Cyclic pattern detection and prediction execution

A computer-implemented method, the method comprising:

• obtaining data observations associated with a monitored process executed on a platform system to identify availability of service resources at the platform system, wherein the data observations are irregularly spaced in time;
• defining a list of time gaps, each time gap being defined as a difference between two data observations according to a common time measure;
• identifying, based on evaluating the list of time gaps, a cyclic pattern in a time distribution of the data observations, identifying comprising:
• identifying that a first time gap in the list of time gaps that is associated with a first set of subsequent time gaps of the list of time gaps matches a second time gap in the list of time gaps that is associated with a second set of subsequent time gaps, wherein the first time gap is associated with a first data observation at a first position i in the time distribution of the data observation, and wherein the second time gap is associated with a second data observation at a second position j in the time distribution of the data observation;
• identifying a length λ of a cycle as a number of time gaps in the first set of subsequent time gaps;
• identifying an index element of a time gap of the list of time gaps as a start element of the cycle to correspond to a lowest index element of either a first index element corresponding to the first time gap or a second index element corresponding to the second time gap in the list of time gaps;
• and
• identifying the cyclic pattern based on determining that the first position i and the second position j fulfill a rule defining that j=i+k λ, wherein k is a positive integer;
• obtaining predicted future data observations for a future horizon based on executing a prediction model according to the cyclic pattern;
• generating an instruction including an adjustment to an execution of a system monitoring process for the future horizon according to the predicted future data observations;
• and
• providing the instruction to the platform system.

A computer system comprising:

• one or more processors;
• and
• one or more computer-readable memories coupled to the one or more processors and having instructions stored thereon that are executable by the one or more processors to perform operations comprising:
• obtaining data observations associated with a monitored process executed on a platform system to identify availability of service resources at the platform system, wherein the data observations are irregularly spaced in time;
• defining a list of time gaps, each time gap being defined as a difference between two data observations according to a common time measure;
• identifying, based on evaluating the list of time gaps, a cyclic pattern in a time distribution of the data observations, identifying comprising:
• identifying that a first time gap in the list of time gaps that is associated with a first set of subsequent time gaps of the list of time gaps matches a second time gap in the list of time gaps that is associated with a second set of subsequent time gaps, wherein the first time gap is associated with a first data observation at a first position i in the time distribution of the data observation, and wherein the second time gap is associated with a second data observation at a second position j in the time distribution of the data observation;
• identifying a length λ of a cycle as a number of time gaps in the first set of subsequent time gaps;
• identifying an index element of a time gap of the list of time gaps as a start element of the cycle to correspond to a lowest index element of either a first index element corresponding to the first time gap or a second index element corresponding to the second time gap in the list of time gaps;
• and
• identifying the cyclic pattern based on determining that the first position i and the second position j fulfill a rule defining that j=i+k λ, wherein k is a positive integer;
• obtaining predicted future data observations for a future horizon based on executing a prediction model according to the cyclic pattern;
• generating an instruction including an adjustment to an execution of a system monitoring process for the future horizon according to the predicted future data observations;
• and
• providing the instruction to the platform system.

A non-transitory, computer-readable medium coupled to one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations comprising:

• obtaining data observations associated with a monitored process executed on a platform system to identify availability of service resources at the platform system, wherein the data observations are irregularly spaced in time;
• defining a list of time gaps, each time gap being defined as a difference between two data observations according to a common time measure;
• identifying, based on evaluating the list of time gaps, a cyclic pattern in a time distribution of the data observations, identifying comprising:
• identifying that a first time gap in the list of time gaps that is associated with a first set of subsequent time gaps of the list of time gaps matches a second time gap in the list of time gaps that is associated with a second set of subsequent time gaps, wherein the first time gap is associated with a first data observation at a first position i in the time distribution of the data observation, and wherein the second time gap is associated with a second data observation at a second position j in the time distribution of the data observation;
• identifying a length λ of a cycle as a number of time gaps in the first set of subsequent time gaps;
• identifying an index element of a time gap of the list of time gaps as a start element of the cycle to correspond to a lowest index element of either a first index element corresponding to the first time gap or a second index element corresponding to the second time gap in the list of time gaps;
• and
• identifying the cyclic pattern based on determining that the first position i and the second position j fulfill a rule defining that j=i+k λ, wherein k is a positive integer;
• obtaining predicted future data observations for a future horizon based on executing a prediction model according to the cyclic pattern;
• generating an instruction including an adjustment to an execution of a system monitoring process for the future horizon according to the predicted future data observations;
• and
• providing the instruction to the platform system.