ARA-Engine – Modeling the Alberta power grid transition in Python

I am developing the ARA-Engine, a Python-based framework designed to quantify the Alberta electricity market transition.

In merchant power markets like Alberta’s, institutional desks have proprietary tools to map real-time grid volatility to equity valuations. Retail traders, however, often rely on lagging financial statements. This project aims to bridge that gap by building an automated pipeline that connects AESO (ISO) API data directly to asset-level SOTP (Sum-of-the-Parts) models.

Current Functional Scope: - Real-time mapping of TSX-listed utility tickers to physical grid assets. - Quantitative tracking of "Capture Price" vs. "Pool Price" to identify revenue cannibalization in renewables. - Modeling the 2026 TIER carbon framework as a merchant margin indicator.

I’m looking for general advice on the architecture, but specifically: Is it viable to use these high-frequency grid indicators to inform medium-term equity trades? Or is the institutional advantage in this sector (via weather modeling and transmission forecasting) too wide for an open-source framework to bridge?