Radio access network slicing
A disclosed method may include (i) providing, to an end-user of a radio access network, a graphical user interface that enables the end-user to configure at least one of a plurality of control knobs for configuring a slice of the radio access network, (ii) receiving, after the providing the graphical user interface, user input from the end-user through the graphical user interface indicating how the end-user would adjust the at least one of the control knobs for configuring the slice of the radio access network, and (iii) configuring the slice of the radio access network according to the user input from the end-user through the graphical user interface. Related systems and computer-readable mediums are further disclosed.
1 . A method comprising:
receiving a dataset indicating preferences of at least one radio access network end-user;
applying a machine learning model to the dataset to map the preferences of each respective radio access network end-user to a respective radio access network slice in terms of at least one radiofrequency band; and
provisioning the radio access network slice to the at least one radio access network end-user, based on applying the machine learning model, consistent with the preferences;
wherein the preferences for a first end-user indicate at least one of:
a preference for maximum throughput except in a network load or congested condition;
a preference for maximum throughput guaranteed even during the network load or congested condition; or
a preference for an elevated maximum throughput that is guaranteed even during the network load or congested condition.
2 . The method of claim 1 , further comprising mapping the preferences of the first end-user to multiple distinct radiofrequency bands.
3 . The method of claim 1 , wherein the at least one radiofrequency band is categorized as either common, allocated, or reserved.
4 . The method of claim 1 , wherein the preferences for the first end-user indicate at least one of:
statistically normal outdoor coverage and reliability; or
extended indoor coverage and reliability.
5 . The method of claim 1 , wherein:
each respective radio access network slice is defined in terms of a set of pairs; and
each pair specifies both a radiofrequency band and a portion of the radiofrequency band
categorized as either common, allocated, or reserved.
6 . The method of claim 1 , further comprising:
receiving an indication that the first end-user has exhausted a reserved portion of radiofrequency spectrum; and
provisioning, in response to receiving the indication, at least a portion of common or allocated radiofrequency spectrum to the first end-user.
7 . The method of claim 1 , wherein the machine learning model was trained on a training dataset that mapped previous indications of end-user preferences to respective radio access network slices.
8 . The method of claim 7 , wherein the machine learning model was supervised due to labels of successful or unsuccessful mappings within the training dataset.
9 . The method of claim 7 , wherein the machine learning model was unsupervised.
10 . A system comprising:
a physical computing processor; and
a non-transitory computer-readable medium encoding instructions that, when executed by the physical computing processor, cause a computing device to perform a method comprising:
receiving a dataset indicating preferences of at least one radio access network end-user;
applying a machine learning model to the dataset to map the preferences of each respective radio access network end-user to a respective radio access network slice in terms of at least one radiofrequency band; and
provisioning the radio access network slice to the at least one radio access network end-user, based on applying the machine learning model, consistent with the preferences;
wherein the preferences for a first end-user indicate at least one of:
a preference for maximum throughput except in a network load or congested condition;
a preference for maximum throughput guaranteed even during the network load or congested condition; or
a preference for an elevated maximum throughput that is guaranteed even during the network load or congested condition.
11 . The system of claim 10 , wherein the system is further configured to map the preferences of the first end-user to multiple distinct radiofrequency bands.
12 . The system of claim 10 , wherein the at least one radiofrequency band is categorized as either common, allocated, or reserved.
13 . The system of claim 10 , wherein the preferences for the first end-user indicate at least one of:
statistically normal outdoor coverage and reliability; or
extended indoor coverage and reliability.
14 . The system of claim 10 , wherein:
each respective radio access network slice is defined in terms of a set of pairs; and
each pair specifies both a radiofrequency band and a portion of the radiofrequency band
categorized as either common, allocated, or reserved.
15 . The system of claim 10 , wherein the system is further configured to perform:
receiving an indication that the first end-user has exhausted a reserved portion of radiofrequency spectrum; and
provisioning, in response to receiving the indication, at least a portion of common or allocated radiofrequency spectrum to the first end-user.
16 . The system of claim 10 , wherein the machine learning model was trained on a training dataset that mapped previous indications of end-user preferences to respective radio access network slices.
17 . The system of claim 16 , wherein the machine learning model was supervised due to labels of successful or unsuccessful mappings within the training dataset.
18 . A non-transitory computer-readable medium encoding instructions that, when executed by at least one physical processor of a computing device, cause the computing device to perform a method comprising:
receiving a dataset indicating preferences of at least one radio access network end-user;
applying a machine learning model to the dataset to map the preferences of each respective radio access network end-user to a respective radio access network slice in terms of at least one radiofrequency band; and
provisioning the radio access network slice to the at least one radio access network end-user, based on applying the machine learning model, consistent with the preferences;
wherein the preferences for a first end-user indicate at least one of:
a preference for maximum throughput except in a network load or congested condition;
a preference for maximum throughput guaranteed even during the network load or congested condition; or
a preference for an elevated maximum throughput that is guaranteed even during the network load or congested condition.