How does electricity consumption change in the city of Zurich?
Electricity consumption in the city of Zurich varies greatly depending on the time of year, the day of the week and the time of day. The current weather and public holidays are also influencing factors. Although consumption has fallen by around 12% since 2010, despite the increasing number of inhabitants, it is important to save electricity now because of potential power shortages this winter.
Electricity consumption forecast
With the help of machine learning, the statistically expected electricity consumption in the city of Zurich can be calculated and displayed visually using a range. If the effective consumption is at the lower or upper edge of the range for several weeks, this means a minimal decrease or a slight increase in electricity. Only when electricity consumption exceeds or falls below the upper or lower limit of the range can it be referred to as an effective increase or decrease in electricity consumption. This means that if the blue curve is lower than the lower limit of the range, electricity consumption has been significantly reduced.
Power consumption in the city of Zurich (online tool)
The display is updated daily at 2 pm. The first selectable electricity consumption curve (only in the city of Zurich) refers to households and SMEs (low voltage, grid level 7) and the other is for businesses and services with higher electricity consumption (medium voltage, grid level 5). The third electricity consumption curve includes both values.
How is the electricity consumption calculated?
The statistically expected electricity consumption is generated using machine learning. It is calculated for the previous seven days and displayed as a daily average within a range. Weather data that has actually been measured is also used and the upper and lower limits of the statistically expected electricity consumption are calculated using a regression model (Prophet Library). The effective power consumption is also based on the average measured values for the last seven days (rolling average), so that the two values can be compared. The regression model was trained using the measured consumption and weather data for the City of Zurich from 1 January 2015 to 31 August 2022. Thanks to this procedure, deviations caused by weekends and public holidays can be taken into account, as they do not fall on the same date each year and energy consumption is lower than during the week.
Power consumption data as open data
The data used here can also be accessed via the city of Zurich’s open data catalogue (in German), which contains many different data series and can be used freely. Further graphs showing electricity consumption can be found on this additional page.
