In 2019, Huawei launched its Ascend AI processors, the all-scenario AI computing framework MindSpore, the Atlas full-series products, and Ascend-based cloud services. “Huawei completed the construction of full-stack, all-scenario AI solutions, which have been widely used across various industries,” says Tony Xu, president of Huawei’s Ascend Computing business unit.
With the development of digital information technologies, Huawei’s Smart PV business unit started with a digital + PV era, moved to the internet + PV era, and now the conglomerate says it is entering the AI + PV era.
In 2014, Huawei launched its Smart PV solution with string solar inverters functioning as the core. “This solution has enabled inverters to serve as PV array sensors that support precise information collection for each PV string, essentially achieving perception intelligence,” says Chen Guoguang, president of Huawei’s Smart PV business unit. From 2015 to 2018, Huawei further integrated digital technologies, with typical applications including wireless private network technologies, MBUS technologies, Smart I-V Curve Diagnosis, and an intelligent O&M cloud center.
In 2019, Huawei released its first Smart PV solution, which integrates AI technologies with its Smart I-V Curve diagnosis solution. In 2020, the company says it is continuing to deepen the integration between smart PV and full-stack, all-scenario AI solutions. “We are currently building a core architecture for device-edge-cloud synergy,” says Chen. “This will maximize the value of each PV plant and accelerate the industry’s intelligentization upgrade.”
At the device-level, Huawei says its solar inverters will be further upgraded at some point to serve as smart PV controllers. “This will enable the implementation of high-precision real-time data collection, real-time control of string-level energy yield optimization, real-time DC arc detection, and real-time response to grid-tied control, with real-time inference, execution, and self-closed-loop control capabilities,” says Chen.
When referencing edge, Chen says that AI inference modules are embedded in the PV array controllers for an intelligent upgrade. The modules will collect device data and infer AI models for optimal power generation in real-time and enable grid-tied control of PV arrays.
The cloud refers to Huawei’s the deployment of the AI inference AI inference platform on a management system that provides continuous training and optimization of the AI algorithm models, without the need for altering existing devices. “As a result, the system energy yield and potential fault diagnosis accuracy are continuously increasing,” says Chen. “The inference models of devices on the device and edge sides can be promptly updated in batches, achieving efficient collaboration.”
Huawei says that its full-stack, all-scenario AI solutions have already been widely adopted by the electric power, manufacturing, and healthcare industries. “In the power sector, for instance, China Southern Power Grid utilizes the Atlas 200-based intelligent O&M and inspection system,” says Chen. And with full-stack, all-scenario AI now being applied for the Smart PV business unit – the company says its next era will offer a variety of new solutions.
To build a closed-loop, collaborative, and convergent system, Huawei has developed a Smart DC System (SDS). The system is designed to integrate the previously independent PV modules, trackers, and solar inverters into a closed-loop synergy among bifacial PV modules, trackers, and smart PV controllers with multiple MPPTs.
A smart PV controller will work as an artificial brain that self-learns and optimizes tracker optimization algorithms. “AI training and modeling will adjust the trackers to the optimal tilt angle to realize the full potential of each PV string in a solar plant,” says Chen. For example, an optimal front-to-rear tracker linkage is provided based on the shadows, scattering ratios, and cloud movement, implementing optimization of the tracker angle in real time.
“Over the last year, Huawei has tested a large number of PV plants, with tests in Huixi and Anhui, indicating a real energy yield increase by 1.31% over a period of 183 days,” says Chen. “Both China General Nuclear Power Group and Huanghe Hydropower have increased their energy yields by 0.5% to 1%.”
AI Boost AFCI
Solar PV fire incidents are typically caused by DC arcs through poor contact, insecure connection of solar PV connectors, and cable aging and damage. And while historically manual inspection and maintenance would be required to locate problems, AI is stepping up to the challenge. “Nearly 100% of arcs can be identified using AI algorithms that ensure system safety by enabling quick-break protection,” says Chen.
Huawei says it has made the industry’s first attempt to integrate AI algorithms into arc-fault circuit interrupters (AFCIs), which it believes will become the global industry standard. By providing more accurate arc detection and faster fault rectification, the company’s AI Boost AFCI feature is set to enhance safety for PV systems.
Remote scanning of all PV strings is now happening in a one-click mode for the solar industry. Huawei says that’s its Smart I-V Curve Diagnosis can now scan a 100 MW PV plant can be scanned within just 15 minutes – but that remote scanning is just the beginning.
Driving down the cost of operations and maintenance from manual labor will be further supported by AI technologies. “Drone inspections and robot-based automatic O&M will replace massive repetitive work,” says Chen.
Drones equipped with a high-definition (HD) or infrared camera can negate the need for manual inspection and complete real-time analysis and judgment.
With a higher penetration of intermittent renewables being tied into power transmission infrastructure, the grid faces stability challenges. “Renewable energy with a strong high-voltage ridethrough (HVRT) capability is imperative to maintaining the safety and stability of power grids,” says Chen.
Huawei believes that its self-learning algorithms will be able to build considerably stronger control capabilities from PV plants to support the grid. By proactively identifying the electrical features of a given PV plant, AI will automatically adjust the grid-tied algorithm to match the power grid.
In the future, the grid-tied control capability of solar PV inverters will support connections to weaker power grids, so that the solar power system can still run stably without disconnecting from the power grid.
Using digitalization, Huawei says that independent devices of solar PV plants will start to work in a much more collaborative fashion as systems moving into the future. With “three-level collaborations” – the solar inverter, solar array, and solar PV plant – all elements will be optimized to build gains and maximize efficiencies more cohesively.
“At the device level, improvements have been made not only in the efficiencies and power densities of solar inverters, but also in maintenance-free designs,” explains Chen, adding that grid-edge support and new AI perception and inference capabilities will continue to rapidly expand in the years ahead.
At the array level, many devices are becoming much more interconnected and optimized in a collaborative manner. An intelligent DC closed-loop system has been formed, consisting of bifacial solar PV modules, solar trackers, and solar inverters. “The AI self-learning and big data feature mining technologies are used to dynamically adjust the tracker angle online to the optimal state, fully achieving the potential of each PV string,” says Chen.
“And finally, at the plant level, driven by the smart PV array and edge computing, PV plants can proactively receive power grid requirements, automatically adjust the operating status, and implement real-time online collaboration,” he adds. “And this is where real evolution of the PV ecosystem arrives with AI.”
This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: firstname.lastname@example.org.