English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

As the use of solar power increases, having accurate and timely forecastswill be essential for smooth grid operators. There are many proposed methodsfor forecasting solar irradiance / solar power production. However, many ofthese methods formulate the problem as a time-series, relying on near real-timeaccess to observations at the location of interest to generate forecasts. Thisrequires both access to a real-time stream of data and enough historicalobservations for these methods to be deployed. In this paper, we propose theuse of Global methods to train our models in a generalised way, enabling themto generate forecasts for unseen locations. We apply this approach to bothclassical ML and state of the art methods. Using data from 20 locationsdistributed throughout the UK and widely available weather data, we show thatit is possible to build systems that do not require access to this data. Weutilise and compare both satellite and ground observations (e.g. temperature,pressure) of weather data. Leveraging weather observations and measurementsfrom other locations we show it is possible to create models capable ofaccurately forecasting solar irradiance at new locations. This could facilitateuse planning and optimisation for both newly deployed solar farms and domesticinstallations from the moment they come online. Additionally, we show thattraining a single global model for multiple locations can produce a more robustmodel with more consistent and accurate results across locations.

Local-Global Methods for Generalised Solar Irradiance Forecasting