CircuitSee provides continuous fault-level monitoring based on machine-learning technology, allowing us to install less equipment on our sites. It could save customers more than £1 million.
What is the project about?
If too much power travels through our substation equipment, it can reach a ‘fault level’ and stop working efficiently. To ensure this doesn’t happen, we routinely monitor our substations with special software to ensure they don’t exceed 95% of the equipment’s rating limits.
At present we use of a software tool called PowerFactory to calculate those fault levels. The number produced by the software helps us ‘check in’ on substations and take corrective action if we see that fault levels are at 95% or more.
We install live monitoring through PowerFactory so that we know if fault levels are between 95% and 100% of our switchgear rating and we will take action to ensure reliability and safety if levels rise too high.
Installing fault level monitoring, however, can be costly and time-intensive. CircuitSee is testing a new approach to improve accuracy and efficiency – and reduce the cost – of our current fault level monitoring methods.
How we’re doing it
The new method proposed in the project is to implement continuous on-line fault level monitoring with three key components.
Active fault level measurement performed on the LV network of 11KV substations
Passive fault level measurement performed on feeders of primary substations
Correlation and verification techniques are implemented to provide fault level monitoring across an entire radial network.
The new software solution provider is Reactive Technologies (RTL). The solution builds up a picture of the fault level across an entire radial network beneath our substations using machine learning techniques. Due to the active measurement approach, the high frequency of measurements allows for high accuracy and for fault levels to be correlated between different substations. This means we can deploy the software more frequently. The technology has been developed in a laboratory setting and is still subject to a patent application. The next stage of development is to trial for real on our network.
What makes it innovative
The approach used in this project is the first of its kind to correlate passive measurements with active measurements. Generally speaking, passive measurements take more time than active monitoring. This time depends on the number of switching activities in the network. Active measurements overcome this but are more expensive and bulky. By using machine learning algorithms to correlate the two methods, we aim to have the best of both worlds.
What we’re learning
The approach used in this project is a first for any DNO in the UK. As part of the project, we will first validate the theoretical standing of the solution against Powerfactory. In phase two, we will implement the solution in a trial to learn more about the costs of implementation and the accuracy of results in a real-world application.
We use cookies to give you the best possible experience when using our website. Many of these cookies are essential to the efficient operation of this site.
