Home › Hard problems › India

India: hard problems at India's scale

Grid forecasting with lots of solar

Solo: possibleOne person can test a narrow slice of it.

solar farmone day: morning to eveningpowerforecastwhat came: dips as clouds passthe distributorFills every gapbuys or sells powerat short notice,and loses money
Solar output swings with every passing cloud, and the electricity distributor pays to fill each gap between the forecast and what actually came.

Why it is still open

Solar and wind swing with the weather, and electricity distributors lose money balancing it.

An experiment one person can run in 8 weeks

Forecast next-day solar output for one state from open weather and generation data and compare it with a simple baseline.

Verdict: Solo: possible

Public data in places; the buyers are utilities (a sales cycle).

The solo test behind the verdict

  1. Can it be measured? There is a number that shows you did better, such as an error rate, a catch rate or a cost per answer.
  2. Is it cheap to try? It runs on a laptop, free open models and open data, or under about ₹50,000 of rented GPU time.
  3. Is there a public yardstick? A benchmark or dataset others use, so your result can be compared and believed.
  4. Would a small win get noticed? A lab, a funder or a customer would care about a 10% improvement, not only a full solution.

Four yeses means Solo: strong. Two or three means Solo: possible. Fewer means Follow, don't build.

PreviousWhere Delhi's air pollution comes fromNextToo few doctors in rural clinics

All 79 hard problems · Working on this, or know of a result we missed? basant@cleandataengineering.ai