Skip to content

AI for Resource Planners

Individual Contributor10 daily tasks · 1 industry

Also known as: IRP Analyst, Integrated Resource Planner

A Day in the Life

How AI changes daily work for Resource Planners

The Resource Planner develops the utility's long-term Integrated Resource Plan (IRP) — the roadmap for meeting future electricity demand through the optimal mix of generation, energy efficiency, demand response, and purchased power over a 10-30 year horizon.

Sorted by impact — tasks changing the most are at the top.

Load forecasting and scenario development
Enhances✓ Now

What you do today

Develop long-term load forecasts incorporating economic growth, energy efficiency, DER adoption, electrification trends (EVs, heat pumps), and weather normalization. Build multiple scenarios reflecting different future states.

AI that applies

AI improves forecast accuracy by incorporating granular data — building permit trends, EV registration rates, industrial pipeline, and climate-adjusted weather patterns — beyond traditional econometric models.

How it works

The system tracks learner progress, competency assessments, and engagement patterns across the learning environment. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The output is a forecast with confidence intervals, showing both the central estimate and the range of likely outcomes.

What Changes

Load forecasting moves from top-down econometric models to hybrid approaches blending econometrics with bottom-up AI analysis of adoption curves.

What Stays

Scenario design requires human judgment about what futures to plan for — economic disruptions, policy changes, technology breakthroughs — and how to weight them.

Capacity expansion modeling
Enhances✓ Now

What you do today

Run capacity expansion models to identify the least-cost portfolio of generation, storage, and demand-side resources that meets reliability, emissions, and policy requirements across planning scenarios.

AI that applies

AI-powered optimization engines evaluate millions of possible resource combinations across scenarios, incorporating unit commitment, dispatch simulation, and reliability constraints.

How it works

For capacity expansion modeling, the system evaluate millions of possible resource combinations across scenarios. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Planners can explore more scenarios and sensitivities as AI reduces model run times and enables broader optimization.

What Stays

Defining model inputs and assumptions, interpreting results, and making the critical judgment calls about which portfolios to recommend — models inform, humans decide.

Renewable energy procurement analysis
Enhances✓ Now

What you do today

Evaluate renewable energy procurement options — utility-scale solar, wind, storage PPAs, build-own-transfer agreements. Compare levelized costs, integration costs, capacity value, and contract terms.

AI that applies

AI benchmarks PPA pricing against market trends, models integration costs including firming and shaping, and evaluates contract risk factors across proposals.

How it works

The system aggregates vendor performance data — pricing, delivery, quality metrics, and contract compliance. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

PPA evaluation becomes more rigorous with AI-powered benchmarking against a broader market dataset.

What Stays

Negotiating contract terms, evaluating counterparty credit risk, and making strategic decisions about technology and timing that shape the utility's portfolio for decades.

Reliability and resource adequacy assessment
Enhances✓ Now

What you do today

Assess whether the planned resource portfolio maintains adequate reserves to meet peak demand with acceptable loss-of-load probability. Coordinate with RTOs/ISOs on regional resource adequacy requirements.

AI that applies

AI enables probabilistic reliability assessment using Monte Carlo simulation with correlated weather, outage, and demand variables rather than simplistic reserve margin calculations.

How it works

The system ingests Monte Carlo simulation with correlated weather as its primary data source. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Deterministic reserve margin checks evolve into probabilistic assessments that better capture the risks of weather-dependent resource portfolios.

What Stays

Interpreting reliability results, setting acceptable risk levels, and navigating the politics of resource adequacy requirements between state commissions and RTOs.

Emissions and clean energy compliance modeling
Enhances✓ Now

What you do today

Model compliance pathways for Renewable Portfolio Standards, Clean Energy Standards, and potential carbon regulations. Evaluate the cost and feasibility of alternative compliance strategies.

AI that applies

AI simulates compliance pathways under multiple regulatory scenarios, optimizing the timing of renewable additions, REC procurement, and thermal retirements to minimize compliance costs.

How it works

The system monitors regulatory data sources — rule changes, enforcement actions, and compliance records. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Compliance modeling becomes more dynamic, continuously updating as regulations evolve rather than waiting for the next IRP cycle.

What Stays

Developing compliance strategy, engaging with regulators on feasibility, and making judgment calls about regulatory risk that models cannot quantify.

