When you have thousands or millions of PV systems to model or forecast...

 With tens of millions of rooftop PV sites being installed annually around the globe, electricity network and market operators are increasingly in need of visibility on the energy generated by these systems.  Often these solar PV systems operate ‘behind the meter’ and send little to no real-time data back to the utilities responsible for ensuring their safe and reliable operation.  As soon as penetrations of these small (<100kW) and medium (<1 MW) solar PV sites reach 1-2% of total load, forecasting the power output of these PV systems starts to become critical for efficient market and network operation. 

We have created our Grid Aggregations product just for you! 

These challenges are precisely why we’ve created our Grid Aggregations product, which was designed for estimating the aggregate power output from a fleet of PV systems. We use our rapid-update cloud and irradiance modelling capability and combine it with information about the spatial distribution and installed capacities of your PV fleet to deliver our customers real-time, forecast and historical estimates fleet performance.  We deliver estimates in total power (MW) or performance units (such as % of total capacity) and update these data every 10 or 15 minutes.  

Related article: How do I know when a Grid Aggregation is the right choice for me?

Grid Aggregations are delivered in a format tailored for your market/network

The Grid Aggregations product is quite dynamic and is tailored specifically to customer requirements. For example, we can group (“aggregate”) the power output from all solar PV systems in a given market or other geographic region, or according to physical or virtual power asset (e.g. transmission or distribution network assets).

Grid Aggregations for Load Forecasting

If you are looking to improve your electricity load forecast for balancing or trading purposes, manage solar-related network congestion and voltage changes, or manage virtual power plants and microgrids, then Grid Aggregations may be of use to you.

Solcast runs over 750 such aggregations globally in real time, built up from millions of PV and grid assets, and can setup a demonstration for your organisation with little to no upfront costs. 

Image description: A Solcast Grid Aggregation in South Australia where PV power output totals are “aggregated” according to their transmission connection point. South Australia has some of the highest behind the meter solar penetration rates in the world.

Our customers use Solcast’s Grid Aggregations to: 

  • Train and improve load forecasting models to include the impacts of behind-the-meter solar generation

  • Manage low voltage network short and medium term demand forecasting, including planning for periods of minimum demand

  • Validate and tune models based on upscaling techniques or other surface data measurements

  • Manage spinning reserve or backup power supplies in tight demand situations or for remote grid applications

  • Dynamically control virtual power plants, including for the orchestration of low voltage network support services

  • Avoid the complexities of building in-house solutions, or to benchmark or improve existing in-house solutions

  • Account for the impacts of cloud cover on specific periods of demand, such a early morning or during periods of low demand and high solar production

Start a Solcast Grid Aggregation Live Trial Now!

You can get started on your first grid aggregation quickly and trial it by privately sharing very basic PV installation metadata (have you signed up for our API?). Get in touch with us via email, or using the chat bubble at the bottom right of your screen, and we'll provide you with a sample upload file format.

Once your aggregation goes live in our system (usually within 2-3 days), we’ll provide you with unique forecasting and estimated actuals API endpoints for your evaluation.

The first step in any Grid Aggregation journey, is to signup for the Solcast API. You can do that right now, for free!


Did this answer your question?