Machine Learning (ML)-based methods have been identified as capable of providing up to one day ahead Photovoltaic (PV) power forecasts. In this research, we introduce a generic physical model of a PV system into ML predictors to forecast from one to three days ahead. The only requirement is a basic dataset including power, wind speed and air temperature measurements. Then, these are recombined into physics informed metrics able to capture the operational point of the PV. In this way, the models learn about the physical relationships of the different features, effectively easing training. In order to generalise the results, we also present a methodology evaluating this physics informed approach. We present a study-case of a PV system in Denmark to validate our claims by extensively evaluating five different ML methods: Random Forest, Support Vector Machine, Convolutional Neural Networks (CNN), Long-Short Term Memory (LSTM) and a hybrid CNN–LSTM. The results show consistently how the best predictors use the proposed physics-informed features disregarding the particular ML-method, and forecasting horizon. However, also, how there is a threshold regarding the number of previous samples to be included that appears as a convex function.

This paper presents a new mixed-integer linear programming formulation for combined generation, storage and demand response expansion planning. The proposed formulation captures flexibility dynamics in integrated energy systems in long horizons with large temporal resolution. The objective function considers costs related to: investment, operation, emission penalties, fixed and variable maintenance. The considered units are: generators, storage (batteries and hydro-pumped) and demand response units (desalination, power-to-X, electric vehicles and electrolysers). The operation is modelled as an hourly unit commitment including time-dependent startup costs and intertemporal constraints such as ramping limits and minimum up and down times. This flexibility enabling formulation boosts renewable integration and contributes towards decarbonisation of other energy sectors such as transport. A commercial solver is used to evaluate the formulation for large scale cases considering 20 years horizon and 12 full weeks per year imposing minimum renewable shares of 50 and 100% in year 9 and 19, respectively. The formulation exceeds tractability limits of previous works, achieves lower over-installation and renewable curtailment by integrating flexibility in the generation expansion problem, and allows to size demand responsive units if desired.