AI-powered bidding platform for Australia’s biggest solar farm
Australian renewables developer Edify Energy and U.K.-based investor Octopus Group have deployed technology provider Fluence’s artificial intelligence-based trading platform to optimize the trading of the 333 MW Darlington Point Solar Farm in southwestern New South Wales.
Darlington Point, which is jointly owned by Edify and Octopus, is the largest solar farm connected to the National Electricity Market (NEM). It features an estimated 1,000,000 solar modules spread over 1,000 hectares and an output equivalent to powering about 115,000 Australian homes.
Octopus has confirmed that U.S.-based technology provider Fluence’s AI-powered trading platform will be deployed to ensure that the project maximizes generation during favorable market conditions. It will allow the installation to respond to market price signals to avoid generation at times of over-supply and negative prices.
“We are always striving to find innovative solutions that will improve asset performance for our investors,” said Octopus Australia Managing Director Sam Reynolds. “Solutions like this will help maximise revenue and investor returns by reducing price volatility, minimising costs and mitigating constraints.”
Darlington Point has a signed power purchase agreement (PPA) with Delta Electricity, the owner of the Vales Point coal-fired power station, for 150 MW, or approximately 55% of its output.
A 100 MW/ 200 MWh lithium-ion battery project is also set to be constructed alongside the solar farm. Earlier this year, the state government announced a AUD 3.2 billion ($2.4 billion), 10-year contract with Edify and Shell Energy. The Riverina Energy Storage System, to be built by early 2023 and operated by Edify, will provide critical dispatchable electricity prior to the closure of the Liddell Power Station.
Australia’s energy market is among the most complex in the world, with energy and ancillary services requiring assets to trade at five-minute intervals, while integrating increasing amounts of variable renewable energy. Renewable energy generation and battery asset operators in the NEM have to deal with exposure to negative prices, physical grid constraints, frequency control ancillary services (FCAS) costs, and managing trading strategies.
Automated bidding solutions are becoming a critical tool for asset owners in the NEM, where renewable energy assets need extremely accurate price forecasting capabilities to navigate “an increasingly volatile market,” said Fluence Chief Digital Officer Seyed Madaeni. “The deployment of our AI-based trading platform at the largest solar farm in the NEM confirms that automated bidding tools are now firmly established as critical tools for operating renewable assets in the NEM.”
Fluence, the result of a joint venture between U.S. utility AES and global power giant Siemens, said that its trading platform analyzes thousands of variables to provide leading price forecasting and optimization using proprietary machine-learning algorithms.
Fluence claims it can increase revenue for standalone renewable energy assets by more than 10% and can increase revenue and operational efficiency for battery-based energy storage by 40% to 50%. It said the software-based trading platform is currently used to optimize about 1.5 GW of wind and solar energy assets bidding into the NEM.
The Australian Energy Market Operator has noted that 30% of grid-scale solar and wind assets in the NEM have started using automated bidding solutions in the past two years. Edify is among the developers that have embraced the technology. It has deployed an AI-backed trading platform at all of its projects to help navigate the increasing price volatility and maximize returns in the NEM.
The list of operational solar farms that the Australian developer manages and partly owns includes Daydream (180 MW), Hayman (60 MW), Whitsunday (69 MW), Hamilton (69 MW) and Gannawarra (60 MW).
Please login to comment
[…] production and consumption dynamics. Already, AI is integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] synthetic intelligence and machine studying are integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power […]
[…] intelligence and machine learning are integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power […]
[…] patterns of production and consumption. Already, AI is integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] of production and consumption. Already, AI is integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power […]
[…] Around the world, AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power […]
[…] production and consumption. Already, AI is playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] production and consumption. Already, AI is playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] and consumption. Already, AI is enjoying a serious function in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] y consumo. La IA ya está desempeñando un papel importante en previsión de energías renovables, redes inteligentes, coordinación de la demanda y distribución de energía, maximizar la eficiencia de la producción […]
[…] and consumption. Already, AI is enjoying a significant position in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] and consumption. Already, AI is playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power […]
[…] and nuanced computing power. AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] and nuanced computing power. AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, […]
[…] and nuanced computing power. AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] and nuanced computing power. AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] and nuanced computing power. AI is already playing a major role in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] computing energy. AI is already enjoying a significant function in renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]
[…] transition in multiple domains, driving measurable improvements in renewable energy forecasting, grid operations and optimization, coordination of distributed energy assets and demand-side management, and materials innovation […]
[…] transition in multiple domains, driving measurable improvements in renewable energy forecasting, grid operations and optimization, coordination of distributed energy assets and demand-side management, and materials innovation and […]
[…] transition in multiple domains, driving measurable improvements in renewable energy forecasting, grid operations and optimization, coordination of distributed energy assets and demand-side management, and materials innovation and […]
[…] This content material is protected by copyright and is probably not reused. If you wish to cooperate with us and want to reuse a few of our content material, please contact: [email protected]. […]
[…] production and consumption dynamics. Already, AI is integral to renewable energy forecasting, smart grids, coordination of energy demand and distribution, maximizing efficiency of power production, and […]