{
  "id": "workflow:etl-pipeline-cost-optimization",
  "_kind": "Workflow",
  "_file": "workflows/workflows/workflows-data-deep.yaml",
  "_cluster": "workflows",
  "attributes": {
    "displayName": "ETL Pipeline Cost Optimization",
    "workflowKind": "governance",
    "triggerType": "scheduled",
    "typicalCadence": "monthly",
    "complexity": "cross-team",
    "description": "Optimizes compute costs and scheduling efficiency across ETL/ELT pipelines —\nprofiling per-pipeline resource consumption (CPU, memory, shuffle I/O)\nagainst actual data volumes, identifying over-provisioned Spark/Flink\nclusters and right-sizing executor configurations, consolidating overlapping\nextraction windows to reduce source-system load, migrating infrequently-run\nbatch jobs to spot/preemptible instances, evaluating incremental versus\nfull-refresh strategies per table based on change-data-capture feasibility,\nand tracking month-over-month cost trends with attribution to pipeline\nowners. Produces cost attribution dashboards, optimization recommendation\nreports, and scheduling conflict analyses. Excludes pipeline logic changes.\n"
  },
  "outgoingEdges": [
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "role:platform-engineer",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "role:data-scientist",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "role:cloud-architect",
      "kind": "involves_role",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "skill-area:etl-pipelines",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "skill-area:spark-jobs",
      "kind": "requires_skill_area",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "domain:data-engineering",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "domain:cloud-infra",
      "kind": "applies_to_domain",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "responsibility:cost-optimization",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "responsibility:capacity-planning",
      "kind": "triggers_responsibility",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "org-unit:data-platform-team",
      "kind": "performed_by_org_unit",
      "attributes": {}
    },
    {
      "from": "workflow:etl-pipeline-cost-optimization",
      "to": "org-unit:infra-engineering",
      "kind": "performed_by_org_unit",
      "attributes": {}
    }
  ],
  "incomingEdges": [
    {
      "from": "stack-profile:etl-reverse-etl",
      "to": "workflow:etl-pipeline-cost-optimization",
      "kind": "follows_workflow"
    }
  ]
}