Application of Machine Learning in Forecasting Energy Usage of Building Design

2018 ◽  
Author(s):  
Truong Xuan Dan ◽  
Phan Nguyen Ky Phuc
Keyword(s):  
Machine Learning ◽  
Building Design ◽  
Energy Usage

Understanding the Impact of Occupancy Trends in Sustainable Housing Designs

2016 ◽  
Author(s):  
Joseph Piacenza ◽  
Salvador Mayoral ◽  
Sean Lin ◽  
Lauren Won ◽  
Xava Grooms
Keyword(s):  
Computational Models ◽  
Building Design ◽  
Student Housing ◽  
Energy Usage ◽  
Sustainable Building ◽  
Leed Certification ◽  
Sustainable Housing ◽  
Course Scheduling ◽  
Housing Complex ◽  
The Impact

As sustainable building mandates become more prevalent in new commercial buildings, it is a challenge to create a broad, one-size-fits-all certification process. While designers can estimate energy usage with computation tools such as model based design, anticipating the post occupancy usage is more difficult. Understanding energy usage trends is especially complicated in university student housing buildings, where occupancy varies significantly as a function of enrollment and course scheduling. This research explores the effect of student occupancy on both predicted and actual energy usage in a LEED (Leadership in Energy and Environmental Design) Platinum certified student housing complex. A case study is presented from the California State University Fullerton (CSUF) campus, and examines diversity factor, defined as a building’s instantaneous energy usage as a percentage of the maximum allowable usage during a period of time, trends throughout the academic year. The CSUF case diversity factor is compared to the diversity factor used in predictive models for obtaining LEED certification, and the mandates that govern the models (e.g., ASHRAE 90.1). The results of the analysis show the benefits of considering post occupancy usage in sustainable building designs, and recommendations are presented for creating unique and application based computational models, early in the design process. This research has broad applications, and can extend to sustainable building design in other organizations, whose operational schedule falls outside of current prediction methods for sustainability mandates.

Towards statistical modeling and machine learning based energy usage forecasting in smart grid

2015 ◽  
Vol 15 (1) ◽  
pp. 6-16 ◽  
Author(s):  
Wei Yu ◽  
Dou An ◽  
David Griffith ◽  
Qingyu Yang ◽  
Guobin Xu
Keyword(s):  
Machine Learning ◽  
Smart Grid ◽  
Statistical Modeling ◽  
Energy Usage

scholarly journals Reducing energy usage in resource-intensive Java-based scientific applications via micro-benchmark based code refactorings

2019 ◽  
Vol 16 (2) ◽  
pp. 541-564
Author(s):  
Mathias Longo ◽  
Ana Rodriguez ◽  
Cristian Mateos ◽  
Alejandro Zunino
Keyword(s):  
Machine Learning ◽  
High Performance Computing ◽  
Computer Simulations ◽  
High Performance ◽  
Machine Learning Algorithms ◽  
Energy Usage ◽  
Energy Aware ◽  
Scientific Application ◽  
Performance Computing ◽  
Reducing Energy

In-silico research has grown considerably. Today?s scientific code involves long-running computer simulations and hence powerful computing infrastructures are needed. Traditionally, research in high-performance computing has focused on executing code as fast as possible, while energy has been recently recognized as another goal to consider. Yet, energy-driven research has mostly focused on the hardware and middleware layers, but few efforts target the application level, where many energy-aware optimizations are possible. We revisit a catalog of Java primitives commonly used in OO scientific programming, or micro-benchmarks, to identify energy-friendly versions of the same primitive. We then apply the micro-benchmarks to classical scientific application kernels and machine learning algorithms for both single-thread and multi-thread implementations on a server. Energy usage reductions at the micro-benchmark level are substantial, while for applications obtained reductions range from 3.90% to 99.18%.

scholarly journals Energy Meter Data Analysis Using Machine Learning Techniques

2020 ◽  
Vol 8 (6) ◽  
pp. 08-13
Author(s):  
Anitha Kumari K ◽  
Indusha M ◽  
Abarna Devi D ◽  
Dheva Dharshini S
Keyword(s):  
Machine Learning ◽  
Data Analysis ◽  
Use Cases ◽  
Machine Learning Techniques ◽  
Energy Usage ◽  
Energy Meter ◽  
Learning Techniques ◽  
Significant Interest ◽  
F Measure

With the advancement of technology, existence of energy meters are not merely to measure energy units. The proliferation of energy meter deployments had led to significant interest in analyzing the energy usage by the machines. Energy meter data is often difficult to analyzeowing to the aggregation of many disparate and complex loads. At utility scales, analysis is further complicated by the vast quantity of data and hence industries turn towards applying machine learning techniques for monitoring and measuring loads of the machines. The energy meter data analysis aims at analyzing the behavior of the machine and providing insights on usage of the energy. This will help the industries to identify the faults in the machine and to rectify it.Two use cases with two different motor specifications is considered for evaluation and the efficiency is proved by considering accuracy, precision, F-measure and recall as metrics.

