Advantage
Smarter load management through more reliable forecasts and automation of work steps
Data
Historical production and consumption data, current weather data, information from the areas of snowmaking and e-mobility, etc.
Solution
AI system for automated timetable creation – as a completely independent solution or in cooperation with the technical experts
Challenge
Variance in Electricity Production and Consumption
The Ursern Electricity Works (EWU) in Andermatt, Switzerland, is continuously expanding its electricity production. From run-of-river power plants to wind turbines, the EWU has a large variance in electricity production. A planned PV system will further increase this variance.
On the consumption side, in addition to the local residents and businesses, seasonal tourism and the operation of ski resorts, including snowmaking systems, are particularly important customers. E-mobility is a new component, which further complicates the forecasting and control of cost-intensive consumption peaks.
Economically critical day-ahead forecast dependent on expert knowledge
The EWU prepares a daily day-ahead forecast for EWA EnergieUri. A contractually agreed allowance for the deviation is stipulated. Anything above this allowance is subject to penalties. A massive increase in this penalty is being considered.
The forecast and thus the deployment plan for the power plants were previously carried out by an experienced operations manager using a complex Excel spreadsheet. With the retirement of this employee, EWU will lose this operational experience and knowledge in this system-critical area.
Increasing complexity requires new solutions
The additional PV production and the expansion of e-mobility will make manual creation impossible in the future due to the significantly increased overall complexity.
Goal
To ensure future compliance with the schedule and control peak power, the key elements of electricity production and consumption are to be controlled by a central intelligence system.
The use of artificial intelligence is intended to increase the accuracy of schedule forecasts, which are becoming increasingly important due to the threat of sanctions, while simultaneously compensating for the loss of expertise with increasing complexity.
Solution
The data science experts at eoda, part of VIVAVIS AG, which specializes in digital infrastructures, have taken over the development of the AI system for the automated creation of the timetable.
The AI system brings together all important information from electricity generation and consumption. For the 15-minute schedule forecasts, in addition to historical generation and consumption data, external information such as current weather data (wind speeds, precipitation amounts, temperature, etc.), public holidays, and information from the areas of snowmaking and e-mobility are also taken into account. The latter is particularly important to avoid unforeseen peak loads when arriving tourists want to charge their electric vehicles while the ski slopes need artificial snow.
The system also supports the identification of optimal periods for electricity sales or storage based on future consumption and price trends.
The system handles schedule management either completely independently or in collaboration with a specialist who oversees the planning. If important facts such as revisions or unavailability are already known in advance, these can be stored in the system and then taken into account by the AI when creating the schedule.
eoda's proprietary solution as a forecast scheduler
eoda offers its own solution for the automatic, cyclical execution of forecasts in 15-minute time frames.
Result
In times of increasingly volatile electricity production and demand, coupled with the ongoing digitalization of infrastructure, artificial intelligence can be a key component of future schedule management. AI can help transform the existing flood of information into reliable forecasts, thus making load management more intelligent and simultaneously automating work steps. Especially in times of skilled labor shortages and the widespread departure of experienced employees, self-learning algorithms fill emerging gaps.
Get started now:
We look forward to exchanging ideas with you.
Your expert on Data-Science-Projects:
Manfred Menze
projects@eoda.de
Tel. +49 561 87948-370
