Management of service availability for multi-access edge computing
View Patent ↗Provided are a method, system, and computer program product in which operations are performed to model edge servers and service reinitialization rates via continuous time probabilistic models. Context-aware edge server failure classification into critical or non-critical failure is performed by analyzing a context comprising one or more services, failure rates associated with edge servers, and service reinitialization rates.
1. A method comprising:
modeling edge servers and service reinitialization rates via continuous time probabilistic models; and
performing context-aware edge server failure classification into critical or non-critical failure by analyzing a context comprising one or more services, failure rates associated with the edge servers, and service reinitialization rates, wherein failure scenarios are analyzed by:
determining a probability associated with a drop in a number of active pods below a minimum specified number within a predetermined interval of time;
determining a probability of a rate of increase in a number of deployed pods; and
determining a probability that a number of reinitializations is greater than a predetermined number, wherein a pod is an instance of a service.
2. The method of claim 1 , wherein the continuous time probabilistic models comprise Continuous Time Markov Chains (CTMC), the method further comprising: encoding a failure scenario context with single or multiple services and different server failure rates under consideration using Continuous Stochastic Logic (CSL) specification.
3. The method of claim 2 , the method further comprising: utilizing CTMC models and the CSL specification with a CTMC to classify failure criticality level.
4. The method of claim 1 , wherein a comparative mechanism for evaluating availability due to failures is provided.
5. The method of claim 4 , wherein recommendations are made of failure criticality of different geo-located edge sites.
6. The method of claim 1 , the method further comprising: analyzing an impact of failures and service reinitialization on service availability.
7. The method of claim 1 , wherein failure scenarios are analyzed by metrics in CSL, and recommendations are made for service criticality.
8. A system, comprising:
a memory; and
a processor coupled to the memory, wherein the processor performs operations, the operations comprising:
modeling edge servers and service reinitialization rates via continuous time probabilistic models; and
performing context-aware edge server failure classification into critical or non-critical failure by analyzing a context comprising one or more services, failure rates associated with the edge servers, and service reinitialization rates, wherein failure scenarios are analyzed by:
determining a probability associated with a drop in a number of active pods below a minimum specified number within a predetermined interval of time;
determining a probability of a rate of increase in a number of deployed pods; and
determining a probability that a number of reinitializations is greater than a predetermined number, wherein a pod is an instance of a service.
9. The system of claim 8 , wherein the continuous time probabilistic models comprise Continuous Time Markov Chains (CTMC), the operations further comprising: encoding a failure scenario context with single or multiple services and different server failure rates under consideration using Continuous Stochastic Logic (CSL) specification.
10. The system of claim 9 , the operations further comprising: utilizing CTMC models and the CSL specification with a CTMC to classify failure criticality level.
11. The system of claim 8 , wherein a comparative mechanism for evaluating availability due to failures is provided.
12. The system of claim 11 , wherein recommendations are made of failure criticality of different geo-located edge sites.
13. The system of claim 8 , the operations further comprising: analyzing an impact of failures and service reinitialization on service availability.
14. The system of claim 8 , wherein failure scenarios are analyzed by metrics in CSL, and recommendations are made for service criticality.
15. A computer program product, the computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code when executed is configured to perform operations, the operations comprising:
modeling edge servers and service reinitialization rates via continuous time probabilistic models; and
performing context-aware edge server failure classification into critical or non-critical failure by analyzing a context comprising one or more services, failure rates associated with the edge servers, and service reinitialization rates, wherein failure scenarios are analyzed by:
determining a probability associated with a drop in a number of active pods below a minimum specified number within a predetermined interval of time;
determining a probability of a rate of increase in a number of deployed pods; and
determining a probability that a number of reinitializations is greater than a predetermined number, wherein a pod is an instance of a service.
16. The computer program product of claim 15 , wherein the continuous time probabilistic models comprise Continuous Time Markov Chains (CTMC), the operations further comprising:
encoding a failure scenario context with single or multiple services and different server failure rates under consideration using Continuous Stochastic Logic (CSL) specification.
17. The computer program product of claim 16 , the operations further comprising:
utilizing CTMC models and the CSL specification with a CTMC to classify failure criticality level.
18. The computer program product of claim 15 , wherein a comparative mechanism for evaluating availability due to failures is provided.
19. The computer program product of claim 18 , wherein recommendations are made of failure criticality of different geo-located edge sites.
20. The computer program product of claim 15 , the operations further comprising:
analyzing an impact of failures and service reinitialization on service availability.