What are the data aggregation methods of, in particularly, residential usage and generation patterns, allow scaling up to a higher level such as patterns and uncertainty envelopes at a sub-station level? What are the differences of such model methods in, e.g., insights gained and performance?

AEMO makes generation decisions with not a high understanding what happens at the prosumer level on the one hand and on the other hand it is computational impractical considering all individual prosumers. Thus, one needs to balance between scalability and usable information where scalability means that not every data point needs to be taking into account.  At what abstraction level, we will make “correct” decisions without needing to know the behaviour of the individual residential assets.

How Can AI Foster Information Integration Across the Highly Specialized and Fragmented Australian Energy Market?

The Australian energy market is a uniquely complex and highly fragmented landscape, shaped by diverse geological, political, and economic factors. On the east coast, the gas wholesale market operates across various platforms, including the Gas Supply Hub (GSH), Day-Ahead Auction (DAA), Short-Term Trading Market (STTM), and Declared Wholesale Gas Market (DWGM). Complementary resources like the Gas Bulletin Board (GBB) and the East Coast Gas System (ECGS) further contribute to the sector’s intricacy. The wholesale electricity market is similarly divided, with the National Electricity Market (NEM) on the east coast and the Wholesale Electricity Market (WEM) on the west coast.

In addition to these primary markets, a network of distribution operators, numerous retailers, diverse customer segments, and an intricate web of regulatory bodies and stakeholders adds further layers of complexity. This structure reflects Australia’s historical, regional, and economic evolution, encompassing specialized terminology, technical documentation, procedural standards, regulatory frameworks, research publications, media coverage, and evolving policy amendments. The financial implications are substantial, impacting companies, government entities, and households alike, underscoring the critical need for efficient information flow.

Given AI’s proven ability to process and unify vast amounts of information, how can we leverage its capabilities to enhance integration and accessibility within the Australian energy market?

Other than AI this project has connections with Linear and Nonlinear Optimization: Optimization techniques are fundamental for resource allocation, demand forecasting, and efficient energy distribution across the different energy market platforms.
Game Theory: With multiple stakeholders (distribution operators, retailers, regulatory bodies), game theory can analyze interactions and incentives, improving market stability and cooperation, and Stochastic Modeling.

How do we coordinate energy generation, demand and storage to maximize reliability and minimize cost

Opturion partnered in the RACE 2030 project “Path to Net Zero”., and simulates and optimises hydrogen production plants for an international client. The company deploys advanced optimisation methods to solve strategic, tactical and operational applications in resource planning and allocation.
More details on the question
Generation and Storage:
What levels of solar and wind generation will be online by what date?
Assuming the grid can cope with the variations in demand and generation,
what mismatches between generation and demand can we expect in the coming years?
Do the mismatches balance out over timescales of a day, a week, a month or a year?
Will the scale of mismatches be too great to be handled by battery storage, and if so
what are the high capacity/long term storage options?
Will pumped hydro be available at scale in Australia?
…or will Australia resort to nuclear generation instead of large scale storage in the longer term?
How much gas will we need as a stopgap?

Demand:
Will demand reduce or increase? Can demand response be managed at large scales?

Risk:
What are the future impacts of climate and weather on energy generation?
What levels of (un)reliability are socially acceptable?
What number of users can acceptably suffer a blackout simultaneously?

How might we improve the supply resilience with limitted budget

Usually, we have 2-3 stormy days in Victoria per annum in which sever weather disrupts the electricity supply for a few hours and some customers remain off for a day our more. This majoe event days cost a lot for both Powercor and its customers.

—
Admin Note: This project has a strong focus on quantitative risk assessment in networks, combined with statistical inference for extreme weather events and fire propagation in Victoria.

Optimizing Grid Coordination in a Smart Metered Future

It is well recognised that coordination of supply and demand will become more complicated as consumer energy resources (CER) which able to flexibly operate in supply and demand continue to increase their presence throughout our energy system. Utilisation of smart meters is seen as a critical enabler for a coordinated and optimised grid, but their use comes with challenges including factors such as data privacy and limited on-board capabilities. Li et al., (20241) propose a federated learning model as one approach to reducing the computational and communication burden in a future with ubiquitous smart metering. Given the desire for Australia to have universal smart meter adoption by 2030 and a move to the development of distribution system operators (DSO2) in the Australian market, what role can an approach such as the federated model of Li et al., (2024) play against alternative methodologies that a DSO could employ using smart meters and/or alternatives including LV transformer monitoring.

1. https://doi.org/10.1038/s41467-024-53352-9
2. A DSO is responsible for managing and operating the distribution system, including integrating consumer energy resources (CERs). They need to ensure the reliability and efficiency of the system, while also balancing power inputs and outputs. They can have several responsibilities including:
Monitoring distribution grid conditions
Maintaining local and regional (through AEMO) system and network security
Dispatching local resources
Interacting with customers and enabling their choices
Signal network conditions to third parties

Optimizing Real Estate Portfolios for Net-Zero: The Role of Data Analytics and Integrative Design in Reducing Emissions

The real estate industry accounts for approximately 40 percent of global combustion related emissions1, of which 28 percent comes from building operations and 12 percent from embodied carbon.
Traditionally, owners have taken a project-by-project approach across their portfolios, focusing on discrete actions with clear stand-alone payback periods, such as installing high-efficiency equipment, lighting, and automated building controls. These choices are often based on marginal abatement cost curves (MACC) curves that prioritize stand-alone paybacks
For real estate portfolios, an optimized approach that uses data and analytics can yield significantly improved results. McKinsey1 note for example, that an optimised portfolio approach could result in net positive financial savings for net zero plans in commercial buildings where a traditional MACC approach would have resulted in a negative financial position. This is consistent with the teachings of integrative design espoused by Prof Amory Lovins over many decades2 and numerous studies that find advanced learning and data-driven modelling can provide customized yet scalable solutions with low cost3.
What approach, and what improvements might we achieve, through advanced data analytics and learning that can speed-up our transition to net-zero in the built environment in Australia?

https://www.mckinsey.com/~/media/mckinsey/industries/real%20estate/our%20insights/a%20new%20way%20to%20decarbonize%20buildings%20can%20lower%20emissions%20profitably/a-new-way-to-decarbonize-buildings-can-lower-emissions-profitably.pdf?shouldIndex=false
https://rmi.org/insight/integrative-design-a-disruptive-source-of-expanding-returns-to-investments-in-energy-efficiency/
https://doi.org/10.1038/s41467-024-50088-4

Digital Agriculture: R&D and Commercialization in Energy & Climate

Energy and climate are essential components in advancing digital agriculture. To better support farmers, we aim to lower their energy expenses, enhance climate resilience, and reduce risks through improved climate forecasting. What R&D directions and commercialization opportunities should we explore to meet these goals effectively?

Battery Management Software

How can we optimize solar battery usage in response to different network tariffs and varying business energy usage profiles, especially when faced with extreme weather conditions ? What decision-making and battery control strategies can help maximize efficiency and cost savings under these conditions?