Downloads · 30 days
13
41% of all-time downloads
alirezaaminzadeh/carbon-aware-production-energy-cooptimizer
carbon-aware-production-energy-cooptimizer is a machine learning model from alirezaaminzadeh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
An operations-research co-optimizer that jointly schedules industrial production and dispatches a factory microgrid (grid, solar, battery, generator, demand response) under a daily carbon quota with cap-and-trade cred…
Downloads · 30 days
13
41% of all-time downloads
All-time downloads
32
Public
Repo size
—
Likes
0
Public
Click a slice to open those files.
Other1.5 KB · 37%
From the Hugging Face model README
An operations-research co-optimizer that jointly schedules industrial production and dispatches a factory microgrid (grid, solar, battery, generator, demand response) under a daily carbon quota with cap-and-trade credit trading.
Minimise total operating cost = production + energy + peak demand charge + battery degradation + carbon credits, subject to meeting order due dates, machine capacity, battery dynamics, generator limits, demand-response commitments and the carbon quota.
The energy sub-problem is a linear program (economic dispatch) solved with HiGHS via scipy.optimize.linprog. The production sub-problem is a time-of-use-aware greedy heuristic. The two are coupled through the production load profile. A budgeted-uncertainty robust counterpart and a rolling-horizon MPC controller are provided as benchmark policies.
total_operating_cost_usd, energy_cost_usd, peak_demand_kw, co2_emissions_kg, battery_cycles, on_time_delivery_rate, production_utilization, renewable_curtailment_kwh.
See config.json for the structured model metadata.