90%
Resource Savings
80%
59%
- Leveraging the operation metadata of the leading monitoring services/solutions and the CI/CD pipeline for optimized and continuous optimization of resource allocation
- Computationally feasible multi-layer correlation with predictive analytics for proactive scaling for assured application resilience
- Removing the guesswork of how the applications use resources to facilitate planning and resource orchestration
- Up to 80% cost savings by eliminating over-provisioning of resources and optimized placements in a MultiCloud environment
Challenges
The digital transformation journey driven by containerized applications orchestrated by Kubernetes delivers agility and efficiency. However, it also introduces new operational challenges across on-premises and multi-cloud deployments.
IT administrators and architects must manage increasing system complexity, diverse and unclear application KPIs, highly dynamic workloads, and numerous configuration variables required to meet optimization goals. As application scale grows and MultiClod strategies expand for cost, security, and resilience, these challenges increase significantly.
To move forward, organizations must address several key challenges:
- Increasing complexity across hybrid and multi-cloud infrastructures
- Lack of clear and unified application performance indicators
- Difficulty balancing cost optimization with performance requirements
- Limited ability to predict and proactively prevent issues
The Solution - Federator.ai®
Federator.ai, ProphetStor’s Artificial Intelligence for IT Operations (AIOps) platform, optimizes cloud operations for both cost and resilience. It ingests operational metadata to understand application behavior, KPIs, and how applications consume resources across underlying layers.
Its patented analytics engine performs continuous yet computationally efficient correlation and impact analysis, providing the intelligence needed to orchestrate container resources on top of virtual machines (VMs) or bare metal. This enables users to operate applications without dealing with initial infrastructure complexity. Federator.ai also enables fine-grained resource management to optimize both operational resilience and cost.
Federator.ai addresses these challenges by orchestrating resources across MultiCloud environments. As illustrated in the figure below, it optimizes both Day-1 deployment and Day-2 operations. By leveraging metrics from monitoring solutions such as Datadog, Sysdig, and Prometheus, Federator.ai dynamically predicts resource consumption and recommends the optimal allocation for pods. It reduces resource waste for typical workloads while preventing under-provisioning for mission-critical applications. Users can aggregate predicted pod requirements to determine the appropriate number and size of VMs, and optionally automate the execution of these recommendations.
Key Features
After Federator.ai is deployed in any Kubernetes, OpenShift, or VMware Tanzu environment, it learns application resource usage patterns from operational metadata. It predicts full-stack resource consumption down to the container level.
Federator.ai also performs multi-layer correlation and impact analysis, providing deep insights and resource recommendations across different layers of a Kubernetes cluster (or VM cluster). Through its APIs, it enables automation to optimize application performance and cost in multi-cloud environments.
To move forward, organizations must address several key challenges:
- Multi-layer workload prediction: Federator.ai applies patented machine learning analytics to predict resource usage across multiple levels, including clusters, nodes, namespaces, applications, and controllers. These predictions serve as the foundation for resource recommendations at each level. Federator.ai supports both physical and virtual CPU, memory, and network resources.
- Application-aware autoscaling and auto-provisioning: Predicted application resource demand determines the number and size of containers. Federator.ai uses workload-based resource usage predictions to recommend Just-in-Time Fitted container resources and automatically scale containers to meet demand.
- Application correlation and impact analysis: Federator.ai analyzes correlations between application microservices and provides system-level recommendations. It offers insights into how individual microservices are affected by external factors impacting the overall workload, helping prevent over- or under-provisioning. In addition, this correlation intelligence can support chargeback across applications and organizations based on resource usage.
- Intelligent cost management: Federator.ai analyzes cost efficiency and trends across clusters, nodes, namespaces, and applications based on expected workloads. It generates predictions and recommendations for planning and cost optimization.
- Policy-driven planning of CPU, memory, and networks: Federator.ai plans cluster-wide CPU, memory, and network allocation for different application types based on user-defined policies.
- Continuous recommendations for optimal resource planning: Federator.ai continuously generates recommendations and improves accuracy as more operational data is collected.
- MultiCloud and Muti-Instances considered: Federator.ai monitors cost structures across major cloud providers, understands workload characteristics, and recommends optimal placement across instance types (On-Demand, Reserved, Spot). It also considers regional pricing differences and analyzes cloud billing data to further optimize operational costs.
- Enterprise-ready: Federator.ai integrates with all Kubernetes distributions, including SUSE Rancher and Red Hat OpenShift environments, and supports application lifecycle management through operator frameworks.
Benefits
Federator.ai provides optimal resource planning recommendations to help enterprises make better operational and cost decisions. Key benefits include:
- Up to 80% resource savings: Federator.ai reduces unnecessary spending while improving application service quality. By leveraging patented analytics, it minimizes resource waste across infrastructure layers while maintaining required performance levels.
- Increased operational efficiency: Federator.ai eliminates the need for continuous manual monitoring of Kubernetes, OpenShift, VMware Tanzu, or VM clusters and cloud spending. It automates data collection, analysis, and configuration adjustments, reducing operational overhead.
- Reduced manual configuration with intelligent automation: Federator.ai enables users to activate its optimization engine to automatically provision and adjust resources as needed. Through its open APIs, users can dynamically configure pods with the right resource settings at the right time.
Feature Details and Specifications
| Feature Area | Key Capabilities/ Specifications |
|---|---|
| AI-based multi-layer workload predictions |
|
| Intelligent recommendations for resource planning |
|
| Application correlation and impact analysis |
|
| Proactive and application-aware autoscaling |
|
| Auto-provisioning application resources |
|
| CI/CD integration |
|
| Intelligent cost management |
|
| Multicloud cost analysis |
|
| Multiple metrics data sources |
|
| Alert Management |
|
| Auto-discovery of cluster resources |
|
| Config DB backup and restore |
|
| Open REST API |
|
| Setup wizard for easy installation |
|
| Usage-based licensing |
|
| Easy-to-use UI |
|
| Integration with third-party monitoring services |
|
| Supported platforms |
|