Skip to main content


OpenSTEF Delivers Operational Forecasts at Hundreds of Grid Locations for Alliander

By Blog, Resource

Download this case study in PDF format

The Challenge

As a grid operator, Alliander – the largest distribution system operator (DSO) in the Netherlands – required accurate forecasts of the load on the electricity grid looking hours to days ahead. With the rise in renewable energy and electrification of energy consumption pushing the capacity of grids even further, this need will only continue to grow. To address this important topic, Alliander started the project OpenSTEF (short for Short-Term-Energy-Forecasting) to anticipate congestion in the distribution grid, allow for grid safety analysis in the transmission grid, and enable smart grid innovations to locally balance supply and demand within the constraints of the grid. This is essential for anticipating local congestion levels and making the most of existing assets to achieve load balance and improve efficiency.

The Solution

OpenSTEF provides a full toolstack to deliver accurate load forecasts over short term periods of up to several days. Given a time series of measured (net) load or generation, a fully automated machine learning pipeline is executed which delivers a probabilistic forecast of future load. The tool works for energy consumption, (renewable) generation, or a combination of both.

“In the real world, input data is not perfect, and measurements can become defective or data sources become unavailable,” said Frank Kreuwel, data scientist at Alliander and lead maintainer of OpenSTEF. “OpenSTEF was built to provide validation of the input data, combine measurements with external predictors such as weather data and market prices, train any scikit-learn compatible machine learning model, and deliver forecasts via both an API and an expert graphical user interface.” 

The OpenSTEF stack is based on open source technology and standards and is organized in a microservice architecture optimized for cloud deployment. Alliander has also completely open sourced the OpenSTEF code and contributed the project to LF Energy to ensure it is neutrally governed. By open sourcing the stack, OpenSTEF can provide an industry standard for generating and evaluating forecasts in the operational time-domain, as well as allow for structured collaboration.

The Results

Today, OpenSTEF is delivering operational forecasts at hundreds of locations in the grid for Alliander. These forecasts are used for grid safety analyses, communication on DSO-to-TSO interfaces, and to enable smart-grid based innovations. The most prominent features and use cases for OpenSTEF include:

  • Resiliency: As forecast availability is critical in energy sector applications, OpenSTEF deploys multiple fallback strategies, meaning a forecast is always available. When a fallback forecast is issued this is always labeled as such making it possible to reconstruct on which forecasts a decision is based.
  • Cloud-based and platform-agnostic OpenSTEF is fully containerized and runs on any container platform. A reference implementation is available that can be deployed directly. Most users will however have a unique IT landscape in which case the modular nature of OpenSTEF enables users to easily adapt OpenSTEF to their environment.
  • Making decisions can be difficult, so OpenSTEF enables making risk-based decisions by providing probabilistic forecasts. This way users can work towards a standard policy to react to predicted events.
  • With renewable sources making up an increasing fraction of the energy mix, balancing the grid can be challenging. OpenSTEF provides insight into the portion of power coming from wind and solar generation, which is particularly relevant for meeting EU commision regulation No. 543/2013, which “lays down the minimum common set of data relating to generation, transportation and consumption of electricity to be made available to market participants.”

Kreuwel continued, “OpenSTEF is proving to be highly effective at short term forecasting, but there is still work to be done. In light of continuing digital transformation activities across the power sector and the growth in renewables, we need to further expand OpenSTEF’s functionality and improve its performance.”

Those who wish to contribute may get involved by exploring the OpenSTEF Project on GitHub and subscribing to the community mailing list

Webinar: TenneT and RTE Discuss Open Source Benefits and Costs with Shuli Goodman

By Announcement, Blog, Latest, Resource, Uncategorized

This is a final reminder that Loek Bakker, Corporate Information Management Office Head at TenneT, and Lucian Balea, R&D Program Director for Réseau de Transport d’Electricité (RTE) will join LF Energy’s Executive Director Shuli Goodman tomorrow for a live discussion about open source and its benefits and costs on the path to the energy transition.

