Atomic deterministic next action with machine learning engine
Methods and apparatuses for providing a dynamically scalable ADNA Manager with decentralized atomic decision making are described. The decentralized atomic decision making may be performed using atomic deterministic next action (ADNA) task blocks that execute one or more workflow rules and then invoke one or more ADNAs within a pool of ADNAs. The ADNA Manager may identify a first ADNA task block, determine a set of input parameters for the first ADNA task block, detect that a first input parameter of the set of input parameters does not satisfy a qualification rule for the first ADNA task block, identify an exception ADNA task block in response to detection that the first input parameter does not satisfy the qualification rule, store breadcrumb information for the first ADNA task block within a persistence layer prior to the exception ADNA task block being invoked, and invoke the exception ADNA task block.
1 . A system including a dynamically scalable workflow engine for decentralized atomic decision making, comprising:
one or more processors configured to:
access a shared persistence layer, using a machine learning engine, to identify an atomic deterministic next action task block to be repaired;
automatically create a new atomic deterministic next action task block, via the dynamically scalable workflow engine, when the atomic deterministic next action task block to be repaired has invoked an exception atomic deterministic next action task block more than a threshold number of times;
add the new atomic deterministic next action task block to a pool of atomic deterministic next action task blocks;
update a first atomic deterministic next action task block to reference the new atomic deterministic next action task block that has been added to the pool of atomic deterministic next action task blocks, wherein the first atomic deterministic next action task block previously referenced the atomic deterministic next action task block to be repaired prior to the update;
invoke the new atomic deterministic next action task block using the updated first atomic deterministic next action task block; and
executing the new atomic deterministic next action task block on a new hardware device associated with the new atomic deterministic next action task block, in response to the new atomic deterministic next action task block being invoked, wherein the new hardware device is a component of a radio access network.
2 . The system of claim 1 , wherein the new atomic deterministic next action task block is associated with one or more of a new hardware device added to the system and a new virtual device added to the system.
3 . The system of claim 1 , wherein the new atomic deterministic next action task block corresponds with a newly instantiated virtualized network.
4 . The system of claim 1 , wherein the threshold number of times is more than ten times.
5 . The system of claim 1 , wherein the updated first atomic deterministic next action task block is automatically updated with a new workflow rule to acquire an updated input parameter.
6 . The system of claim 1 , wherein the one or more processors are configured to store breadcrumb information for the atomic deterministic next action task blocks within a persistence layer prior to the machine learning engine accessing the persistence layer.
7 . The system of claim 6 , wherein the breadcrumb information for the atomic deterministic next action task blocks includes a timestamp for when the atomic deterministic next action task blocks are invoked.
8 . The system of claim 6 , wherein the breadcrumb information for the atomic deterministic next action task blocks includes an identification of the atomic deterministic next action task blocks.
9 . The system of claim 1 , wherein the machine learning engine that accesses the shared persistence layer identifies a set of atomic deterministic next action task blocks to be repaired.
10 . The system of claim 9 , wherein the set of atomic deterministic next action task blocks to be repaired includes a plurality of atomic deterministic next action task blocks that invoked a greatest number of exception atomic deterministic next action task blocks.
11 . A method including a dynamically scalable workflow engine for decentralized atomic decision making, comprising:
accessing a shared persistence layer, using a machine learning engine, to identify an atomic deterministic next action task block to be repaired;
automatically creating, via the dynamically scalable workflow engine, when the atomic deterministic next action task block to be repaired has invoked an exception atomic deterministic next action task block more than a threshold number of times;
adding, using the processor, the new atomic deterministic next action task block to a pool of atomic deterministic next action task blocks;
updating, using the processor, a first atomic deterministic next action task block to reference the new atomic deterministic next action task block that has been added to the pool of atomic deterministic next action task blocks, wherein the first atomic deterministic next action task block previously referenced the atomic deterministic next action task block to be repaired prior to the update;
invoking, using the processor, the new atomic deterministic next action task block using the updated first atomic deterministic next action task block; and
executing the new atomic deterministic next action task block on a new hardware device associated with the new atomic deterministic next action task block, in response to the new atomic deterministic next action task block being invoked, wherein the new hardware device is a component of a radio access network.
12 . The method of claim 11 , wherein the new atomic deterministic next action task block is associated with one or more of a new hardware device added to the method and a new virtual device added to the method.
13 . The method of claim 11 , wherein the new atomic deterministic next action task block corresponds with a newly instantiated virtualized network.
14 . The method of claim 11 , wherein the threshold number of times is more than ten times.
15 . The method of claim 11 , wherein one or more processors are configured to store breadcrumb information for the atomic deterministic next action task blocks within a persistence layer prior to the machine learning engine accessing the persistence layer.
16 . The method of claim 11 , further comprising: storing breadcrumb information for the atomic deterministic next action task blocks that includes a timestamp for when the atomic deterministic next action task blocks are invoked.
17 . The method of claim 16 , wherein the breadcrumb information for the atomic deterministic next action task blocks includes an identification of the atomic deterministic next action task blocks.
18 . The method of claim 11 , wherein the machine learning engine that accesses the shared persistence layer identifies a set of atomic deterministic next action task blocks to be repaired.
19 . The method of claim 11 , wherein a set of atomic deterministic next action task blocks to be repaired includes a plurality of atomic deterministic next action task blocks that invoked a greatest number of exception atomic deterministic next action task blocks.
20 . A system including a dynamically scalable workflow engine for decentralized atomic decision making, comprising:
one or more processors configured to:
access a shared persistence layer, using a machine learning engine, to identify an atomic deterministic next action task block to be repaired;
automatically create a new atomic deterministic next action task block, via the dynamically scalable workflow engine, when the atomic deterministic next action task block has be repaired;
update a first atomic deterministic next action task block to reference the new atomic deterministic next action task block that has been added to a pool of atomic deterministic next action task blocks, wherein the first atomic deterministic next action task block previously referenced the atomic deterministic next action task block to be repaired prior to the update;
invoke the new atomic deterministic next action task block using the updated first atomic deterministic next action task block; and
executing the new atomic deterministic next action task block on a new hardware device associated with the new atomic deterministic next action task block, in response to the new atomic deterministic next action task block being invoked, wherein the new hardware device is a component of a radio access network.