To fill these gaps, we introduce SKIPP’D—a SKy Images and Photovoltaic Power Generation Dataset. The dataset contains three years (2017–2019) of quality-controlled down-sampled sky images and PV power generation data that is ready-to-use for short-term solar forecasting using deep learning.
Remote Pacific Island Renewable Project Example: Clean Gas Power Generation may have an important role in the Energy Transition from other more carbon intensive fuels like Coal, Heavy Fuel Oil (HFO) and Diesel – but for these remote islands it would be impacted by transportation and storage logistical factors.
A curated sky image and PV generation dataset is released for short-term solar forecasting. Processed benchmark data and raw data are both provided for flexibility of research. Reference codes for data processing and baseline model implementations are provided. Baseline deep learning models are developed to demonstrate the uses of the dataset.
The Sky 1.5 scenario reaches net zero carbon dioxide emissions globally, from all sources, by the late 2050s, whereas the Islands scenario doesn’t get there until some time in the first half of the 22 nd century. Waves arrives at the goal in 2100.
Both solutions could be installed to improve resilience, e.g. the 550 kW Wind Turbine (2 x 275 kW) site below in Samoa could easily have Solar PV panels installed on the same site to help provide electrical power in cases of wind lulls.
These remote islands face some of the highest fuel costs in the world due to their location and logistical challenges. It has also been noted that some of these communities have electrical load restrictions due to inadequate and aging (~20 years old in many cases) Conventional Power Generation equipment.