Transmission and delivery system interface
Enhances◐ 1–3 yrs

What you do today

Coordinate resource plan assumptions with transmission planning — ensure new generation and load centers have adequate transmission, and that transmission expansion aligns with the resource plan timeline.

AI that applies

AI links resource planning and transmission planning models, identifying transmission constraints that affect resource siting decisions and vice versa.

How it works

For transmission and delivery system interface, the system draws on the relevant operational data and applies the appropriate analytical models. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Iterative resource-transmission planning cycles become more integrated through co-optimization.

What Stays

Navigating the organizational and regulatory boundaries between generation planning, transmission planning, and distribution planning — each with different stakeholders and timelines.

Demand-side resource evaluation
Enhances◐ 1–3 yrs

What you do today

Assess demand-side resources — energy efficiency programs, demand response, and behind-the-meter storage — as alternatives to supply-side additions. Evaluate achievable potential, cost-effectiveness, and reliability contributions.

AI that applies

AI models demand-side resource potential using granular customer data — AMI profiles, building characteristics, appliance saturation — to improve achievable potential estimates.

How it works

The system ingests granular customer data — AMI profiles as its primary data source. The analytics engine aggregates data across sources, applies statistical analysis to identify significant patterns and outliers, and presents the results through visualizations that highlight what needs attention. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Demand-side potential assessments move from survey-based estimates to data-driven models using actual customer energy profiles.

What Stays

Designing program structures, setting cost-effectiveness thresholds, and the regulatory advocacy needed to get demand-side resources valued fairly against supply-side options.

IRP stakeholder engagement
Enhances◐ 1–3 yrs

What you do today

Facilitate stakeholder engagement through IRP advisory groups, public workshops, and technical conferences. Present complex planning analysis in accessible formats and incorporate stakeholder input into the planning process.

AI that applies

AI helps generate stakeholder-friendly visualizations of complex modeling results and summarizes public comment themes for efficient review.

How it works

For irp stakeholder engagement, the system draws on the relevant operational data and applies the appropriate analytical models. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The output — stakeholder-friendly visualizations of complex modeling results and summarizes p — surfaces in the existing workflow where the practitioner can review and act on it.

What Changes

Data visualization and public comment analysis become more efficient.

What Stays

Facilitating contentious stakeholder discussions, translating technical analysis into public understanding, and the political navigation that makes or breaks an IRP proceeding.

IRP filing and regulatory defense
Enhances◐ 1–3 yrs

What you do today

Prepare the IRP filing document and supporting workpapers. Respond to commission staff data requests and defend the plan through hearing proceedings. Navigate the approval process that authorizes the utility to pursue its preferred portfolio.

AI that applies

AI assists with document assembly, cross-referencing workpapers, and preparing data request responses from the model outputs.

How it works

The system ingests model outputs as its primary data source. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The results integrate into the practitioner's existing workflow — presenting recommendations, flags, or automated outputs alongside their normal working context.

What Changes

Document preparation and data request response compilation accelerates.

What Stays

Crafting the regulatory narrative, defending planning assumptions under cross-examination, and the judgment about when to fight for preferred portfolio elements and when to compromise.

Emerging technology monitoring
Enhances○ 3–5+ yrs

What you do today

Track emerging technologies — long-duration storage, advanced nuclear, green hydrogen, enhanced geothermal — and assess when they should enter the planning process. Balance innovation with the utility's need for proven, financeable resources.

AI that applies

AI monitors technology development milestones, cost trajectory projections, and pilot project results across the industry to identify when emerging technologies cross the planning threshold.

How it works

The system ingests technology development milestones as its primary data source. The processing layer applies the appropriate analytical models to the structured data, generating scored outputs that surface the most actionable insights. The output is a prioritized alert queue, with the highest-confidence findings surfaced first for immediate review.

What Changes

Technology monitoring becomes more systematic with AI tracking development across hundreds of sources.

What Stays

Judging technology readiness for utility-scale deployment, managing the tension between innovation and prudence, and the engineering intuition about what will actually work at scale.

5 tasks AI-ready now 4 tasks within 1–3 yrs 1 task 3–5+ yrs out

Build your AI roadmap

Get a prioritized list of AI applications for your industry — ranked by impact and readiness.