Home / Swarm / Frameworks built on the swarm law

Frameworks built on the swarm law

The rules measured in real swarms, reused as controllers for grid batteries, mixed energy fleets, wildfire crews, epidemic response, air traffic, drones and logistics. Five run on real data, two in simulation, and the wildfire forecast still loses to a simple baseline.

The idea

The universal swarm study found the same three ingredients in real swarms: align with neighbours, switch from push to pull at about one neighbour distance, and pull the group back toward a set point. Each framework below reuses those rules as a controller, and each is compared with the simple rule or forecast people use today.

Results

DomainWhat the framework doesDataResult
Energy gridbatteries share discharge by state of charge (alignment) toward a 24-hour set pointreal ERCOT load, Oct to Dec 2020the rule-based framework cuts demand swings by 7.3% but not the peak. On the same data the trained battery swarm (10 seeds) cuts swings by 10.8% and the peak by 704 MW, ahead of the proportional rule (9.1%), a 24-hour forecast planner (6.8%) and a threshold rule (5.0%); the perfect-foresight bound is 949 MW. Use the trained swarm
Mixed-role energybatteries, solar with curtailment and demand response each act on the net load they see, with no coordinatorreal ERCOT + NREL data until the Ontario and Alberta files are downloadeddemand swings −14.5% and peak −453 MW with all three roles, against −11.7% with solar and batteries. More
Wildfireeach fire forecasts its final size with a growth law and bids for crewsreal US and Canadian fires (203 fires, the same fires at every horizon)median log error after 5, 8, 12 and 16 days: growth law 1.81, 1.52, 0.94, 0.68; persistence 0.83, 0.84, 0.56, 0.40. More days help the growth law a lot, but simple persistence still wins; it needs weather and fuel inputs
Epidemicseach region forecasts its wave and asks for help by forecast growthreal COVID-19 first wave, forecast 21 days ahead from the first 20% of the waveGompertz 0.16, Richards 0.26, exponential 0.86 (median absolute log error): saturating laws are 3 to 5 times better
Air trafficaircraft add swarm separation and alignment only inside an alert radiusreal OpenSky traffic for density; simulation for control0.51 close pairs (under 5 NM) per real snapshot; in simulation, close-pair steps fall from 28,635 to 3,920 (−86%)
Dronesflocking controller with gains measured in real swarms, plus goal seekingsimulationall 30 drones arrive; 3 obstacle hits vs 18 without alignment
Logisticsant-style task pickup with thresholds that adaptsimulationmean queue 5.6 vs 69 for round robin, with 70% fewer moves

What this does and doesn’t show

  • The epidemic and air-traffic results are the strongest: real data, a clear baseline and a large gap.
  • The drone and logistics results are simulations. They show the rules work as controllers, not that they beat a tuned real-world system.
  • The wildfire forecast is an honest loss, and the rule-based grid framework is weaker than the trained battery swarm. They are listed so the next step is clear.

What's next

  • Wildfire: add weather and fuel inputs, since the growth law alone still loses to persistence.
  • Energy: rerun the mixed-role swarm on Ontario (IESO) and Alberta (AESO) data.
  • Rule first: a swarm controller stays on only if it beats the rule on held-out data.

Updates