AI-based IoT-enabled PV module-level portfolio optimal predictive maintenance and PV-enhanced industrial plant optimal operation
Improvement in operational efficiency of PV assets through the combined effect of optimised maintenance and increased assets efficiency. Increased self-consumption from local RES and electricity cost reduction.
What is the challenge that is being addressed?
With actual and prospected O&M business constantly growing BFP has started recently to undergo through a corporate-level innovation program aimed to leverage on AI-based predictive and prescriptive analytics with a view to move from the actual pre-scheduled, reactive and RES-plant individual-level towards IoΤ and data-driven predictive maintenance activities with a specific focus on PV plants O&M, which covers the 2/3 of the company O&M activity. The aggregated SCADA information from the central plant level does not give the necessary information at the level of the individual module with a view to understand the real situation of the PV plant and from there to carry out an anticipated prediction of abnormal operational conditions, and accordingly schedule a cost-effective predictive maintenance plan.
What is the AI solution the project plans to implement?
The BFP pilot will be deployed by BFP O&M for RES generation plants in Puglia region (Italy) and will consist of: (a) an industrial-scale medium-size Poly-crystalline Silicon PV farm (designed, deployed and operated by BFP) with module-level smart inverters within an operational malt production plant, accounting 498 kWp (1780x280W) of Peak Power, (b) two utility-scale PV plants with nominal power around 0,9 MWp, (c) a data hub which includes BFP operated PV-plant level SCADA electrical measurement data over 6 PVs plants composed by Suniva 240W PV modules and a Solar 280W modules and a SMA centralised PV-plant level inverter. BFP will demonstrate and validate AI-driven analytics tools to the PV module-level with a view to introduce innovative services devoted to: Move forward from reactive maintenance based on centralised PV-farm level SCADA-based alarm notification to improved predictive maintenance, based on anticipated prediction and detection of malfunctioning at module decentralised level by leveraging on an increased availability of data (also shared by other partners) via the I-NERGY scalable data handling infrastructure; Support aggregated and optimised O&M management of PVs portfolios, through data-driven effective clustering of PVs at design time, according to a variety of different criteria (geographical location, sun irradiance level, size, types of technologies), by leveraging on Digital Twin models developed in the project; Industrial plant optimal operation and electricity bill reduction by prioritising local PV-based consumption of locally generated renewable electricity.
Major expected outcomes for BFP will be: (a) 10-15% improvement in operational efficiency of PV assets through the combined effect of optimised maintenance and increased assets efficiency (b) Increased self-consumption from local RES and electricity cost reduction by 25-30%.
Who will help implement this solution?
This pilot is implemented within the framework of the “I-NΕRGΥ: Artificial Intelligence for Next Generation Energy” Project. The I-NERGY Project has received funding from the European Union's Horizon 2020 Research and Innovation programme under grant agreement No. 101016508.
The responsible partner for this Use Case is BFP (https://bfpgroup.net/).