Optimal Operation of Community Energy Storage using Stochastic Gradient
Boosting Trees
Abstract
This paper proposes an algorithm for the optimal operation of community
energy storage systems (ESSs) using a machine learning (ML) model, by
solving a nonlinear programming (NLP) problem iteratively to obtain
synthetic data. The NLP model minimizes the network’s total energy
losses by setting the operation points of a community ESS. The
optimization model is solved recursively by Monte Carlo simulations in a
distribution system with high PV penetration, considering uncertainty in
exogenous parameters. Obtained optimal solutions provide the training
dataset for a stochastic gradient boosting trees (SGBT) ML algorithm.
The predictions obtained from the ML model have been compared to the
optimal ESS operation to assess the model’s accuracy. Furthermore, the
sensitivity of the ML model has been tested considering the sampling
size and the number of predictors. Results showed an accuracy of 98%
for the SGBT model compared to optimal solutions, even after a reduction
of 83% in the number of predictors.