Proa Analytics

Proa Analytics is an Australian company of engineers and scientists. With a deep knowledge about solar, optimisation, and energy systems, we provide validated forecasting and modelling solutions to our customers.

The founders of Proa previously created the rooftop PV generation model used by the Australian Energy Market Operator (AEMO) to calculate the solar generation in each postcode for the last 10 years. They also developed the energy system planning model for ARENA to optimise long term carbon abatement in the Australian electricity industry.

We are a proud member of the Microsoft Bizspark Plus start up program, and gratefully acknowledge Microsoft’s support. Our systems are built and run on the Azure cloud computing platform to provide reliable and scalable services to our customers.

Clients and partners

 

Solar forecasts

The Proa Forecasting System (PFS) was developed with advanced techniques to provide state-of-the-art forecasts to a range of applications where solar is increasingly important. Several data sources are combined to create an optimal forecast of the solar irradiance for each time scale. Then, detailed modelling of the configuration and shading of PV systems is used to estimate accurately their power output. For regional or networks forecasts, validated statistics on the performance of thousands of real world PV systems are used to calculate the aggregated generation.

The PFS can calculate custom solar forecasts for:

  • single PV systems,
  • large scale solar plants,
  • entire networks, states, or countries,
  • any application affected by solar irradiance (e.g. bushfire modelling or crop modelling)

Continue reading “Solar forecasts”

Applications

Proa’s solar forecasts are for anyone who needs to make decisions based on solar generation. If solar generation is high – or low – should a particular generator turn on? Should a battery recharge? What needs to be done to manage uncertain generation?

Market operators Networks operators Generators
Retailers  Traders Storage operators
Self-consumption Demand response Hybrid systems

Contact us to discuss a tailored solution to your particular case.

Optimal forecast mix

The Proa Forecasting System (PFS) uses multiple methods to provide an optimal combined forecast for all time scales. Each component forecasts is calculated independently, using independent input data, which creates redundancy and increases overall reliability.

  • Live Data forecasts (LDF): real time monitoring of the generation of a single system, or a group of PV systems, can be used to estimate the current cloud cover for a location or region.
  • Cloud Motion Vectoring forecasts (CMV): this method uses data from the Himawari-8 meteorological satellite, which provides high resolution images every 10 minutes. Our CMV algorithms detect the clouds, track their motion and forecast their position into the future.
  • Numerical Weather Prediction models (NWP): this methods uses dynamic equations and physical models of the atmosphere to estimate cloud formation and dissipation, and hence solar irradiance. The PFS uses several global and mesoscale NWP models.

The PFS forecast combines each of these methods, with optimal weights as a function of the forecast horizon, so that the combined forecast has the best performance over all time scales.

Custom input data

We can also incorporate your custom data feeds to improve the forecast accuracy. For example, if you have sky camera feeds for your site, we can include these to improve the forecasts. Our forecast engine will automatically combine all forecasts with the optimal weighting for each forecast horizon. Contact us to discuss custom input data further.

Data feed (API)

Our forecast API is designed for you to download and embed your new forecast into your systems or spreadsheets, or visualise the outputs to inspect the generation for the following hours. Forecasts are delivered with 10 minute updates and 10 minute resolution, 24/7 operation and 24/7 support.

The API  was built on Microsoft’s Azure cloud platform with the collaboration of our partner Object Consulting, and designed to deliver our forecasts securely in the most straightforward, fast and reliable way.