Recent research suggests smarter software could transform the way Australian households understand their solar systems – from production to consumption – without necessarily adding more hardware.
Can inverter data reveal solar problems?
An Australian study examined whether inverter data alone can detect underperformance in solar production. Meanwhile, a separate study in Switzerland examined estimating household electricity consumption using smart meter measurements without dedicated CTs (current transformers). Overall, the research points to a future where software could give households a clearer view of what’s actually going on in their systems, potentially helping them get better value from their solar system.
Why monitoring is important
The “holy grail” of solar monitoring is to see both solar energy production and household consumption in real time, identify system problems early, and get tips to improve home consumption. Most system owners only see solar production through their inverter app, meaning performance issues and optimization opportunities can easily go unnoticed. The stakes are even higher for households with batteries, where knowing when energy is generated, stored and consumed can have a direct impact on savings.
Today, full visibility generally requires either the installation of current transformers in the switchgear or a third-party monitoring platform that integrates smart meter data. Many users don’t see enough benefit to justify additional hardware or subscriptions, especially when the system appears to be running smoothly. Standard inverter apps still focus primarily on solar PV performance.
Australian Solar Production Monitoring Research
Scientists from the University of Technology Sydney, energy resources company Diagno Energy and the University of New South Wales have contributed to a new Australian study that analyzed the AC-side solar production of over 1,000 residential complexes in several regions. Using only standard inverter data, the researchers developed a rules-based workflow that compares expected daily output – based on system specifications and local weather – to actual generation and flags deviations that indicate common errors such as inverter trips, extended zero power or clipping.
This approach is new because it can detect and classify underperformance without additional sensors or high-resolution measurements. The method identified most major errors with high accuracy – showing that existing inverter data, at least in this dataset, can be better used.
Overall, the study shows that manufacturers and monitoring platforms can use this workflow to identify problems and improve the performance of systems already in use. This is a useful, incremental step toward smarter diagnostics of solar power generation, but does not provide device-level insights or real-time consumption information.
Research on consumption data without additional CTs
Meanwhile, researchers at the Urban Energy Systems Laboratory in Switzerland investigated whether ordinary smart meter data recorded at intervals of 1 to 15 minutes could estimate the energy consumption of individual devices – a technique known as non-intrusive load monitoring (NILM). They tested six algorithms – from statistical methods to modern deep learning models – on different data sets and recording intervals.
The study found that deep learning models such as SGN and Seq2Point outperformed older methods and more accurately captured both regular and changing patterns in device usage. Performance still varied depending on device type and data frequency, showing that very low-frequency smart meter data can provide useful, but not perfect, device-level readings.
This research is relevant to Australia because it suggests that standard smart meters could one day give households a more detailed understanding of consumption without additional power converters or sensors, although the technology is still experimental.
Comparison to current monitoring
In Australia, electricity networks already record household consumption through smart meters for billing and network management. However, these meters do not provide the household with real-time self-consumption or device-level insight.
Some monitoring platforms can combine inverter production with household consumption data, either through CTs or by accessing smart meter totals. These services require additional setup and are outside of the standard inverter apps.
Commercial platforms such as Solar Analytics can display total household consumption in addition to solar production, sometimes without additional hardware. However, without CTs or other sensors, they cannot break consumption down to individual devices, which makes the NILM approach in the Swiss study unique in terms of its sophistication and scope.
The snack bar
Taken together, these studies suggest smarter, more data-driven solar monitoring. Currently, getting a complete picture still requires additional hardware or a dedicated platform, while standard inverter apps only focus on solar output.
Better software could one day give households a clearer sense of how their systems actually work. It could also offer energy retailers a new way to offer “smart diagnostics” as a paid upgrade.
For those seeking more comprehensive monitoring today, a dedicated platform remains the most practical option. To compare solutions, read the SolarQuotes guide to solar monitoring.
Comments are closed.