Heating and Cooling Loads Forecasting for Residential Buildings Based on Hybrid Machine Learning Applications: A Comprehensive Review and Comparative Analysis

نویسندگان

چکیده

Prediction of building energy consumption plays an important role in conservation, management, and planning. Continuously improving enhancing the performance forecasting models is key to ensuring sustainability systems. In this connection, current paper presented a new improved hybrid model machine learning application for cooling load (CL) heating (HL) residential buildings after studying analyzing various types CL HL models. The proposed model, called group support vector regression (GSVR), combination method data handling (GMDH) (SVR) To forecast HL, study also made use base methods such as back-propagation neural network (BPNN), elastic-net (ENR), general (GRNN), k-nearest neighbors (kNN), partial least squares (PLSR), GMDH, SVR. technical parameters were utilized input variables models, adopted output each network. All saved form black box training initial testing. Finally, comparative analysis was performed assess predictive suggested well-known basic Based on results, with high correlation coefficient (R) (e.g. R=99.92% R=99.99% forecasting) minimal statistical error values provided most optimal prediction performance.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A hybrid model based on machine learning and genetic algorithm for detecting fraud in financial statements

Financial statement fraud has increasingly become a serious problem for business, government, and investors. In fact, this threatens the reliability of capital markets, corporate heads, and even the audit profession. Auditors in particular face their apparent inability to detect large-scale fraud, and there are various ways to identify this problem. In order to identify this problem, the majori...

متن کامل

Comparative study between dynamic transient and degree-hours methods to estimate heating and cooling loads of building’s wall

In this paper, dynamic transient method and conventional degree-hours method (static) have been compared to estimate heating and cooling loads of building’s wall. All main wall surfaces of various orientations, i.e.South, West, East, North, and horizontal are considered in the climate of Tehran, Iran. In this study, a conventional wall structure, which is comprisedconcrete as main wall material...

متن کامل

Effects of Southern Wall Angle on Heating Performance and Energy Consumption of Residential Buildings in Yazd

The southern wall plays an important role on heating perfrmance and energy consumption of residential buildings. This study investigates the effects of southern wall angle, glass area and external canopy on heating perfrmance and energy consumption of a typical residential building in Yazd. Using causality method and thermal simulation by DesignBuilder simulator, we examined energy consumption ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Access

سال: 2022

ISSN: ['2169-3536']

DOI: https://doi.org/10.1109/access.2021.3136091