AI is the master key to unblocking our power grids

As network constraints continue to bar a renewables boom, AI has the potential to unblock the path towards more sensitive, adaptive power grids, writes Amir Cohen of EGM.

A recent report warns that Europe’s wind and solar energy boom is being held back by power grid congestion and constraints. The problem is exemplified by the Netherlands where surging solar power capacity growth is being stunted by a grid capacity squeeze, threatening its national energy transition.

This is reflected worldwide with an estimated 930GW of US renewable potential being wasted waiting in grid interconnection queues while grid integration challenges are seeing the UK waste enough wind energy each year to power 1 million homes.

The common perception is that this could all be overcome by building bigger grids and more interconnections with renewables. Yet, this overlooks the necessity of a commercially flexible grid that enables a utility company to quickly determine the best times to buy from a producer and understand the amount of power they can load onto the grid at any one point. Together, these factors contribute to maximising distributed renewable energy sources, which are essential for reducing reliance on fossil fuels.

A lack of monitoring capabilities across networks means grids are failing to take advantage of desirable weather conditions or times of day to draw more from existing renewable power sources or safely carry more current. Utilities are also missing opportunities to ‘double up’ by sharing loads between parallel lines or prevent large-scale power loss and theft. Stopping the waste of renewable energy on our grids is increasingly imperative to delivering on the energy transition.

Have you read?
AI and the power sector: Ushering in a new era
How predictive AI is helping smooth the path to net zero

The network blind spots keep clean energy locked out

The current renewable power waste and inefficiencies arise from the nature of our electricity networks. Power grids built for an era of centralised, stable power sources are only designed to collect limited data mostly from transmission networks and have little analytical or predictive capabilities.

Many utilities do not collect real-time data on parameters that directly affect renewable generation and integration from windspeed and line temperature to voltage and frequency. For example, operators cannot predict the periods of most plentiful wind or solar power production without tracking windspeeds and ambient temperatures across their networks.

There are big blind spots in specific parts of the grid, too. Many operators have little to no visibility of the medium and low voltage distribution networks that increasingly draw on distributed power sources from batteries to rooftop solar panels. This prevents utilities from drawing on the full array of available clean power sources during peak periods or identifying spare capacity for clean energy trading.

Network blind spots also cause needless grid congestion by wasting capacity. Many utilities currently rely on crude, overcautious calculations to set safe capacity limits instead of accurately monitoring line temperatures and local weather conditions in real time.

Rigid, restrictive capacity limits on long-range transmission lines reduce the amount of power that can be drawn from distant renewables such as offshore wind, compelling utilities to ‘top up’ from nearby fossil-fueled power plants instead. This needlessly skews the electricity mix towards fossil fuels.

How AI could unblock our grids

Integrating more far-flung, fluctuating renewable power sources in a way that is commercially flexible and with an awareness of how much power can be handled, requires a shift towards sensitive, adaptive grids. Both in Europe and in the US, the rates for raw electricity, purchased from electricity generators such as PV, and wind, change every 15 minutes.

An accurate understanding of the situation in both: grid capabilities and generation projection, and the ability to plan in advance how much energy will be routed along which lines will allow a reduction in electricity prices for the benefit of consumers.

Enter, multi-sensing grid monitoring systems which can now transform even older grids into smart nervous systems detecting over 60 electrical, physical and environmental phenomena, from voltage, frequency, and harmonics to cable ampacity, temperature and windspeed.

This rich reservoir of data is now being combined with the predictive power of Machine Learning (ML) to adapt network capacity and renewable power sources to changes in the weather. The same innovations can also predict and prevent causes of power loss and even fuel smarter designs built to boost renewable integration.

For example, ML algorithms can use historic data on cable temperatures and weather conditions to predict how much current can be safely carried across networks in specific weathers, daytimes and locations months in advance. This enables network operators to safely increase capacity and integrate more renewable energy when temperatures are lower such as in the evening or in locations with cooler conditions such as in the mountains.

Data on fluctuations in supply and demand could also predict when and where loads could be shared between parallel lines to further boost network capacity.

The cognitive power of AI could help unlock more renewable generating capacity too.  Sensor data showing the effect of weather variations on renewable generation including distributed energy sources could predict potential spikes in renewable generating capacity in different conditions and locations.

Operators could use this to forecast the times of day or year when solar or wind are at their most productive in each place so that utilities always avail of the cheapest and cleanest power sources. This could be matched with data on historical drivers of electricity demand to continuously synchronise renewable supply with demand in all weathers, reducing reliance on fossil-fueled flexibility services.

Integrating more renewable energy also demands that we reduce electricity waste such as power loss and theft. New location-based fault detection systems could allow AIs to identify the site and source of power leaks and theft to help protect networks and conserve clean electricity.

Ultimately, this data can improve network designs so that future upgrades or build-outs are based around maximising capacity, conserving power and integrating more renewable energy from the outset. As Machine Learning systems grow smarter, they could suggest the optimal siting of new networks to reduce wire temperatures and boost network capacity or new replacement materials that could conduct more electricity. AIs could predict the optimal network configurations and locations to reduce power loss.

The rethink of grid strategy needed for net zero

The energy transition will not only require bigger and more interconnected grids but smarter and more efficient ones that make better use of existing renewable energy. Grids are being rapidly enlarged and diversified to draw on more renewable power sources but we need a parallel expansion and diversification of very advanced grid analytics.

Especially because nowadays, it has become clear beyond any doubt that software tools not based on numerous and accurate data monitored from the grid will not be able to cope with the challenges. Increasing the contribution of unstable and dispersed renewable generators requires grids that can intelligently scale capacity or switch power sources in response to changing environmental and physical conditions.

Recent innovations in sensors, data analytics and artificial intelligence now create the possibility of creating smart, hyper-efficient networks that can unleash the true potential of renewables and even reduce the need for new grid infrastructure.

About the author

Amir Cohen is the Co-Founder and CEO of Electrical Grid Monitoring (EGM). EGM supplies advanced smart grid monitoring systems to top power grid operators from Israel to Europe.