Read More

Linux Foundation Energy member TenneT “open sources” their open source strategy

By Announcement, Blog, Resource

TenneT is the first European cross-border electricity transmission system operator (TSO), with activities in the Netherlands and in Germany, providing uninterrupted electricity to over 41 million people. The security of our supply is among the best in Europe, with 99.99% grid availability. With the energy transition, TenneT is contributing to a future in which wind and solar energy are the most important primary sources to produce electricity.

Read More

Why The Energy Industry Needs Open Source Shared Technology

By Resource

Gabriel Bareux, RTE; Lucas Saludjian, RTE; Shuli Goodman, Executive Director LF Energy

Our electricity system is a complex, multi-player system that has slowly evolved over the last 125 years. Investments are made in hard assets – like transformers, relays, switches, generators, and substations – with a 30-80 year lifetime window. This has made the grid both a robust, sustainable, and efficient energy system, and a slow and lumbering management scheme that is resistant to change. The “electrification of everything” imperative driving the energy transition is forcing power systems engineers to become fast students in Moore’s Law of rapid innovation. These conditions – the need for change in a critical 24/7 environment that is a fairly rigid system now requiring immense flexibility – makes for an interesting moment in time and illustrates perfectly why open source shared technology and LF Energy are so critical to accelerating the diffusion of energy innovations. We can be moving and innovating faster – progress is in our hands.

Historically, grid operations are more or less organized in a layered fashion between transmission, distribution, generation, and load. It is the system interfaces between these layers that offers virtualization and communication opportunities – thereby allowing us to do more with less and move from centralized to distributed.

Operating the grid from a command and control paradigm is challenged because:

  • The dynamics of the operation of the grid have become incompatible with post-fault actions relying on solely on human intervention.
  • The rise of variable and distributed renewable energy resources (wind/sun/hydro), coupled with storage and electric mobility, plus the potential offered by demand response and IoT, require entirely new models and ways of facilitating the grid.
  • This exponential increase in the number of potential flexibilities produces a system that is far beyond the capability of a human brain to organize.

To explore but one part of a vast system of systems – take the transmission-distribution interface:

  • The first level of operation is at the centralized control room, which has been responsible for (from a few hours in advance until real-time) the optimal and robust control of grid elements (switches, breakers, voltage set points, HVDC set points, taps of phase shifters) and the balancing of the system (adequacy between generation and demand). These controls have been mainly manual (e.g opening of a breaker), semi-automated (e.g voltage control) or completely automated (primary frequency control) and implemented either as preventive actions or post-fault. Most post-fault actions must be compatible with the ability of an operator to react (minutes) with the help of tools such as SCADA systems.
  • The second level is at the substation.  This is where fast (ms or seconds) automation routines have been implemented to protect humans and physical assets when the grid is stressed beyond its nominal operational limits.

Technological challenges can become opportunities by leveraging new flexibilities to turn previously unimagined advances to our advantage:

  • Artificial intelligence and deep learning algorithms may be used to propose a global, optimal, and robust preventive actions/profiles, while taking into account the flexibilities provided by distributed, fast automations.
  • The ability for fast (seconds) control of sub-areas of the grid using distributed algorithms in digital substations. Smart algorithms can coordinate flexibilities located in tens/hundreds of substations, enabling the preventive profiles provided by the upper layer.
  • The ability to shape and orchestrate load control, along with distributed generation control, can enable grid operators to relax the constraints of grid operation, and/or short-term balancing, in flexible and innovative ways.

Our electricity system has been remarkably dependable, so much so that nearly all of us take it for granted: the grid’s stability, security, and reliability have enabled great social advances and robust economies. Yet, the grid, and power system in general, are brittle and slow to adapt to the social and political imperatives driving the fast pace of change. Timing – from hours, to minutes, to milliseconds – can be facilitated by smart communication between hardware and the system as-a-whole. Mastering the coordination is critical to opening the door to orchestrating and shaping electricity loads and demands through information and communication technology (ICT).

Leveraging open source shared technology, the new LF Energy project from The Linux Foundation is helping to push the envelope with ICT to exponentially increase network capacity as well as accelerate the energy transition and the move to renewable energy, electric mobility, demand response and more. Sign up for the LF Energy newsletter for the latest updates on this exciting new initiative.