with adaptive scaling and frequency adjustments for energy prediction in resource-constrained environments.

Findings

S4ConvD outperforms existing benchmarks on the ASHRAE dataset.

Significant GPU runtime improvements via Block Tiling optimization.

Open-source code and dataset available for further research.

Abstract

Predicting energy consumption in smart buildings is challenging due to dependencies in sensor data and the variability of environmental conditions. We introduce S4ConvD, a novel convolutional variant of Deep State Space Models (Deep-SSMs), that minimizes reliance on extensive preprocessing steps. S4ConvD is designed to optimize runtime in resource-constrained environments. By implementing adaptive scaling and frequency adjustments, this model shows to capture complex temporal patterns in building energy dynamics. Experiments on the ASHRAE Great Energy Predictor III dataset reveal that S4ConvD outperforms current benchmarks. Additionally, S4ConvD benefits from significant improvements in GPU runtime through the use of Block Tiling optimization techniques. Thus, S4ConvD has the potential for practical deployment in real-time energy modeling. Furthermore, the complete codebase and dataset are accessible on GitHub, fostering open-source contributions and facilitating further research. Our method also promotes resource-efficient model execution, enhancing both energy forecasting and the potential integration of renewable energy sources into smart grid systems.