Plain-language summary
- What it solves
- An industrial steam network can be fed in many ways: some cost less and emit less.
- Who it can serve
- Anyone running industrial utilities, and anyone studying energy cost optimisation.
- What it produces
- Current versus optimal cost, how to dispatch the steam, and the emissions difference. On simulated demand and real or configurable prices.
Evaluate steam-network dispatch and cost with a transparent optimisation problem compared against a reference policy.
3 · What it produces
Reference/optimized cost, steam dispatch, direct-combustion ΔCO₂, LP shadow prices and perturbation-based MILP marginal values.
The cards expose multiple views of the same workflow so result, method, evidence and history remain distinct. Demo utility demand uses synthetic data (simulated data); prices and scenarios are disclosed separately.
4 · How it works
Utility balances + LP/MILP + frozen reference policy
1steam demand based on synthetic data (simulated data), capacities/efficiencies, EEX TTF, licence-checked Energy-Charts Italian bidding-zone day-ahead power, EUA
2HiGHS LP and MILP; dispatch and perturb/re-opt
3feasibility, balances, optimality, solve time, stability and reference policy
4Persistence, rendering and governed publishing.
5 · Data and signals
| Element | Detail |
|---|---|
| Data and signals | steam demand based on synthetic data (simulated data), capacities/efficiencies, EEX TTF, licence-checked Energy-Charts Italian bidding-zone day-ahead power, EUA |
| Industrial transferability | energy management, steam balancing and capacity debottlenecking |
| Research | LP duality, unit commitment and sensitivity |
| Interpretation condition | utility demand based on synthetic data (simulated data); modelled opportunity, not measured plant savings; electrical balance not modelled |
HiGHS LP and MILP; dispatch and perturb/re-opt
feasibility, balances, optimality, solve time, stability and reference policy
Python, SciPy HiGHS, NumPy, pandas, SQLite, Matplotlib
calling MILP marginal values duals or presenting simulated savings as measured savings
Workflow technical dossier
Methods, checks, stack and transferability conditions.
Data and signals
steam demand based on synthetic data (simulated data), capacities/efficiencies, EEX TTF, licence-checked Energy-Charts Italian bidding-zone day-ahead power, EUA
Inference / calculation
HiGHS LP and MILP; dispatch and perturb/re-opt
Validation
feasibility, balances, optimality, solve time, stability and reference policy
Stack
Python, SciPy HiGHS, NumPy, pandas, SQLite, Matplotlib
Limitations
calling MILP marginal values duals or presenting simulated savings as measured savings
See recent outputs
The Publications page collects local previews and, on request, the public feed.
Potential transferability
Have a problem similar to Energy & Steam Optimizer?
A first discussion can start from the objective, available data and success criterion without sending confidential information. A result observed here is not assumed to transfer automatically to another context.