Knowledge-infused deep learning diagnosis model with self-assessment for smart management in HVAC systems

Du, Zhimin; Liang, Xinbin; Chen, Siliang; Zhu, Xu; Chen, Kang; Jin, Xinqiao

doi:10.1016/j.energy.2022.125969

Cited by 13 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, in the studies dealing with DL, researchers focused on user preferences and not on the number of people in the building, which could be empty, full, or partially occupied. Enhancing the use of energy in buildings has been extensively researched in the literature, particularly in managing HAVC systems by incorporating DL techniques, as clearly revised in the studies [24][25][26][27][28][29].…”

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Power Management Models for Buildings: A Comparative Analysis

Talib,

Croock

2024

JESA

View full text Add to dashboard Cite

Power management in several sectors poses the problem of conserving the consumed power while satisfying the imposed conditions It is considered as a proactive control and management of the organization's energy consumption to save use and reduce energy expenses. Therefore, there is an actual need to include smart energy management systems in buildings in order to reduce the consumed energy. In this work, a comparative analysis is presented to evaluate deep and machine-learning approaches in the context of intelligent models for conserving power in smart buildings. The deep learning model is structured by using Deep Neural Networks (DNN), while machine learning models are represented by Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Naive Bayes (NB). These models adopt three classes: full (power in full consumption), select (power in partial consumption), and shout down (no power consumption). Moreover, feature reduction methods of Boruta and Principal Component Analysis (PCA) are implemented to reduce the complexity of the models. The proposed models are trained and tested using a measured dataset for a building. Comparison results of the proposed models showed that the Random Forest attracts more attention regarding classification accuracy by 100% and a reasonable classification time of 1.23 seconds. The effectiveness of the comparative analysis which indicating the highest accuracy results for RF makes it as a suitable model to be implemented as an optimal one in real-time power management systems.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Intelligent Power Management Models for Buildings: A Comparative Analysis

Talib,

Croock

2024

JESA

View full text Add to dashboard Cite

show abstract

“…[27] utilized cWGAN to generate synthetic energy consumption data and generated realistic energy consumption data by given labels as a condition imitating real data distribution. [28] used deep learning GANs in generating electricity consumption and fault diagnosis to develop smart management tools for heating, ventilation, and air conditioning (HVAC). The authors showed that deep learning GAN can help to increase the fault diagnosis accuracy in electricity consumption.…”

Section: Literature Reviewmentioning

confidence: 99%

Generative adversarial network for load data generation: Türkiye energy market case

Yilmaz

2023

Mathematical Modelling and Numerical Simulation With Applications

View full text Add to dashboard Cite

Load modeling is crucial in improving energy efficiency and saving energy sources. In the last decade, machine learning has become favored and has demonstrated exceptional performance in load modeling. However, their implementation heavily relies on the quality and quantity of available data. Gathering sufficient high-quality data is time-consuming and extremely expensive. Therefore, generative adversarial networks (GANs) have shown their prospect of generating synthetic data, which can solve the data shortage problem. This study proposes GAN-based models (RCGAN, TimeGAN, CWGAN, and RCWGAN) to generate synthetic load data. It focuses on Türkiye's electricity load and generates realistic synthetic load data. The educated synthetic load data can reduce prediction errors in load when combined with recorded data and enhance risk management calculations.

show abstract