The field “Quarantine (h)” indicates the number of hours before the start of the forecast for which load data is to be ignored. I.e. if you start a forecast on 1 May 2007 at 01.00 hours and this value is 168, the system will not utilise data after 24.00 hours on 23 April. This value has two purposes: firstly so that Aiolos can easily allow for a degree of scepticism relating to the most recent data; and secondly, when you test a forecast model and you want to compare a real situation where you perhaps do not have data for the most recent week.
The Quarantine setting can be both positive and negative. Thus, a value 0 does not turn the quarantine completely off, but merely sets the end of reliable data to the same as the forecast start date. In order to be able to use the real-time correction, a negative value must be specified. If for example a forecast is made that starts 2016-01-01 and has quarantine hours setting set to -10. In that case all values in the time series data after 2016-01-01 10:00 will be ignored. (Possible for the newer models)