MSc
Smart Houses
A reimplementation of a published demand-response system: an LSTM forecasting twelve hours of electricity prices, feeding reinforcement-learning agents that schedule electric-vehicle charging.
A reimplementation of Lu, Hong and Yu’s demand-response system from IEEE Transactions on Smart Grid, in two stages: forecast the next twelve hourly electricity prices, then use those forecasts to decide when to charge an electric car.
- Reimplements
- Lu, Hong & Yu · IEEE Trans. Smart Grid 10(6), 2019
- My half
- The reinforcement-learning simulator
- Data
- Nord Pool prices · Test-An-EV charging histories · SmartHG
- Repository
- VincenzoImp/smart-houses
What it was
The work splits cleanly, and the git history shows it: Deborah Dore wrote the forecasting stage and the data pipeline; I wrote the simulator underneath the second stage. The forecaster reads fifty past hourly prices and predicts twelve ahead, and a three-hour hyperparameter search improved its RMSE from 0.059 to 0.043.
My half models the car battery four ways – never shifted, shifted as one block, split greedily across cheap hours, or continuously modulated by a Q-learning agent – and scores each against doing nothing, on cost, on energy actually delivered, and on how full the battery is when unplugged.
What I took from it
The committed results say something the report does not. There is a weighting between saving money and inconveniencing the driver, and everything depends on it. When cost is weighted four times more heavily than convenience, the scheduler wins clearly and cuts the bill by about a third, but it does so by delivering roughly a third less charge. Weight the two equally, and every reinforcement-learning variant scores worse than doing nothing. Weight convenience more heavily and all of them do.
That is the lesson, and it is not about reinforcement learning: a result reported at one setting of a trade-off parameter is a result about that setting. The evaluation ran at three, and only the flattering one made it into the write-up.