The Applicability of a Machine Learning Methodology to Generate TMY Weather Files - A Master’s Thesis

Aug 5, 2026

Upload by Asher

Accurate building energy models are essential for decarbonization, and typical meteorological year (TMY) weather files are widely used to represent long-term climate conditions in energy simulations. This thesis investigates generating TMY files with machine learning to improve accuracy beyond an expert-judgment-based workflow that can miss seasonal, climate, and application-specific differences. Manuscript 1 develops a feature-importance-driven methodology to identify key Sandia generation parameters and improves long-term energy demand representativeness. Manuscript 2 evaluates applicability across six Canadian climate zones using standardized weighting factors, showing improved predictive performance and greater adaptability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages110

Reading Time4 h 37 min

AccessFree to download

Chapter 1 Introduction

Background

Literature Review

Objective

Thesis Structure

Manuscript Executive Summary

The Applicability of a Machine Learning Methodology to Generate TMY Weather Files Ashleigh Marie Papakyriakou A Thesis in The Department Of Building, Civil, and Environmental Engineering Presented in Partial Fulfillment of the Requirements for the Degree of Master of Building Engineering at Concordia University Montreal, Quebec, Canada April 2024 © Ashleigh Papakyriakou, 2024 CONCORDIA UNIVERSITY School of Graduate Studies This is to certify that the thesis prepared By: Ashleigh Papakyriakou Entitled: The Applicability of a Machine Learning Methodology to Generate TMY Weather Files and submitted in partial fulfillment of the requirements for the degree of Master of Applied Science (Building Engineering) complies with the regulations of the University and meets the accepted standards with respect to originality and quality. Signed by the final Examining Committee: Chair Dr. Radu Zmeureanu Examiner Dr. Radu Zmeureanu Examiner Dr. Alireza Nazemi Supervisor Dr. Bruno Lee Approved by Chunjiang An, Graduate Program Director 2024 Dr. Mourad Debbabi, Dean of Faculty Abstract The Applicability of a Machine Learning Methodology to Generate TMY Weather Files Ashleigh Papakyriakou To effectively decarbonize buildings accurate energy models must be created to predict building energy performance. Typical meteorological year (TMY) weather files represent long-term weather conditions and are used in energy modelling to help evaluate energy performance. This thesis explores generating TMY files using machine learning to improve accuracy, which can significantly influence energy simulation results. The current TMY generation approach relies on expert judgment, often overlooking seasonal, climate and application-based variations. Manuscript \#1 introduces a machine learning methodology using feature importance to determine the relevant generation parameters used in the Sandia method to enhance the current TMY generation approach. The proposed methodology is applied to a medium office building in Montreal. The results reveal an improved representativeness of the long-term average building energy demand for the TMY generated using the proposed methodology. Manuscript \#2 aims to (1) assess the applicability of the methodology across Canadian climates; (2) investigate the feasibility of using standardized climate zone-based weighting factors to reduce the computational time associated with extracting location-based weighting factors to facilitate wider adoption of the proposed methodology. The methodology is applied to 18 cities across six Canadian climate zones and generates two weather files for each location. TMYSTATION uses location-based weighting factors while TMYCZ uses climate zone-based weighting factors. The CV(RMSE) and NMBE indicate the proposed weather files outperform the conventional weather files in predicting the long-term energy performance of buildings. Although the TMYSTATION files performed marginally better, the convenience of standardized climate zone-based weighting factors can enhance the methodology’s adaptability. Acknowledgements I would like to express my gratitude and appreciation to my supervisor Dr. Bruno Lee for his assistance and support. A special thank you goes to my dear friend, Ana, whose valuable insights, contributions, and dedicated time played a pivotal role in finalizing this contribution. Your friendship and support have meant the world to me. To my partner, Jared, and my close friends, and family, I am thankful for your support and patience during this challenging journey, and for encouraging me not to give up. In loving memory of my grandfather, John Papakyriakou, I dedicate this thesis. His enduring encouragement, guidance, kindness, and unwavering support has shaped me into the person I am today. Table of Contents LIST OF FIGURES.............................................................................

FAQs

Why are TMY weather files important for building energy modeling?

TMY weather files represent long-term weather conditions and are used to predict building energy performance. Their accuracy can materially affect simulation results.

What does Manuscript #1 contribute to TMY generation?

It introduces a machine learning methodology using feature importance to determine relevant generation parameters within the Sandia method, improving the representativeness of long-term average building energy demand.

How does Manuscript #2 expand the methodology for use across Canada?

It assesses applicability across Canadian climates and tests standardized climate zone-based weighting factors to reduce computation time. Applied to 18 cities in six climate zones, the resulting files outperform conventional files in predicting long-term energy performance.

Aug 5, 2026

Upload by Asher