Predictive Resource Allocation for NFV Cloud Platforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Network Function Virtualization Management and Orchestration (NFV-MANO) architectures face inefficiencies in resource utilization due to static resource allocation, leading to underutilization during lean workload periods in Virtual Network Functions (VNFs) on cloud platforms, which results in suboptimal performance and increased costs.
Innovation Solution
The proposed solution involves using predictive analytics, specifically the ARIMA model, to forecast future resource utilization and dynamically allocate resources to additional workloads during lean periods, ensuring optimal resource utilization by identifying periods where resources are underutilized and reallocating them to support additional workloads without compromising existing application performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If static resource allocation is used to meet strict KPIs, then reliability is improved, but resource utilization deteriorates during lean workload periods
Solution Approach 1:
The patent implements dynamic resource allocation that adapts to changing workload conditions. The system continuously monitors workload patterns and adjusts resource allocation in real-time, transitioning from static to dynamic provisioning. This allows the system to maintain reliability during peak periods while optimizing resource utilization during lean periods through automated scaling and load balancing mechanisms.
Solution Approach 2:
The system changes resource allocation parameters based on workload conditions. By monitoring key performance indicators and workload metrics, the system dynamically adjusts CPU, memory, and storage allocation parameters. This enables optimal resource utilization across varying demand levels while maintaining service level agreements and KPI compliance.
2Reliability
If over-provisioning is done to secure stable deployment cost, then reliability is improved, but loss of energy increases due to underutilized resources
Solution Approach 1:
The system implements self-service resource management through automated monitoring and allocation. The resource allocation system autonomously adjusts provisioning based on actual demand, eliminating the need for conservative over-provisioning. This self-adjusting mechanism ensures deployment stability while preventing energy waste from underutilized resources by continuously optimizing allocation to match actual workload requirements.
Solution Approach 2:
The system incorporates feedback loops that monitor resource utilization and workload demands. This feedback mechanism enables the system to detect underutilization conditions and automatically adjust resource allocation downward, preventing energy waste. The feedback-driven approach maintains deployment stability by ensuring resources are available when needed while eliminating wasteful over-provisioning during low-demand periods.
3Ease of operation
If static mapping of resources is used, then ease of operation is improved, but resource utilization deteriorates
Solution Approach 1:
The system replaces manual static configuration with automated self-service resource mapping. The resource allocation system automatically discovers workload requirements and maps resources accordingly, eliminating the need for complex manual configuration. This self-service approach maintains operational simplicity while dramatically improving resource utilization by dynamically adapting to actual demand patterns.
Solution Approach 2:
The patent transforms static resource mapping into a dynamic, adaptive process. The system continuously monitors workload characteristics and automatically adjusts resource mapping in real-time based on actual usage patterns. This dynamic approach maintains ease of operation through automation while optimizing resource utilization by matching resources to actual demands rather than fixed allocations.
4Productivity
If additional workloads are deployed during lean periods, then productivity is improved, but reliability may deteriorate if resources are reallocated improperly
Solution Approach 1:
The system uses feedback mechanisms to monitor service quality and workload performance in real-time. Before and during resource reallocation for additional workloads, the system continuously checks KPI compliance and service levels. This feedback-driven approach ensures that productivity improvements from deploying additional workloads during lean periods do not compromise reliability or service quality.
Solution Approach 2:
The system performs preliminary assessments before deploying additional workloads during lean periods. It evaluates available capacity, predicts potential impacts on existing services, and validates resource availability beforehand. This preliminary action ensures that additional workloads can be deployed to improve productivity without jeopardizing the reliability of existing services.
Data Source
AI summary
This disclosure relates to deployment of additional workload in the NFV-MANO to efficiently utilize resources during a lean workload period of Virtual Network Functions (VNFs) associated with an intelligent cloud platform. The method comprises measuring, over a time period, a current resource utilization level of one or more rendered VNFs. Thereafter, forecasting future resource utilization for the time period based on predictive analysis criteria and the current resource utilization level of the one or more VNFs. The method further comprises a machine learning based inference for determining whether the forecast future resource utilization for said time period is less than a determined optimal resource utilization threshold value of the one or more VNFs. Thereafter, resources of the one or more VNFs to one or more additional workloads are allocated based on the determination of the future resource utilization.