Posted on

Carter Weaver’s Status Report for 2/24/24

This week I spent time revising my methodology for accessing and providing a baseline model for each of our training data sets (load, wind generation, and solar radiation).

In response to learning more about the SUGAR simulation tool we’re using, I decided to do away with the persistence algorithm we were previously using as a baseline algorithm, since recently observed power generation/demand will not be available to our models as a part of the simulation output. Instead, I decided to fit a linear regression model using weather and time as features and power/radiation/demand as the target variable. So far I’ve gathered Relative-MSE scores of 0.59 and 0.41 for our solar and wind data respectively, indicating that we have far to go in terms of improving our predictions. With these results and the results I will soon have for our load data, I am reasonably on pace for my forecasting goals.

Next week, I plan to generate baseline metrics for our load data with a linear regression model as well. Also, as the designated project manager for these two weeks before spring break, I will be devoting much of my time to developing our design report.

Posted on

Team Status Report for 2/17/24

Risks

  • If multi-period optimization has early convergence issues then we will need to rapidly develop heuristics – this is a timeline risk that could push back development.

System Changes

  • Removed the building of a custom grid-lab d file processing tool because a parser already exists within SUGAR.

Schedule Changes

  • None

Please write a paragraph or two describing how the product solution you are designing will meet a specified need…

Part A.

Microgrids have significant implications for social dynamics as they can empower local communities, promote energy independence, and foster collaborative decision-making. Improving microgrids and making them easier to work with will help communities to control their power efficiently and cater their grids to their own needs, ensuring that stakeholders have a voice in the planning and operation of their energy. Moreover, by finding ways to harness renewable power more effectively and making wind and solar more predictable, we are increasing the potential reach of clean energy to underserved communities where energy is scarce, thereby promoting social inclusion and cohesion. Overall, power grids are an overlooked, yet essential way to connect distant social groups through the sharing of essential resources and making the development and control of those grids more intuitive will hopefully connect more communities to the power we take for granted.

Part B.

Microgrids have significant implications for social dynamics as they can empower local communities, promote energy independence, and foster collaborative decision-making. Improving microgrids and making them easier to work with will help communities to control their power efficiently and cater their grids to their own needs, ensuring that stakeholders have a voice in the planning and operation of their energy. Moreover, by finding ways to harness renewable power more effectively and making wind and solar more predictable, we are increasing the potential reach of clean energy to underserved communities where energy is scarce, thereby promoting social inclusion and cohesion. Overall, power grids are an overlooked, yet essential way to connect distant social groups through the sharing of essential resources and making the development and control of those grids more intuitive will hopefully connect more communities to the power we take for granted.

Part C:

Our microgrid energy management tool finds the most economically optimal dispatch of the battery and generators in the system. This saves the operator money which transfers directly to cost-saving for electricity consumers. Furthermore, the battery dispatch enables renewables to be more economic by charging during periods of excess generation and discharging during periods of low generation to meet demand.

 

Posted on

Carter Weaver’s Status Report for 2/17/24

This week is was able to initialize my codebase for experimenting with ML forecasting, and I helped my group with narrowing down our design plans for the presentation next week.

In order to inform our decisions about what training and testing methods will be most appropriate, I devoted the first half of this week to understanding the limitations of the data we have available to us. I figured out how to efficiently access wind, solar, and general weather data and then used the wind data to produce baseline results with a persistence algorithm (predicting the previous value as the next value). This allowed me to output an array of error metrics for a naive forecasting approach that I can use to revise our goals for our models and have as a benchmark for later results. After my experiments and further research into appropriate ML techniques, I spent the latter part of the week developing design plans for the forecasting portion of the project and updating our presentation slides accordingly.

I’d say we are more than on schedule with our progress so far and after we have our design fully nailed down, progress on the codebase should come quickly. Next week, I plan to generate baseline results for our solar data and load data before starting to experiment with some slightly more effective regression models (linear regression, random forest regression). We will also devote time to our design report, taking into account feedback from our design presentation.

Posted on

Team Status Report for 2/10/24

This week, our main focus as a group was on taking the feedback we received for our proposal presentation and using it to shape our expectations going forward. The main recommendations were:

  • create an overall block diagram
  • create a fully defined testing process
  • specify more detailed UI requirements

Risks

  • If multi-period optimization has early convergence issues then we will need to rapidly develop heuristics – this is a timeline risk that could push back development.

System Changes

  • Added load forecasting to machine learning requirements

Schedule Changes

  • None
Posted on

Carter Weaver’s Status Report for 2/11/24

This week I mainly focused on researching viable ML models for renewable energy forecasting as well as finding data sources. From my research, i was able to find multiple papers and surveys comparing methods for renewable forecasting. Based on these papers, I was able to narrow my list of algorithms that I’ll start experimenting with to SVM, RNN, ARIMA, and more. From my search for data sources I found global weather data for day-ahead forecasting and model training as well as solar radiation datasets for model validation from the National Solar Radiation Database. Data for wind turbine generation proved more difficult to find for multiple locations, but I was able to find some Kaggle datasets for turbines in Europe that could be used for validation purposes. These sources are linked at the bottom of this post.

My progress is on schedule so far. For next week I plan on setting up a remote repository for work on renewable forecasting and develop a detailed outline for our ML pipeline including plans for data scraping, preprocessing, training, validation, and testing. I intend on focusing first on SVMs as the favorite of the algorithms I found, and I’ll look to make a visual representation of our full ML pipeline.

Weather API:  https://openweathermap.org/api

NSRB Solar Datasets: https://nsrdb.nrel.gov/data-viewer

Kaggle Wind Dataset: https://www.kaggle.com/datasets/berkerisen/wind-turbine-scada-dataset