AI & Mathematics

The maths that makes energy decisions pay

Machine learning, mixed-integer linear programming, optimisation, and the occasional bit of signal processing nobody else wanted to attempt. Applied to real energy problems, in production, where the maths usually has about 200 milliseconds to be right.

OptimisationMILPMachine learningSignal processing
0.2 ms
to dispatch 72 generators
Patent
approved disaggregation method
36–42%
cost improvement vs merit-order

In energy, the model controls real assets

Applied maths in energy isn't a paper you present and forget. The output goes off and does something — it dispatches a battery, schedules a plant, or turns up as a number on someone's electricity bill that they will absolutely query. That changes how you build it: accurate enough that you'd stake money on it, fast enough to run on whatever modest hardware is actually in the field, and never so clever that nobody can tell you why it did what it did.

“Electricity demand isn't a number to be met — it's a signal with layers. Read it the right way and the optimisation almost designs itself.”

From brief to working outcome

01

Formulate

Turn the business problem into the right mathematical one — objective, constraints, data.

02

Choose the method

MILP, LP, ML, signal processing — fit the technique to the problem, not the fashion.

03

Build & validate

Develop the model and test it against real data and the optimal benchmark.

04

Make it fast

Engineer it to run at the speed the application needs — milliseconds, on modest hardware.

05

Deploy

Put it into production with the software and data platform around it.

Full-spectrum capabilities

Optimisation

  • Mixed-integer linear programming (MILP)
  • Linear programming & dispatch
  • Production & capacity scheduling
  • Day-ahead price arbitrage

Machine learning

  • Load disaggregation & prediction
  • Anomaly detection in logs & telemetry
  • Forecasting & pattern recognition
  • Supervised learning from field data

Signal processing & statistics

  • Wavelet & frequency-domain methods
  • Statistical modelling & inference
  • Measurement & verification maths
  • Synchrophasor / time-series analysis

Applied research

  • Algorithm design & prototyping
  • Benchmarking against optimal
  • Patentable methods
  • Lightweight, dependency-free code

Where we've done this for real

Maths that runs in production, not just in a paper.

R&D

Wavelet-based dispatch for mixed fleets

Decomposing demand by timescale to dispatch 72 generators in 0.2 ms on a Raspberry Pi — within 2.3% of optimal, beating merit-order by 36–42% on cost.

View project →
M&V · USA

Patented load disaggregation

A patent-approved method (US 10,734,809) that infers fixture run-times from a single circuit signal — accurate enough to put on a bill.

View project →
Biogas · Germany

MILP production scheduling

Mixed-integer linear programming turns biological, storage and market constraints into a 15-minute dispatch schedule against day-ahead prices.

View project →
EV charging · USA

Charging-tariff optimisation

Demographic-driven demand personas and Time-of-Use modelling that size infrastructure and flatten peaks.

View project →

Frequently asked questions

Why not just use an off-the-shelf solver or library?

Sometimes you should — but the hard problems don't fit. A 72-generator fleet has more on/off states than grains of sand on Earth; we design methods (like wavelet-based dispatch) that sidestep the blow-up and run in milliseconds on cheap hardware.

Is the maths accurate enough to bill on?

When it has to be, yes. Our patented load-disaggregation method calculates the probability of each load being on accurately enough that customers and utilities will sign off the savings on every M&V project.

Can the models run on constrained hardware?

Yes. We've delivered dispatch as a 90KB dependency-free binary running on a Raspberry Pi — because in the field, fast and lightweight beats elegant-but-heavy.

Do you do applied research, or only production work?

Both. We prototype and benchmark novel methods against the optimal solution, and we engineer the winners into production systems with the software and data platform around them.

Get started

Got a problem the off-the-shelf tools can't crack?

We formulate it, solve it, and make it fast enough to run for real.

Talk to us →All capabilities