Context

Renewable generation often fluctuates faster than grid demand, creating surplus energy periods that must be managed carefully to maintain stability. The Curtailment Recommendation Assistant uses an AI‑first planning approach to help operators and planners visualize generation vs. load, detect surplus windows, and receive optimized curtailment recommendations. Built through Microsoft Planner Designer, it generates a structured blueprint,defining purpose, users, processes, and data models—to support transparent and predictable grid‑side decision‑making.

Challenges

Planners traditionally rely on manual inspection of generation curves and load profiles, making it hard to detect surplus periods quickly or understand the trade‑offs behind curtailment. Without a unified workflow, stakeholders struggle to review rationale, validate energy impact, or maintain transparency across decisions. Fragmented tables and unstructured data impede consistent surplus identification, curtailment estimation, and approval cycles.

Solution

The Curtailment Recommendation Assistant standardizes planning workflows and applies AI to evaluate renewable generation and load profiles, identify surplus windows, and propose optimized curtailment periods that minimize lost energy. A dedicated canvas app visualizes profiles, surplus slots, curtailment windows, and impact metrics, while an AI Copilot Advisor provides clear reasoning, trade‑offs, and data‑grounded recommendations. Approval workflows, dashboards, and structured data tables ensure planners and stakeholders share a common, transparent view of the curtailment plan and its expected outcomes.