How Python is supporting Australia’s energy transition to 100% renewable
Australia’s electricity grid is transitioning to 100% renewable and the industry’s goal is to be able to run in this configuration by 2025.
This is a huge engineering and organizational undertaking, and Python is supporting us all the way.
This talk shall start with an overview of the energy grid as it has been pretty much for a century. We shall look at the physics of electricity and the control systems required to maintain constant, reliable supply.
Management of the grid involving the movement of large volumes of data from sensors in the field, to centralized data stores. Data is merged with models and used to make operational decision in near real time, to design the grid into the future, and to analyse faults in the past.
Python is used to support these data flows and models and executes in a high availability environment on servers, as well as on users’ desktops supporting ad hoc analysis.
With every line of new code, Python becomes more critical to Australia’s energy future.
We shall cover three broad topics:
a) A little power system engineering: How the grid works. b) Case study: Modeling the grid in Python with code fragments. b) Case study: The weather (sunny? windy? hot? cold?) and social (weekend, weekday, public holiday) aspect of forecasting supply and demand.
See this talk and many more by getting your ticket to PyCon AU now!
I want a ticket!This session will be co-presented by Peter Aych and Josh James.
Peter's bio is attached elsewhere.
Josh's bio is below:
Josh leads AEMO's Data Science team within Operational Forecasting, where they are responsible for the development and implementation of new machine learning (ML) models for operational grid demand and variable renewable energy (VRE) forecasting.
Josh has a long history in numerical modelling and writing code, originally as an Engineer, and subsequently in a varied career comprising wind and solar farm design in Southern Africa, energy modelling for a large Australian energy retailer, and the past 7 years working across various forecasting teams within AEMO, with a key focus on delivery of new modelling capabilities.
Josh is passionate about the use and promotion of open-source software, starting years back attending events at the University of Cape Town Linux Enthusiasts Group (UCT LEG), and the Ubuntu ZA LoCo, and with interests ranging across Linux, sysadmin, robotics, and programming languages geared towards AI/ML such as Python and R.
Peter has been with AEMO, the Australia Energy Market Operator since soon after market start. The Australian electricity grid has undergone two major transformations: First in the late 1990s when the national market was created, and the states were interconnected. Now the biggest transformation is now underway as we move towards a 100% renewable grid.
There are many software systems that support the electricity grid and market: Pascal, Fortran, C, Oracle and Java in the early days. Python, JavaScript & Vue, C# & C++ today.
Peter’s team supports a suite of tools called AMP – The AEMO Modelling Platform – a ‘digital twins’ of the grid used to predict its behavior, design it into the future, and analyze operation faults.
AMP Features a SQL Server & Python backend running on Windows, with Vue & JavaScript user interface. At the time of writing, we have 25,000 lines of Python code, all linted and unit tested with 100% coverage.
Some of the Pascal code we wrote in the late 90s is still in production delivering value to the industry. We are planning a 20 year or longer life for our Python code so have a somewhat manic focus on quality.
Josh leads AEMO's Data Science team within Operational Forecasting, where they are responsible for the development and implementation of new machine learning (ML) models for operational grid demand and variable renewable energy (VRE) forecasting.
Josh has a long history in numerical modelling and writing code, originally as an Engineer, and subsequently in a varied career comprising wind and solar farm design in Southern Africa, energy modelling for a large Australian energy retailer, and the past 7 years working across various forecasting teams within AEMO, with a key focus on delivery of new modelling capabilities.
Josh is passionate about the use and promotion of open-source software, starting years back attending events at the University of Cape Town Linux Enthusiasts Group (UCT LEG), and the Ubuntu ZA LoCo, and with interests ranging across Linux, sysadmin, robotics, and programming languages geared towards AI/ML such as Python and R.