☆ 4.6 Article

Study of the Data Augmentation Approach for Building Energy Prediction beyond Historical Scenarios

BUILDINGS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Energy & Fuels

A data-driven strategy using long short term memory models and reinforcement learning to predict building electricity consumption

Xinlei Zhou et al.

Summary: This paper presents a new strategy that integrates LSTM models and RL agents to forecast building electricity consumption. Results show that the proposed strategy can significantly improve prediction accuracy for buildings with large monthly variations in electricity consumption, while showing less improvement for those with insignificant variations.

APPLIED ENERGY (2022)

添加到收藏夹

Article Thermodynamics

Data-centric or algorithm-centric: Exploiting the performance of transfer learning for improving building energy predictions in data-scarce context

Cheng Fan et al.

Summary: Data-driven methods have become popular due to their convenience and accuracy, with transfer learning being used to enhance feasibility and robustness. This study investigates transfer learning performance in data-scarce context, aiming to draw conclusions and provide guidelines for developing cost-effective solutions.

ENERGY (2022)

添加到收藏夹

Article Construction & Building Technology

Building energy prediction using artificial neural networks: A literature survey

Chujie Lu et al.

Summary: This article surveys the research on using artificial neural networks (ANNs) for building energy prediction and summarizes the details and applications of twelve ANN architectures in this field. The article also discusses the challenges of choosing ANN architecture, improving prediction performance, and dealing with the lack of building energy data.

ENERGY AND BUILDINGS (2022)

添加到收藏夹

Article Thermodynamics

Development of a key-variable-based parallel HVAC energy predictive model

Huajing Sha et al.

Summary: Building HVAC systems consume significant amounts of energy, requiring accurate energy prediction for developing energy efficiency strategies. Data-driven predictive models have gained attention, with parallel predictive models being used to predict energy consumption based on historical data of similar buildings. However, the input features for this type of model are difficult to identify and collect. In this study, a novel key-variable-based parallel HVAC energy predictive model is proposed, utilizing informative input features and a simplified architecture. A general key-variable screening toolkit is developed to aid in the selection of key variables for the model. A case study of hotel buildings in eastern China is conducted, resulting in a parallel chiller energy predictive model with acceptable prediction accuracy.

BUILDING SIMULATION (2022)

添加到收藏夹

Article Thermodynamics

Federated learning-based short-term building energy consumption prediction method for solving the data silos problem

Junyang Li et al.

Summary: The study introduces a federated learning-based method to learn transferable knowledge from building operational data without leaking privacy. The federated model outperforms the standalone model in prediction accuracy and training time, providing a solution for the data silos problem in building energy management.

BUILDING SIMULATION (2022)

添加到收藏夹

Article Construction & Building Technology

A data mining research on office building energy pattern based on time- series energy consumption data

Xiaodong Liu et al.

Summary: This paper investigates the energy usage pattern of office buildings throughout the year using time-series energy consumption data. It employs innovative artificial intelligent algorithms for data mining and discovers the energy utilization issues through cluster analysis and association rule discovery. The findings reveal the wastage of energy after working hours and the significant impact of cooling energy on total energy consumption.

ENERGY AND BUILDINGS (2022)

添加到收藏夹

Article Construction & Building Technology

Hybrid approach for energy consumption prediction: Coupling data-driven and physical approaches

Kadir Amasyali et al.

Summary: This paper proposes a hybrid machine-learning approach for building energy consumption prediction, which learns the impact of outdoor weather conditions and occupant behavior to predict hourly cooling energy consumption. The experimental results demonstrate the promising prediction performance of the proposed approach.

ENERGY AND BUILDINGS (2022)

添加到收藏夹

Article Thermodynamics

A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions

Cheng Fan et al.

Summary: This study introduces a deep generative modeling-based data augmentation strategy to enhance short-term building energy predictions by generating high-quality synthetic energy data samples. Experimental results show that this method can significantly improve predictive performance, with important implications for practical applications in buildings.

BUILDING SIMULATION (2022)

添加到收藏夹

Review Thermodynamics

Review on occupancy detection and prediction in building simulation

Yan Ding et al.

Summary: The study focuses on the deviation of energy simulation results for buildings from actual consumption, attributing it mainly to inaccurate estimation of occupancy. Improving the accuracy level of occupancy prediction can notably reduce the error between reality and prediction. Despite various studies on occupancy, differences in detection, prediction, and validation methods still exist.

BUILDING SIMULATION (2022)

添加到收藏夹

Article Construction & Building Technology

The Hourly Energy Consumption Prediction by KNN for Buildings in Community Buildings

Goopyo Hong et al.

Summary: This study utilized the KNN algorithm to predict the hourly energy consumption of community buildings composed of different types of buildings. The results showed that the accuracy of the predictions was higher for summer and fall compared to spring and winter.

BUILDINGS (2022)

添加到收藏夹

Review Construction & Building Technology

Building Energy Prediction Models and Related Uncertainties: A Review

Jiaqi Yu et al.

