Method and device for determining an estimated time before a technical incident in a computing infrastructure from values of performance indicators

A non-transitory computer program product for determining an estimated duration before a technical incident in a computing infrastructure comprising program code instructions for execution, on a computing device, of a method for determining an estimated duration before a technical incident in a computing infrastructure, said computing device comprising a data processing module, a storage module configured to store in memory at least one correlation base between performance indicators, said at least one correlation base comprising values of duration before becoming anomalous between said performance indicators that are correlated, and a collection module, said method comprising:

• receiving, by the collection module, performance indicator values of a computing infrastructure,
• identifying anomalous performance indicators, by the data processing module, said identifying anomalous performance indicators comprising an analysis of the performance indicator values to identify abnormal values and performance indicators associated with these abnormal values,
• identifying first at-risk indicators, by the data processing module from the at least one correlation base, said first at-risk indicators being performance indicators that are correlated with the anomalous performance indicators that are identified,
• identifying other at-risk indicators, by the data processing module from the at least one correlation base, said other at-risk indicators being performance indicators that are directly or indirectly correlated with the first at-risk indicators that are identified, and
• determining, by the data processing module, an estimated duration before a technical incident in the computing infrastructure to predict failures from weak signals, said estimated duration before a technical incident being calculated from the values of duration before becoming anomalous of the at least one correlation base for the first at-risk indicators that are identified and the other at-risk indicators that are identified,
• wherein the values of duration before becoming anomalous corresponds to the duration between an occurrence of an abnormal value for a performance indicator in question and an occurrence of an abnormal value for a performance indicator correlated with the performance indicator in question,
• wherein the determining the estimated duration comprises
• a calculation, from the first at-risk indicators that are identified and the other at-risk indicators that are identified, of several paths leading to a risk of technical incident,
• such that the estimated duration before a technical incident of the computing infrastructure is selected from several alternatives as said several paths,
• a calculation, from the first at-risk indicators that are identified and the other at-risk indicators that are identified, of a shortest path from said several paths leading to a risk of technical incident,
• such that a potential sequence of anomalies which will most quickly lead to failure of the computing infrastructure is identified as said shortest path, and
• converting the shortest path of said several paths into a chain of temporal values which, when added together, identify the estimated duration before technical incident.

A computing device for determining an estimated duration before a technical incident in a computing infrastructure, said computing device comprising:

• a data processing module,
• a storage module configured to store in memory at least one correlation base between performance indicators, said at least one correlation base comprising values of duration before becoming anomalous between said performance indicators, and
• a collection module, said collection module configured to receive performance indicator values of the computing infrastructure,
• wherein said data processing module is configured to
• identify anomalous performance indicators, said identify anomalous performance indicators comprising an analysis of the performance indicator values to identify abnormal values and performance indicators associated with these abnormal values,
• identify first at-risk indicators, from the at least one correlation base, said first at-risk indicators being performance indicators that are correlated with the anomalous performance indicators that are identified,
• identify other at-risk indicators, from the at least one correlation base, said other at-risk indicators being performance indicators that are directly or indirectly correlated with the first at-risk indicators that are identified, and
• determine an estimated duration before a technical incident, said estimated duration before a technical incident being calculated from values of duration before becoming anomalous of the at least one correlation base for the first at-risk indicators that are identified and the other at-risk indicators that are identified,
• wherein the values of duration before becoming anomalous corresponds to the duration between an occurrence of an abnormal value for a performance indicator in question and an occurrence of an abnormal value for a performance indicator correlated with the performance indicator in question,
• wherein the determining the estimated duration comprises
• a calculation, from the first at-risk indicators identified and the other at-risk indicators identified, of several paths leading to a risk of technical incident,
• such that the estimated duration before a technical incident of the computing infrastructure is selected from several alternatives as said several paths,
• a calculation, from the first at-risk indicators identified and the other at-risk indicators identified, of a shortest path from said several paths leading to a risk of technical incident,
• such that a potential sequence of anomalies which will most quickly lead to failure of the computing infrastructure is identified as said shortest path, and
• converting the shortest path of said several paths into a chain of temporal values which, when added together, identify the estimated duration before technical incident.