Extended evaluation datasets for IIoT TestBed (Release version 1 from November 28th, 2023)

This contribution serves as an extension of the existing evaluation data set and thus also for the evaluation of planning strategies for the IIoT test bed environment, which was presented here: https://zenodo.org/records/10212298.

This evaluation data set presented here comprises a total of four different files, each containing 1000 entries and thus describing 1000 different initial situations.  

The objective of this dataset is to assess and compare the policies achieved with different algorithms.

The first data set (#1) is identical to the data set already published in https://zenodo.org/records/10212319. The same environmental conditions apply here as in the training, however the situations for the agents are unseen.  

In the second evaluation data set (#2), the number of carriers used at the same time was increased by 25%, i.e. from 16 to 20.

In evaluation data set three (#3), the number of products to be completed varies between 50 and 500.  

In evaluation data set four (#4), the lot size was limited to 1, which means that each order only includes one product. This increases the diservity (product types and families) that are manufactured at the same time, which can lead to higher set-up efforts. In evaluation data set five (#5), the number of carriers used at the same time was increased by 50%, i.e. from 16 to 24.

In evaluation data set six (#6), the previously used work plans are no longer used, instead 3 new, previously unknown product variants are presented:variant number 7:  A -> C -> E -> G -> Ivariant number 8:  A -> B -> D -> F -> H -> Ivariant number 8:  A -> B -> C -> G -> H -> I

In evaluation data set seven (#7), The probability of occurrence of the errors as well as the error duration were doubled.

In evaluation data set eight (#8), various environmental changes are combined together. - The probability of occurrence of errors and the error duration have been increased by a factor of 1.2- The number of products to be produced has been set to 128 instead of 64 per episode- The batch size can vary between 1 and 10 instead of 1 and 3- The number of carriers has been set to 20 instead of 16- The previous 6 routings have been extended by 3 new, previously unknown work plans (analogous to dataset #6), so that an order can now be composed of 9 different product variants.