Alex Moltzau 莫战

May 9, 2020

2 min read
Photo by — @draufsicht

Solar Inverters and AI

How Huawei plans to use artificial intelligence to improve solar inverters

Huawei has a roadmap that includes improvement of AI capabilities for operation and maintenance (O&M) services.

Within this framework grid management is important.

Solar Panels (PV) plant design can really make a difference if incremental improvement is made.

Huawei has expressed that fault processing tools integrated with AI can be rolled out.

They use these algorithms to prevent fires.

Arc-fault circuit interrupters (AFCIs) can already help detect these fires, but artificial intelligence can help predict with risk assessment as well as being responsive (taking different actions to adapt).

They have a database of 1 million arc features that can be used to build models. According to an article by Emiliano Bellini the company stated the following:

Two projects owned by China General Nuclear Power Group Huanghen Hydropower have been pilots. They used string inverters equipped with neural network-based AI training and modeling.

In this way power generation can be increased at least that is what Huawei AI roadmap claimed with an energy yield rising an average 1.31% over 183 days with an added energy yield improved 0.5–1%.

Data will be collected real-time with real-time control.

They aim to make AI models for optimal power generation in real time, according to the inverter maker. In this regard they are moving towards AI training and inference platform is aimed at further optimizing AI algorithm models without the need to alter existing devices.

This is #500daysofAI and you are reading article 341. I am writing one new article about or related to artificial intelligence every day for 500 days. My focus for day 300–400 is about AI, hardware and the climate crisis.