A Systematic Review of Building Energy Consumption Prediction: From Perspectives of Load Classification, Data-Driven Frameworks, and Future Directions

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3086 - 3086

Published: March 12, 2025

The rapid development of machine learning and artificial intelligence technologies has promoted the widespread application data-driven algorithms in field building energy consumption prediction. This study comprehensively explores diversified prediction strategies for different time scales, types, forms, constructing a framework this field. With process as core, it deeply analyzes four key aspects data acquisition, feature selection, model construction, evaluation. review covers three acquisition methods, considers seven factors affecting loads, introduces efficient extraction techniques. Meanwhile, conducts an in-depth analysis mainstream models, clarifying their unique advantages applicable scenarios when dealing with complex data. By systematically combing existing research, paper evaluates advantages, disadvantages, applicability each method provides insights into future trends, offering clear research directions guidance researchers.

Language: Английский

---

Attention-empowered transfer learning method for HVAC sensor fault diagnosis in dynamic building environments

Building and Environment, Journal Year: 2023, Volume and Issue: 250, P. 111148 - 111148

Published: Dec. 28, 2023

Language: Английский

---

Optimizing Slogan Classification in Ubiquitous Learning Environment: A Hierarchical Multilabel Approach with Fuzzy Neural Networks

Published: Jan. 1, 2024

Language: Английский

---

Intrinsically interpretable machine learning-based building energy load prediction method with high accuracy and strong interpretability

Energy and Built Environment, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Black-box models have demonstrated remarkable accuracy in forecasting building energy loads. However, they usually lack interpretability and do not incorporate domain knowledge, making it difficult for users to trust their predictions practical applications. One important interesting question remains unanswered: is possible use intrinsically interpretable achieve comparable that of black-box models? With an aim answering this question, study proposes machine learning-based method forecast It creatively combines two learning algorithms: clustering decision trees adaptive multiple linear regression. Clustering automatically identify various operation conditions, allowing the training tailored each condition. can reduce complexity model data, leading higher accuracy. Adaptive regression improved algorithm load prediction. adaptively modify coefficients according operations, enhancing non-linear fitting capability The proposed evaluated utilizing operational data from office building. results indicate exhibits both random forests extreme gradient boosting. Furthermore, shows significantly superior accuracy, with average improvement 10.2 %, compared some popular algorithms such as artificial neural networks, support vector regression, classification trees. As interpretability, reveals historical cooling loads are most crucial predicting under conditions. Additionally, outdoor air temperature has a significant contribution prediction during daytime on weekdays summer transition seasons. In future, will be valuable explore integrating laws physics into further enhance its interpretability.

Language: Английский

---

Unveiling the bright side and dark side of AI-based ChatGPT : a bibliographic and thematic approach

Journal of Decision System, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 27

Published: Oct. 11, 2024

The current research endeavour aims to examine the most recent advancements pertaining AI-powered ChatGPT in scholarly literature. Moreover, this examines both positive and negative aspects of utilisation across several sectors including business, research, society. data was collected from Scopus, using Preferred Reporting Items for Systematic Meta-Analysis (PRISMA) methodology. process scientific mapping carried out, wherein biblometric thematic analysis conducted. results suggest that there is a significant amount being conducted on subject, particularly fields healthcare education. Thematic reveals wide range issues, examination impact technology decision-making processes address complex business challenges. Theoretical perspectives underscore significance ethical deliberations, regulatory structures, interdisciplinary cooperation, user instruction advancement implementation Artificial Intelligence systems.

Language: Английский

---