Wind and solar farms to forecast their own output, in ARENA-backed pilot | RenewEconomy

Wind and solar farms to forecast their own output, in ARENA-backed pilot

Print Friendly, PDF & Email

ARENA funds AEMO-backed pilot to test potential for wind and solar farms to provide their own forecasts of generation output, and boost accuracy of market operations.

HDR image of a row of solar panels at sunset under a beautiful cloudscape with lens flares and sun rays
Print Friendly, PDF & Email

A pilot program to test the potential for wind and solar farms to provide their own forecasts of generation output, and thus improve the accuracy of market operations, has been awarded grant funding from the Australian Renewable Energy Agency.

In a joint statement with the Australian Energy Market Operator, ARENA said on Monday it had awarded $9.41 million to 11 different projects to trial short-term forecasting at large-scale wind and solar farms across Australia.

AEMO, which is currently responsible for forecasting how much electricity will be generated by wind and solar farms, has facilitated market changes as part of the initiative, allowing all wind and solar farms registered in the National Electricity Market to submit their own 5-minute ahead forecasts for use in central dispatch.

The ARENA-funded trial will be exploring the benefits that this new capability brings to the system, the statement said, and will incorporate at least 45 per cent of the NEM’s registered wind and solar capacity, which provides a combined total of 3.5GW of renewable electricity generation.

The portfolio of 11 projects will involve a range of weather forecasting technologies including cloud cameras for solar farms, wind speed radars, Japanese weather satellites, infrared, crunching of Bureau of Meteorology data and machine learning algorithms.

ARENA CEO Darren Miller said the trials would provide test cases for wind and solar to do their own five-minute forecasts just as traditional power plants do.

“Working with AEMO, we’re supporting these trials to help avoid generators being unfairly penalised for inaccurate forecasts while also supporting system security by better matching demand with anticipated supply from variable renewable generators,” Miller said.

“Much like traditional energy generators, we’re aiming to show that renewable energy is now capable of providing accurate measurement of energy output.

“With almost half of all solar and wind power generation taking part in projects in this initiative, this will lead to better deals for wind and solar farms, lower costs and more accurate data for AEMO.”

AEMO chief Audrey Zibelman welcomed the collaboration.

“Weather is the fuel for an ever-increasing proportion of the electricity generated across Australia, so it is vitally important that we foster innovation and rapid development of world leading technologies and services,” she said.

“As the market operator, we require the best possible information in real-time to manage the secure and reliable delivery of energy to Australian consumers, 24/7.”

Among the funding recipients is Danish wind giant Vestas, which confirmed on Monday it had been tapped by ARENA to develop a new short-term wind energy forecasting solution for Australia.

Vestas said the solution would be developed in partnership with its wholly-owned energy analytics solution provider, Utopus Insights, and tested at Infigen Energy’s Lake Bonney 2 and 3 Wind Farms in South Australia.

“An important challenge in wind and solar power is predicting fluctuations in generation to ensure system stability by balancing the energy supply and demand in the market”, said Vestas Australia and New Zealand head, Peter Cowling.

“We hope to offer a much more advanced forecasting solution that can reduce generator dispatch uncertainty, lower the operational cost of balancing energy supply and demand, and limit energy price volatility and regulatory complexity,” he said.

Other collaborators in the project include the CSIRO spin-off Windlab, which will use funding to apply machine learning algorithms and custom hardware to refine the accuracy of short-term forecasts at two of its wind project sites.

Industrial Monitoring and Control has been funded to further develop CSIRO’s cloud camera, currently used at large scale grid connected solar farms.

Another interesting pilot being led by Fulcrum 3D aims to generate and optimise solar farm forecasts, using ground based sky imaging devices – or “cloud cams” at Genex’s Kidston 1 Solar Project in Queensland – part of the industry-leading Kidston solar and pumped hydro storage hub.

The funding and potential new approach to 5-minute ahead renewables forecasting on the national grid follows news that Australia’s fleet of wind and solar projects – and many thermal generators for that matter – would be “de-rated” in the next financial year because of severe congestion in parts of the grid.

As RenewEconomy reported exclusively here, it was the second major de-rating in a row for many wind and solar projects as the Australian Energy Market Operator advised on the latest “marginal loss factors” (MLF) for each power plant.

Print Friendly, PDF & Email

Get up to 3 quotes from pre-vetted solar (and battery) installers.