Summary: This study provides a comprehensive review of building energy prediction models, discussing three types of prediction methods and analyzing the uncertainties in these models. The research gaps in predicting building energy consumption are summarized in order to guide the optimization of building energy prediction methods.

BUILDINGS (2022)

添加到收藏夹

Article Construction & Building Technology

Bayesian Calibration for Office-Building Heating and Cooling Energy Prediction Model

Yu Cui et al.

Summary: This paper introduces the application of Bayesian calibration (BC) method in building energy models, and presents a calibrated prediction model for office buildings in Guangdong, China. The model's accuracy meets the requirement of ASHRAE Guideline 14 and has significant implications for improving the quality and integrity of existing building energy databases.

BUILDINGS (2022)

添加到收藏夹

Article Construction & Building Technology

Building Energy Consumption Prediction Using a Deep-Forest-Based DQN Method

Qiming Fu et al.

Summary: In this paper, the authors proposed a deep-forest-based DQN method (DF-DQN) for energy consumption prediction, which achieves higher prediction accuracy and shorter computation time compared to other methods. The DF-DQN method replaces the action space, introduces deep forest for mapping, and constructs new states using state class probabilities.

BUILDINGS (2022)

添加到收藏夹

Review Energy & Fuels

Transfer learning for smart buildings: A critical review of algorithms, applications, and future perspectives

Giuseppe Pinto et al.

Summary: This study provides a comprehensive overview of the applications of transfer learning in smart buildings, classifying and analyzing 77 papers. The research identifies four main application areas of transfer learning: building load prediction, occupancy detection and activity recognition, building dynamics modeling, and energy systems control.

ADVANCES IN APPLIED ENERGY (2022)

添加到收藏夹

Article Construction & Building Technology

A New Explication of Minimum Variable Sets (MVS) for Building Energy Prediction Based on Building Performance Database

Mingya Zhu et al.

Summary: Building energy simulation is important in the field of architecture, and the concept of minimum variable sets (MVS) can improve the general applicability of building energy prediction models by selecting the most essential variables. Through validation cases of two office buildings in Shanghai and California, the study showed the hierarchical correlations between different sizes of MVS and their prediction accuracies, offering potential support for reasonable decision-making regarding building energy model variables.

BUILDINGS (2022)

添加到收藏夹

Article Thermodynamics

Data augmentation strategy for short-term heating load prediction model of residential building

Yakai Lu et al.

Summary: Data-driven models are widely used for short-term heating load prediction of buildings, but insufficient data often affects prediction performance. This study proposes a data augmentation strategy using calibrated simulation model and transfer learning-based data fusion method to improve prediction accuracy under limited data conditions, showing a significant reduction in prediction errors.

ENERGY (2021)

添加到收藏夹

Article Construction & Building Technology

Interpretable deep learning model for building energy consumption prediction based on attention mechanism

Yuan Gao et al.

Summary: This paper proposes three interpretable encoder and decoder models based on LSTM and self-attention to improve the interpretability of deep learning models. In a case study, the addition of future real weather information only slightly improved the MAPE, and the model's attention to different time steps and features was discussed. The most important features were identified as daily max temperature, mean temperature, min temperature, and dew point temperature, with other features like pressure, wind speed, and holidays receiving lower weights.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Review Energy & Fuels

A review of machine learning in building load prediction

Liang Zhang et al.

Summary: This paper reviews the application of machine learning techniques in building load prediction, covering tasks T, performance P, and experience E aspects. It discusses the modeling algorithms that improve performance, as well as data engineering for modeling, and concludes with identified gaps and future trends in machine learning application for building energy systems.

APPLIED ENERGY (2021)

添加到收藏夹

Article Thermodynamics

A general transfer learning-based framework for thermal load prediction in regional energy system

Yakai Lu et al.

Summary: This paper presents a transfer learning-based framework for predicting thermal load with limited data. By selecting the optimum source prediction task and utilizing a model-based transfer learning method, the framework achieves the best prediction stability and reduces prediction errors.

ENERGY (2021)

添加到收藏夹

Article Construction & Building Technology

Sequence-to-sequence deep learning model for building energy consumption prediction with dynamic simulation modeling

Chul Ho Kim et al.

Summary: This study utilized a detailed dataset approach to predict building energy demand more accurately and constructed a prediction model covering various factors. The research found that occupancy information and solar radiation exerted the greatest influence on building energy demand prediction.

JOURNAL OF BUILDING ENGINEERING (2021)

添加到收藏夹

Article Green & Sustainable Science & Technology

Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings

Kadir Amasyali et al.

Summary: The study presents a machine-learning approach for predicting building energy consumption in an occupant-behavior-sensitive manner, using a large dataset to train the model and comparing four machine-learning algorithms in terms of prediction accuracy and computational efficiency. The research findings demonstrate the high impact of variables considered in this study and show the potential of the proposed approach to better understand the impact of occupant behavior on building energy consumption.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

添加到收藏夹

Article Energy & Fuels

Problem of data imbalance in building energy load prediction: Concept, influence, and solution

Chaobo Zhang et al.

