All posts
-

Developing and deploying machine learning models for online load forecasts
Load forecasts are important input to operating the power system, especially as renewable energy sources become a bigger part of our power mix and new electrical interconnectors link the Norwegian power system to neighbouring systems. That is why we have been developing machine learning models to make predictions for power consumption. This post describes the… Read more
-

How we quantify power system reliability
An important aspect of digital transformation for a utility company is to make data-driven decisions about risk. In electric power systems, the hardest part in almost any decision is to quantify the reliability of supply. That is why we have been working on methodology, data quality and simulation tools with this in mind for several… Read more
-

Prediction of rare events and the challenges it brings: Wind failures on power lines
Summer internship blog 2018: Comparing different weather data, evaluating their corresponding probabilistic predictions and trying to develop a better forecast model. Read more
-

Simulating power markets with competitive self-play
In this post we present an unpublished article from 2009 that uses self-play to evolve bidding strategies in congested power markets with nodal pricing. Read more
-

Comparing javascript libraries for plotting
After some research on available javascript libraries for plotting we decided that plotly fits our needs the best. We also provide a small vue-wrapper for plotly. Read more
-

Setting up a forecast service for weather dependent failures on power lines in one week and ten minutes
Combining Tableau, Python, Splunk and open data from met.no to deliver a realtime forecast of the probability of failure due to wind and lightning on overhead lines. Read more
