A Gap in Time: The Challenge of Processing Heterogeneous IoT Point Data in Buildings
- URL: http://arxiv.org/abs/2405.14267v1
- Date: Thu, 23 May 2024 07:45:48 GMT
- Title: A Gap in Time: The Challenge of Processing Heterogeneous IoT Point Data in Buildings
- Authors: Xiachong Lin, Arian Prabowo, Imran Razzak, Hao Xue, Matthew Amos, Sam Behrens, Stephen White, Flora D. Salim,
- Abstract summary: The need for sustainable energy solutions has driven the integration of digitalized buildings into the power grid.
incorporating IoT point data within deep-learning frameworks for energy management presents a complex challenge.
This paper comprehensively analyzes the multifaceted heterogeneity present in real-world building IoT data streams.
- Score: 15.06538531625261
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The growing need for sustainable energy solutions has driven the integration of digitalized buildings into the power grid, utilizing Internet-of-Things technology to optimize building performance and energy efficiency. However, incorporating IoT point data within deep-learning frameworks for energy management presents a complex challenge, predominantly due to the inherent data heterogeneity. This paper comprehensively analyzes the multifaceted heterogeneity present in real-world building IoT data streams. We meticulously dissect the heterogeneity across multiple dimensions, encompassing ontology, etiology, temporal irregularity, spatial diversity, and their combined effects on the IoT point data distribution. In addition, experiments using state-of-the-art forecasting models are conducted to evaluate their impacts on the performance of deep-learning models for forecasting tasks. By charting the diversity along these dimensions, we illustrate the challenges and delineate pathways for future research to leverage this heterogeneity as a resource rather than a roadblock. This exploration sets the stage for advancing the predictive abilities of deep-learning algorithms and catalyzing the evolution of intelligent energy-efficient buildings.
Related papers
- BiTSA: Leveraging Time Series Foundation Model for Building Energy Analytics [15.525789412274587]
This paper presents the design of an interactive visualization tool, BiTSA.
The tool enables building managers to interpret complex energy data quickly and take immediate, data-driven actions based on real-time insights.
arXiv Detail & Related papers (2024-11-20T23:49:06Z) - Exploring Capabilities of Time Series Foundation Models in Building Analytics [15.525789412274587]
Internet of Things (IoT) networks have transformed the management and optimization of building energy consumption.
We conduct a comprehensive benchmarking of two publicly available IoT datasets.
Our analysis shows that single-modal models demonstrate significant promise in overcoming the complexities of data variability and physical limitations in buildings.
arXiv Detail & Related papers (2024-10-28T02:49:22Z) - Enabling High Data Throughput Reinforcement Learning on GPUs: A Domain Agnostic Framework for Data-Driven Scientific Research [90.91438597133211]
We introduce WarpSci, a framework designed to overcome crucial system bottlenecks in the application of reinforcement learning.
We eliminate the need for data transfer between the CPU and GPU, enabling the concurrent execution of thousands of simulations.
arXiv Detail & Related papers (2024-08-01T21:38:09Z) - Speech Emotion Recognition under Resource Constraints with Data Distillation [64.36799373890916]
Speech emotion recognition (SER) plays a crucial role in human-computer interaction.
The emergence of edge devices in the Internet of Things presents challenges in constructing intricate deep learning models.
We propose a data distillation framework to facilitate efficient development of SER models in IoT applications.
arXiv Detail & Related papers (2024-06-21T13:10:46Z) - Best Practices and Lessons Learned on Synthetic Data [83.63271573197026]
The success of AI models relies on the availability of large, diverse, and high-quality datasets.
Synthetic data has emerged as a promising solution by generating artificial data that mimics real-world patterns.
arXiv Detail & Related papers (2024-04-11T06:34:17Z) - Effective Intrusion Detection in Heterogeneous Internet-of-Things Networks via Ensemble Knowledge Distillation-based Federated Learning [52.6706505729803]
We introduce Federated Learning (FL) to collaboratively train a decentralized shared model of Intrusion Detection Systems (IDS)
FLEKD enables a more flexible aggregation method than conventional model fusion techniques.
Experiment results show that the proposed approach outperforms local training and traditional FL in terms of both speed and performance.
arXiv Detail & Related papers (2024-01-22T14:16:37Z) - Exploring Artificial Intelligence Methods for Energy Prediction in
Healthcare Facilities: An In-Depth Extended Systematic Review [0.9208007322096533]
This study conducted a literature review, utilizing the PRISMA framework, of articles that employed machine learning and artificial intelligence techniques for predicting energy consumption in hospital buildings.
This review revealed a diverse range of data inputs influencing energy prediction, with occupancy and meteorological data emerging as significant predictors.
The findings underscore the immense potential of AI in optimizing hospital energy consumption but also highlight the need for more comprehensive and granular research.
arXiv Detail & Related papers (2023-11-27T13:30:20Z) - Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks.
Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios.
New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
arXiv Detail & Related papers (2023-08-27T03:55:28Z) - Smart Home Energy Management: VAE-GAN synthetic dataset generator and
Q-learning [15.995891934245334]
We propose a novel variational auto-encoder-generative adversarial network (VAE-GAN) technique for generating time-series data on energy consumption in smart homes.
We tested the online performance of Q-learning-based HEMS with real-world smart home data.
arXiv Detail & Related papers (2023-05-14T22:22:16Z) - Distributed intelligence on the Edge-to-Cloud Continuum: A systematic
literature review [62.997667081978825]
This review aims at providing a comprehensive vision of the main state-of-the-art libraries and frameworks for machine learning and data analytics available today.
The main simulation, emulation, deployment systems, and testbeds for experimental research on the Edge-to-Cloud Continuum available today are also surveyed.
arXiv Detail & Related papers (2022-04-29T08:06:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.