Home » REU2017 » Bayley Meyer: Visualizing Watt Energy Consumption

Bayley Meyer: Visualizing Watt Energy Consumption

Home Institution
Westminster College
Salt Lake City, UT
Contact Email: bcm0926@westminstercollege.edu 

Clemson Research Mentors
Dr. David White
Research Professor of Electrical and Computer Engineering
Tim Howard
Project Manager

Clemson Visualization Mentor
Dr. Wole Oyekoya
Visualization Director


About Me:

I’m currently a senior at Westminster College studying Mathematics with minors in Data Science and French. After graduation I hope to become a data analyst or statistical consultant. I’m from Seattle, WA but moved to Utah for school.  I plan to move back to Seattle after I graduate in order to be closer to the tech industry.

Project Description:

The goal of my project is to visualize the energy data for the Watt Innovative Center, in order to discover and address potential inefficiencies in the building.  I will be using SAS Visual Analytics in order to show the data for the following subsets of the building’s consumption; receptacle, isolated ground, media lights, lighting, and HVAC. Visualizing this data will help to reduce the utility costs for Watt. Originally, we were planning on creating a prediction for future hourly consumption of Watt, but changed the goal of the project in week 6.

Week 1:

This week I met with my mentor, Dr. David White, and defined my goal for summer research: create dashboards for the resources that are consumed by the Watt Innovation Center including a prediction of future hourly consumption.  I started getting familiar with SAS Visual Analytics in order to analyze the data next week.  As a group, we had sessions on writing the paper and using adobe premiere software. We also took a tour of the Watt building to see the advantages of an innovation center.

Week 2:

I began drafting dashboards for the different subsets of the Watt center, unfortunately I haven’t been able to create any of the dashboards yet due to a technical issue of getting full access to SAS Visual Analytics.  So I began working in R in order to look at the many options for creating a predictive, time dependent model.  I began researching different methods that have previously been used for creating time predictive models both generally, and specifically for smart buildings.  As a group we had demos with Linux command line, the Palmetto cluster, GIS, and many of the options for 3D visualization, visual analytics, and information visualization.

Week 3:

Things finally started to come together this week since I was able to upload the Watt data into SAS Visual Analytics and begin drafting dashboards for the different energy subsets of the building. Unfortunately, SAS is not quite as user friendly as I’d hoped so I’m having to manually create categories such as weeks and hours of operations in order to get the program to graph my data. I was also given the code that was used for the original lighting dashboard and I’ve begun to see if that’ll help me to construct a predictive model for the Watt data. The group sessions that I attended this week were about Python, Unity 3D, retrieving and graphing census data. Attending these sessions has been really useful because it is helping me to understand many of the different programs that are available for visualizing all different kinds of data.

Week 4:

After going to the R sessions that were held this week I was able to collapse my data into hourly readings instead of readings every 15 minutes. Since this reduced my data to the quarter of the size, SAS was able to read the time column to allow for drilling down on specific time periods and animating consumption use over time. Once I finished making the interactive dashboards I focused on preparing for the midterm presentation that is coming up. I’m focusing my presentation on how commercial buildings (including Watt) consume 70% of the US’ electricity, and how prediction methods can be used to reduce total usage. Through my project I hope to find a predictive algorithm that will help to reduce energy consumption in Watt, and spread awareness of the amount of energy being consumed on campus. Next week I’ll continue using R to create predictive aspect for the dashboards.

Week 5:

This week started off with the midterm presentations which allowed us to share our progress with the rest of the group and our mentors. I thought that mine went fairly well, however I quickly realized that I did not have a strong understanding of all that the Watt center does. During my mentor meeting Tim Howard, the project manager, gave me a tour of the building that focused on all the technology that the building uses. It helped me to understand what makes this building an innovation center, and why some of the readings are so large. I was able to see the meters that are retaining the information I’ve been graphing, along with the systems that I connect to when using SAS Visual Analytics. The end of this week was focused on drafting the related works, and methods section to the research paper. I’ve started looking into the most efficient and accurate way to create the predictive piece of this project. ARIMA (auto-regressive integrate moving average) models seem to be the best way to forecast the Watt data, so next week will be focused on finding the best parameters for fitting it to the data.

Week 6:

At the beginning of this week we took a tour of the ITC Data Center which holds the Palmetto Cluster. I found it especially interesting to compare this building’s consumption to the Watt Center. We were also given tours of the animation, digital production arts, and virtual environment labs. This gave us an inside look of how much work goes into animating movies and video games, along with studies that will hopefully improve future VR environments.

