A short talk on my 2019 side project.
My experience being a part the Summer Camp - Pipeline’s week long data engineering adventure.
A useful idea to understand computational control algorithms.
Ha & Schmidhuber’s World Models reimplemented in Tensorflow 2.0.
I’m going to be somewhere saying some things.
Badges of honour for the accomplished data scientist.
Getting control using a stateful and stateless LSTM.
A guide for the energy professional.
A parallelized Python implementation.
Hal Harvey shows the way.
Using energy-py-linear to measure the economic value of using a forecast.
A library for optimizing energy systems using mixed integer linear programming.
Finally - stable learning.
Using the defaultdict to simulate temporal problems.
Our evolution shaped psychology is a big reason why.
Making use of the Python standard library.
A simple guide to the data for the Australian electricity grid - the NEM.
Dota fans are making the same mistake Go fans did in underestimating Open AI.
What we need to do next.
Tuning hyperparameters of the new energy_py DDQN reinforcement learning agent.
Debugging the new energy_py DQN reinforcement learning agent.
How do we get to a zero carbon world?
All is not well with the clean energy transition.
Whats going on with energy storage?
Not every technology trend applies to energy.
Energy efficiency is not so simple.
Inertia is a common criticism of the energy transition - is it valid?
I’ve been learning Python for around 11 months - it’s been a wonderful journey!
This post covers three interesting insights from the 2017 IEA report Getting Wind and Sun onto the Grid.
Technical modeling of combined heat & power (CHP) plants was my first area of professional specalization.
An introduction to blockchain the technology.
Musk thinks autonomous vehicles will be cheaper and driven for longer.
Applications of machine learning in energy - forecasting, disaggregation and reinforcement learning.
On May 3rd 2017 the California grid experienced its first Stage 1 grid emergency in nearly a decade.
What is machine learning anyway?
The more oil we burn, the more oil reserves we have.
Jesse Jenkin’s insights on decarbonizing electricity systems.
An introduction to the open source energy focused reinforcement learning library energy-py.
It’s not how much capacity (MW) you have - it’s how you use it (MWh).
Peak oil won’t save the planet, wind and solar lack an inherent economy of scale and German capacity factors.
BP’s view on the next 40 years.
Many professionals are getting this wrong.
Can a fossil fuel efficiency penalty offset the benefits of renewables?
How clean are wind and solar really?
CHP is efficient, but is it clean?
A fundamental concept in business and energy.
Two insights from the excellent Vaclav Smil.
Highlights from the 2016 IEA World Energy Outlook.
How far we’ve come and is there an upper limit?
Why are return temperatures are a major problem in district heating?
Plotting using matplotlib.
Explaining the relationship between gas turbines and ambient temperature.
Scraping UK electricity grid data.
Costa Rica is often wrongly held up as an example of how to go renewable.
An introduction to the economics of imbalance in electricity systems.
Insights from the IEA World Energy Investment 2016 report.
Confessions of a former spreadsheet monkey.
The equation I used the most as an energy engineer.
Simple enough to be summarized in two sentences.
Being careful and consistent when dealing with kilowatts and kilowatt-hours is a basic for all energy professionals.
Explaining the conventions for quantifying the heat of combustion.