Summary: Building energy systems face data imbalance issue under various operation conditions, affecting prediction accuracy. A clustering decision tree algorithm and multi-model prediction method were proposed in this study to address this problem, showing better performance compared to conventional single model-based methods.

APPLIED ENERGY (2021)

添加到收藏夹

Article Construction & Building Technology

Hourly energy consumption prediction of an office building based on ensemble learning and energy consumption pattern classification

Zhenxiang Dong et al.

Summary: Accurate prediction of building energy consumption is crucial for building energy management and policy. This study proposes a prediction strategy based on ensemble learning and energy consumption pattern classification, showing promising results in terms of prediction accuracy and robustness.

ENERGY AND BUILDINGS (2021)

添加到收藏夹

Article Energy & Fuels

A novel improved model for building energy consumption prediction based on model integration

Ran Wang et al.

APPLIED ENERGY (2020)

添加到收藏夹

Article Thermodynamics

Potential analysis of the transfer learning model in short and medium-term forecasting of building HVAC energy consumption

Fanyue Qian et al.

ENERGY (2020)

添加到收藏夹

Article Construction & Building Technology

Study on deep reinforcement learning techniques for building energy consumption forecasting

Tao Liu et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Article Thermodynamics

LSTM based long-term energy consumption prediction with periodicity

Jian Qi Wang et al.

ENERGY (2020)

添加到收藏夹

Article Construction & Building Technology

Multi-objective optimization of building energy performance using a particle swarm optimizer with less control parameters

Zhang Yong et al.

JOURNAL OF BUILDING ENGINEERING (2020)

添加到收藏夹

Article Thermodynamics

Short-term prediction of building energy consumption employing an improved extreme gradient boosting model: A case study of an intake tower

Hongfang Lu et al.

ENERGY (2020)

添加到收藏夹

Article Construction & Building Technology

Combination of short-term load forecasting models based on a stacking ensemble approach

Jihoon Moon et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Review Construction & Building Technology

A review of the -state-of-the-art in data -driven approaches for building energy prediction

Ying Sun et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Article Construction & Building Technology

Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data

Yuan Gao et al.

ENERGY AND BUILDINGS (2020)

添加到收藏夹

Article Construction & Building Technology

Prediction and optimization of energy consumption in an office building using artificial neural network and a genetic algorithm

Marjan Ilbeigi et al.

SUSTAINABLE CITIES AND SOCIETY (2020)

添加到收藏夹

Article Thermodynamics

Day-ahead prediction of hourly subentry energy consumption in the building sector using pattern recognition algorithms

Yibo Chen et al.

ENERGY (2020)

添加到收藏夹

Article Construction & Building Technology

Application of Machine Learning for Predicting Building Energy Use at Different Temporal and Spatial Resolution under Climate Change in USA

Rezvan Mohammadiziazi et al.

BUILDINGS (2020)

添加到收藏夹

Article Construction & Building Technology

Data driven parallel prediction of building energy consumption using generative adversarial nets

Chenlu Tian et al.

ENERGY AND BUILDINGS (2019)

添加到收藏夹

Article Thermodynamics

A novel deep reinforcement learning based methodology for short-term HVAC system energy consumption prediction

Tao Liu et al.

INTERNATIONAL JOURNAL OF REFRIGERATION-REVUE INTERNATIONALE DU FROID (2019)

添加到收藏夹

Review Construction & Building Technology

Modeling and forecasting building energy consumption: A review of data-driven techniques

Mathieu Bourdeau et al.

SUSTAINABLE CITIES AND SOCIETY (2019)

添加到收藏夹

Article Construction & Building Technology

Minimising the Deviation between Predicted and Actual Building Performance via Use of Neural Networks and BIM

Ahmed W. A. Hammad

BUILDINGS (2019)

添加到收藏夹

Article Construction & Building Technology

Random Forest based hourly building energy prediction

Zeyu Wang et al.

ENERGY AND BUILDINGS (2018)

添加到收藏夹

Article Construction & Building Technology

Transfer learning with seasonal and trend adjustment for cross-building energy forecasting

Mauro Ribeiro et al.

ENERGY AND BUILDINGS (2018)

添加到收藏夹

Article Construction & Building Technology

Day-ahead prediction of hourly electric demand in non-stationary operated commercial buildings: A clustering-based hybrid approach

Yibo Chen et al.

ENERGY AND BUILDINGS (2017)

添加到收藏夹

Review Green & Sustainable Science & Technology

From occupancy to occupant behavior: An analytical survey of data acquisition technologies, modeling methodologies and simulation coupling mechanisms for building energy efficiency

Mengda Jia et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2017)

添加到收藏夹

Article Energy & Fuels

Short-term prediction of electric demand in building sector via hybrid support vector regression

Yibo Chen et al.

APPLIED ENERGY (2017)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.