Posted on

Alby’s Status Report – Feb 10

Accomplishments:

  • presented the project proposal and received good feedback.
  • made a first rough draft of the multi-period code architecture
  • implemented a simple multi-period class that runs sugar3 at each time step with specified input load

Progress Reflection:

  • met with my research advisor to discuss the next steps in building the multi-period optimization tool – need to focus more on getting initial results than polishing codebase.
  • need to speed up my work to get results soon and uncover any initial convergence issues

Next Week’s Goals:

  • test multi-period class is changing loads correctly by seeing changes in slack bus power
  • change slack and SOC variables to class variables in Batteries.py and run the inner loop for 2 periods, check battery SOC variable and verify it correctly changes
Posted on

Yuchen’s Status Report for 2.10.2024

This week, my main task involves creating a preliminary template for the website’s main page, focusing on integrating the Generation and Load forecasting time series panel and the power flow network graph panel. The current website is built on the Django framework. I’ve attached a screenshot showcasing the current design progress. As you can see from the screenshot, we plan to separate various content elements, such as current machine learning outputs and forecasting results, into different tabs. This strategy aims to enhance user experience by reducing visual clutter, addressing a concern from previous design iterations.

The next step entails researching methods to enable users to upload their microgrid architecture files on the website and visualize nodes. This involves studying efficient techniques, such as utilizing a Python parser, to extract information from the user’s architecture file and generate visually appealing visualizations of the data.

Posted on

Yuchen’s Status Report for 2.3.2024

As mentioned in our week’s team status report, we are in the stage of collecting the appropriate datasets and researching the complexity of the model, etc. This week, I’m responsible for the website setup and looking for data sets regarding wind direction/speed.

We’ve also decided on a clear division of labor that I will be broadly responsible for the final Web application, and I’ll also assist Carter in the ML model training process.  Regarding the final web application side, since it’s been a while since the last time I built a website, I plan to do a quick overview of CSS just to be more familiar with the format as well as UI-based libraries such as React.  In addition, I plan to start designing the front-end web interface using Figma and research how to load users’ microgrid architecture files on the website and possibly enable the user to edit the file on the website with visualization. On the ML side, I’m researching on previously done work as a reference and start to think how to implement our model in the near future.

Posted on

Team Status Report for 2.2.2024

Current Challenge Overview:

Our primary challenge involves understanding what data we need and collecting appropriate datasets. We’re currently looking for localized time-series data relating solar and wind power statistics to weather patterns and using it to train a model for renewable generation and load forecasting. Selecting the right location is also and we are currently planning to choose representative states in the U.S. to cover most use cases. Additionally, we’re navigating and researching the complexities of integrating generic microgrid standards and power flow modeling programs. Risk management is a priority, and we’re developing a robust backup plan in case data collection encounters obstacles.