Energy & Utilities · Rate Design & Revenue Requirements

Cost-of-Service Studies & Rate Case Preparation

Enhances→Stable

Available Now

Production-ready. Commercial solutions exist and organizations are actively deploying.

Trajectories describe the observable direction of human effort — not a prediction about specific roles, headcount, or individual careers.

What You Do Today

Perform cost-of-service allocation studies using AMI load research data, develop revenue requirements, design tariff structures, and prepare rate case exhibits. Each rate case involves months of analysis, thousands of data requests, and intense regulatory scrutiny.

AI Technologies

ML Segmentation (Customer Class Load Profile Clustering)ML Optimization (Cost Allocation Factor Calculation)Automated Reporting (Rate Case Exhibit Generation)NLP Extraction (Regulatory Precedent and Order Mining)Predictive Analytics (Rate Impact Simulation by Customer Class)

Roles Involved

Who works on this

Utility CFOVP Regulatory AffairsDirector of PricingPricing ManagerRate AnalystUtility PlannerResource Planner

C-SuiteVP/SVPDirectorManager/SupervisorIndividual Contributor

How It Works

ML automates allocation factor calculations from AMI load profiles, segments customers into cost-causation groups, and generates rate case exhibits that previously required months of spreadsheet work.

What Changes

COSS (Cost of Service Study) analysis that took months completes in weeks. Customer class load profiles are derived from millions of AMI reads instead of small sample sets. Rate impact analysis runs thousands of scenarios instead of a handful.

What Stays the Same

Rate case strategy and regulatory testimony. The commission cares about rate impacts on vulnerable customers, economic development, and political fairness — not just cost allocation mathematics. That judgment is human.

Cross-Industry Concepts

Customer Segmentation Document Automation Regulatory Compliance

Evidence & Sources

•NARUC rate case best practices
•AMI load research program data
•State PUC cost-of-service proceedings

Sources listed are directional references, not formal citations. Verify against primary sources before using in business cases or presentations.

Last reviewed: March 2026

What To Do Next

This section won't tell you what your numbers should be. It will show you how to find them yourself. Every instruction below produces a real, verifiable result in your organization. No benchmarks, no projections — just the steps to build your own evidence.

Establish Your Baseline

Know where you are before you move

Before adopting AI tools for cost-of-service studies & rate case preparation, document your current state in rate design & revenue requirements.

•

Map your current process: Document how cost-of-service studies & rate case preparation works today — who does what, how long each step takes, and where the bottlenecks are. Use your SCADA/EMS data to establish a factual baseline.

•

Identify the judgment calls: Rate case strategy and regulatory testimony. The commission cares about rate impacts on vulnerable customers, economic development, and political fairness — not just cost allocation mathematics. That judgment is human. — these are the boundaries AI won't cross. Know them before you start.

•

Check your data readiness: AI tools for rate design & revenue requirements need clean, accessible data. Check whether your SCADA/EMS has the historical data, integrations, and quality to support ML Segmentation (Customer Class Load Profile Clustering) tools.

Without a baseline, you can't tell whether AI actually improved cost-of-service studies & rate case preparation or just changed who does it.

Define Your Measures

What to track and how to calculate it

system reliability (SAIDI/SAIFI)

How to calculate

Measure system reliability (SAIDI/SAIFI) for cost-of-service studies & rate case preparation before and after AI adoption. Pull from your SCADA/EMS.

Why it matters

This is the most direct indicator of whether AI is adding value to rate design & revenue requirements.

generation efficiency

How to calculate

Track generation efficiency using the same methodology you use today. Don't change how you measure just because you changed how you work.

Why it matters

Speed without quality is just faster mistakes. Measure both together.

When to check: Check after 30 days of consistent use, then quarterly.

The commitment: Give new tools at least 30 days before judging. The first week is always awkward.

What NOT to measure: Don't measure AI adoption rate as a goal. Measure outcomes. If the tool helps with cost-of-service studies & rate case preparation, people will use it.