As far as my project, I’ve worked on plotting time series in R, with the goal of plotting prediction data on the same plot in order to have a good estimate for the future. The three forecasting functions that I looked at were forecast(), HoltWinters(), and arima(). ARIMA models were the most informative of the three, but after meeting with David and Tim we decided a better direction would be to drill down on some of the largest power consumers in the building. I was given three things to look into; the relationship between HVAC and outside temperature, the relationship between receptacle power usage and occupancy, and lastly the cost differences when changing some aspects of the lighting.  So far I’ve done correlation and regression analysis on HVAC and temperature and found a moderate correlation. Next week I’ll look into the cost differences for making lighting more efficient, and hopefully I’ll receive the occupancy data, so that I can explore that as well.

Week 7:

The sessions that were held this week were about power of presence and building relationships where we created and rehearsed elevator talks, as well as identified which “color” we were in the work place. This helped us to have a better understanding of what to say to potential employers if given the chance to have a short conversation with them. The color identifiers were entertaining mostly because 6 of the REU students (including myself) were in the blue-detailed oriented group.

Its been a very productive week for my project. I’ve completed the dashboards for HVAC and temperature correlation, as well as receptacle data correlated with occupancy, and cost reduction dashboards for the lighting and the media lights. At the meeting with my mentors we discussed final touches to the dashboard along with a couple more things to add before the end of the program. I was also able to complete a draft of my research paper and get it formatted in LaTeX. On Friday my mentor, Tim, and I went over the format for my final presentation so that I can take full advantage of the hyper-wall in the Watt auditorium. Next week I’ll focus on getting my presentation together and planning a poster or demo for the breaks during the Visualization Symposium. Only one week left!

Week 8:

No group sessions were held this week so that everyone could have time to finish their papers, posters, and presentations. However, we did have a group dinner at Solé on the Green to celebrate the (near) completion of our REU. I decided to not make a poster, but to display my dashboard that I’ve been making these past 8 weeks instead, since I think that will give viewers a better understanding of what I did throughout this REU. I’ve had time to edit my paper a few times and am satisfied with the end product. Luckily, I was able to rehearse my presentation in Watt Auditorium a few times since we decided to use a dual screened approach which involves a lot of interaction with the hiper-wall.

Visualization Symposium:

The presentations were a success! I thought that all the REU students did a fantastic job, and it was really great to see everyone progress throughout these 8 weeks. It was fun to explore the other demos that were set up during the poster sessions, and using the entire hiper-wall worked very well for my presentation. A huge thank you to Dr. Wole for the nomination to the NSF REU Conference, and for the wonderful experience that I’ve had here at Clemson.

Final Results and Remarks:

By analyzing the Watt Innovation Center energy consumption data, we found that $22,485 is saved annually by having LED overhead lighting with motion and ambient light sensors. The current minimum consumption for the media light is 10 kWh, if we were able to completely turn off the media lights 12pm-6am on weekdays and all weekend utility costs could be reduced by nearly $4,000 annually. This cost reduction does not include the amount that would be saved by the ability to turn off the HVAC in the rooms where the media lights are controlled (these rooms get overheated if not controlled by the HVAC system).  Outside temperature and HVAC power have a moderate linear correlation with a r-squared value of .28. This knowledge can be used to further align the HVAC systems with the outside temperature to avoid unnecessary surges in energy use. Last we saw that receptacle usage and occupancy data had a strong linear relationship. The second floor had the highest correlation and an r-squared value of .64. The first floor had the lowest r-squared value of .45, this is because the first floor has a cafe that has appliances that run nonstop. These findings can hopefully be used in the future to reduce total utility costs and to even have Watt run its’ own utilities without intervention.

This REU program has been very beneficial to me, I was able to learn many new skills (SAS, linux, GIS, LaTeX, python, etc.), and have the opportunity to expand my knowledge base in visualization.  The biggest takeaway for me is my improved ability to search for solutions with programs where my knowledge base is limited. Being able to self learn is a something that can be beneficial in any field, and I’m happy that this experience has helped improve my ability to do so.

Final Report

Hunter College
City University of New York
695 Park Ave
New York, NY 10065

Telephone: +1 (212) 396-6837
Email: oo700 at hunter dot cuny dot edu

Follow me:
wolexvr on Twitter  wole-oyekoya-5b753610 on Linkedin  woleucl's YouTube channel  oyekoya's Github profile  Googlescholar 
Need help with the Commons? Visit our
help page
Send us a message