Machine Learning-Based Day-Ahead Market Energy Usage Bidding for Smart Microgrids

2021 ◽  
pp. 249-266
Author(s):  
Mohd Saqib ◽  
Sanjeev Anand Sahu ◽  
Mohd Sakib ◽  
Essam A. Al-Ammar
Keyword(s):  
Machine Learning ◽  
Energy Usage

Understanding the Importance of Post Occupancy Usage Trends During Concept-Stage Sustainable Building Design

2017 ◽  
Author(s):  
Joseph Piacenza ◽  
Salvador Mayoral ◽  
Bahaa Albarhami ◽  
Sean Lin
Keyword(s):  
Computational Models ◽  
Energy Use ◽  
Building Design ◽  
Student Housing ◽  
Energy Usage ◽  
Sustainable Building ◽  
Actual Usage ◽  
Mixed Use ◽  
Housing Complex ◽  
The Impact

As sustainable building mandates become more prevalent in new commercial and mixed use buildings, it is a challenge to create a broad, one-size-fits-all certification process. While designers can estimate energy usage with computational tools such as model based design, anticipating the post occupancy usage is more challenging. Understanding and predicting energy usage trends is especially complicated in unique mixed use building applications, such as university student housing buildings, where occupancy varies significantly as a function of enrollment, course scheduling, and student study habits. This research explores a computational modeling approach used to achieve LEED (Leadership in Energy and Environmental Design) Platinum certification for a student housing complex design. A case study is presented from the California State University, Fullerton (CSUF) campus, and examines the impact of post occupancy building usage trends, and diversity factor, defined as a building’s instantaneous energy usage normalized by the maximum allowable usage, on energy use estimates. The CSUF case model, which was originally created using EnergySoft’s EnergyPro 5 software, is examined. An annual predictive energy use comparison is performed in EnergyPro 5 using general building design mandates (i.e., ASHRAE 90.1, California Title 24), and CSUF case specific building usage details (e.g., student scheduling, diversity factor). In addition, the energy usage estimates of these two predictive models are compared to the actual usage data collected during the 2014 academic year. The results of this comparison show the benefits of considering post occupancy usage, and recommendations are presented for creating unique and application based computational models, early in the design process. This research has broad applications, and can extend to sustainable building design in other organizations, whose operational schedule falls outside of current prediction methods for sustainability mandates.

scholarly journals Enhancing the Practicality of Tools to Estimate the Whole Life Embodied Carbon of Building Structures via Machine Learning Models

2021 ◽  
Vol 7 ◽  
Author(s):  
Francesco Pomponi ◽  
Maria Luque Anguita ◽  
Michal Lange ◽  
Bernardino D’Amico ◽  
Emma Hart
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Real Time ◽  
Energy Demand ◽  
Structural Engineering ◽  
Building Design ◽  
Raw Material ◽  
Design Stage ◽  
Building Structures ◽  
Embodied Carbon

The construction and operation of buildings account for significant environmental impacts, including greenhouse gas (GHG) emissions, energy demand, resource consumption and waste generation. While the operation of buildings is fairly well regulated and globally considered in the pathways to net-zero mid-century targets, a different picture emerges when looking at the other life cycle stages, which incur the so-called embodied impacts. These cover raw material extraction and product manufacturing through to construction and end of life activities. Only a handful of examples exist where such embodied carbon (EC) emissions are enshrined in law with most of the ongoing debate still around estimating and understanding where such emissions occur and how to mitigate them. Building structures account for a significant share of a building’s embodied emissions and they also are the building element with the longest service life, thus presenting potential lock-in challenges for choices made today. To support the ongoing global effort to mitigate embodied carbon and equip engineers and designers worldwide with easy-to-use and robust calculation tools, we describe a real-time decision-support tool to aid building design that leverages machine learning (ML) methods from computer science to speed-up the computationally expensive process of finite element analysis (FEA) traditionally exploited in structural engineering. We demonstrate that replacing FEA calculations with a model learnt using ML from a large dataset offers real time decision support while guaranteeing the same level of confidence and accuracy that a traditional FEA-based method would offer at the design stage. The tool has been developed both as a standalone version and as a plugin for Trimble SketchUp to maximise its usability and diffusion. It offers results correlated with uncertainty analysis in the form of probability density functions to account for the inherent variability of input data that characterises early stages in the design process. This research contributes to the ongoing global efforts to decarbonising the built environment and offers an immediately implementable method and tool for doing so.

Sign in / Sign up

Export Citation Format

Share Document