Handbook of Energy Analytics

Techno-economic energy systems modeling and analysis using data-centric and algorithmic approaches

Kshitiz Khanal

As the digitalization of our energy systems ramps up, making sense of those energy systems to accelerate the energy systems will increase the demand for modeling and analytical skills specific to energy systems. The analysts require domain knowledge in the physical, technical, social, and economic sides of the energy systems as well as analytical knowledge in data and algorithms.

While various software specializing in various aspects of modeling and analyzing energy systems are currently available, it is more important for analysts to learn how to approach a problem than to learn how to use specific software/tools. This handbook, through detailed worked-out examples, helps analysts learn how to model ad-hoc aspects of complex energy systems for common energy modeling tasks. Even though specific software/tools can be used, learning ad-hoc modeling helps develop analysts who are better prepared for the energy transition.

This handbook covers lessons and tutorials on applications of modeling, optimization, data science, machine learning, spatial analysis, and other techniques. The resources are demonstrated primarily in Python, with some developed in R, Excel, and other tools best fit for the purpose.

• Intro to Energy Analytics

• Object Oriented Programming for Energy Modelers

• Forecasting and time series analysis

• Long-range energy planning and optimization

• Clean energy project finance

  • Comparing various modes of project financing for commercial solar

• Energy markets and trading

  • Importing energy market data using gridstatus Python package
  • Modeling profitability of electricity price arbitrage from a grid-connected battery

• Spatial analysis

• Energy justice

• Applications of machine learning

• Using Structural Causal Models to Estimate Energy Project Investment Cost

• Building decarbonization

• Techno-economic analysis of energy technologies

• Ratemaking

• Energy system performance evaluation

• Miscellaneous

• Featured tutorials

  Featured tutorials are tutorials from external sources that can be very helpful to the audience of this handbook.

  • Building Load Forecasting with ML
  • Smart Meter Data Analytics: Practical Use-Cases and Best Practices of Machine Learning Applications for Energy Data in the Residential Sector
  • Estimating Coal Power Plant Operation From Satellite Images with Computer Vision
  • AI for optimal power flow
  • A Tutorial on Reinforcement Learning Control for Grid-Interactive Efficient Buildings and Communities