Solar Energy

Toward new solar cells with active learning

Published

4 years ago

April 25, 2021

sarosh

Toward new solar cells with active learning

How can I prepare myself for something I do not yet know? Scientists from the Fritz Haber Institute in Berlin and from the Technical University of Munich have addressed this almost philosophical question in the context of machine learning. Learning is no more than drawing on prior experience. In order to deal with a new situation, one needs to have dealt with roughly similar situations before.

In machine learning, this correspondingly means that a learning algorithm needs to have been exposed to roughly similar data. But what can we do if there is a nearly infinite amount of possibilities so that it is simply impossible to generate data that covers all situations?

This problem comes up a lot when dealing with an endless number of possible candidate molecules. Organic semiconductors enable important future technologies such as portable solar cells or rollable displays.

For such applications, improved organic molecules – which make up these materials – need to be discovered. Tasks of this nature are increasingly using methods of machine learning, while training on data from computer simulations or experiments.

The number of potentially possible small organic molecules is, however, estimated to be on the order of 1033. This overwhelming number of possibilities makes it practically impossible to generate enough data to reflect such a large material diversity. In addition, many of those molecules are not even suitable for organic semiconductors. One is essentially looking for the proverbial needle in a haystack.

In their work published recently in Nature Communications the team around Prof. Karsten Reuter, Director of the Theory Department at the Fritz-Haber-Institute, addressed this problem using so-called active learning. Instead of learning from existing data, the machine learning algorithm iteratively decides for itself which data it actually needs to learn about the problem.

The scientists first carry out simulations on a few smaller molecules, and obtain data related to the molecules’ electrical conductivity – a measure of their usefulness when looking at possible solar cell materials. Based on this data, the algorithm decides if small modifications to these molecules could already lead to useful properties or whether it is uncertain due to a lack of similar data.

In both cases, it automatically requests new simulations, improves itself through the newly generated data, considers new molecules, and goes on to repeat this procedure.

In their work, the scientists show how new and promising molecules can efficiently be identified this way, while the algorithm continues its exploration into the vast molecular space, even now, at this very moment. Every week new molecules are being proposed that could usher in the next generation of solar cells and the algorithm just keeps getting better and better.

Source link

Solar Energy

New system offers early warning of dust storms to protect solar power output

Published

2 days ago

April 16, 2025

sarosh

New system offers early warning of dust storms to protect solar power output

by Simon Mansfield

Sydney, Australia (SPX) Apr 10, 2025

A new predictive platform called iDust is poised to transform dust storm forecasting and improve solar energy output in dust-prone regions. Developed by researchers at the Chinese Academy of Sciences, iDust offers high-resolution, fast-turnaround dust forecasts that could help mitigate power losses across solar farms, particularly in arid zones.

The tool was created under the leadership of Dr. Chen Xi from the Institute of Atmospheric Physics and detailed in the Journal of Advances in Modeling Earth Systems (JAMES).

“Dust storms not only block sunlight but also accumulate on solar panels, decreasing their power output.” said Chen, outlining the motivation behind the project. With China’s rapid expansion of solar installations in desert areas, the need for precise and timely dust forecasts has become increasingly urgent to avoid operational disruptions and revenue shortfalls.

Traditional systems like those from the European Centre for Medium-Range Weather Forecasts (ECMWF) often lack the spatial resolution and processing speed needed for optimal solar planning. iDust addresses these limitations by embedding dust-related dynamics directly into its forecast engine. This allows the system to generate forecasts with 10-kilometer resolution-a fourfold improvement over previous models-while maintaining near-parity in computational load. Crucially, iDust can deliver 10-day forecasts within six hours of initial observations.

The effectiveness of iDust was put to the test on April 13, 2024, when it successfully tracked a severe dust storm over Bayannur in northern China. Such storms can distort solar energy projections by as much as 25% if unaccounted for, underscoring the value of integrating dust modeling into energy planning.

Designed for practical deployment, iDust aims to assist solar facility operators and grid managers in optimizing power production and reducing losses due to airborne particulates. As China pushes toward its carbon neutrality goals, innovations like iDust will be central to achieving sustainable energy reliability.

Researchers plan to expand the system for global application, allowing other countries with desert-based solar assets to benefit from enhanced dust forecasting.

Research Report:The Efficient Integration of Dust and Numerical Weather Prediction for Renewable Energy Applications

Source link

Solar Energy

Going green with fluoride-enhanced perovskite solar cells

Published

3 days ago

April 15, 2025

sarosh

Going green with fluoride-enhanced perovskite solar cells

by Simon Mansfield

Sydney, Australia (SPX) Apr 15, 2025

A team of scientists from Queensland University of Technology (QUT) has unveiled a sustainable method for fabricating perovskite solar cells (PSCs) by using a fluoride-based additive in a water-only solution. This innovation replaces hazardous solvents typically used in PSC production, achieving a notable power conversion efficiency exceeding 18%.

Perovskite solar cells have emerged as a promising technology for the future of solar energy, thanks to their high efficiency and cost-effectiveness. Yet, their commercial scalability has been hindered by the environmental and health hazards posed by conventional toxic solvents used during manufacturing. While water-based methods offer a more sustainable route, they have so far underperformed in delivering high-efficiency devices.

To overcome this barrier, QUT researchers introduced lead(II) fluoride (PbF2) into the aqueous precursor mix. This additive plays a dual role: it speeds up the formation of the light-absorbing phase and aligns the crystallization process to optimize light conversion. The fluoride ions also passivate surface defects in the perovskite grains, minimizing charge loss and improving conductivity.

“With the PbF2 additive, we achieved a power conversion efficiency of 18.1%, compared to 16.3% in the control device,” said Dr. Minh Tam Hoang, a postdoctoral researcher at QUT and lead author of the study. “Even more exciting is the improved operational and environmental stability, which brings us closer to scalable, green manufacturing of PSCs.”

This advancement signals a meaningful shift in perovskite solar cell development, offering a pathway to produce efficient and durable solar modules through eco-friendly processes. The results demonstrate the value of fluoride-based chemistry in advancing both performance and sustainability in solar technologies.

The findings were published in the journal Materials Futures, underscoring the growing role of green additives in next-generation clean energy solutions.

Research Report:Lead (II) fluoride additive modulating grains growth of water-processed metal halide perovskites for enhanced efficiency in solar cells

Source link

Solar Energy

Launch of AI-powered solar diagnostics platform boosts PV asset performance

Published

3 days ago

April 15, 2025

sarosh

Launch of AI-powered solar diagnostics platform boosts PV asset performance

by Simon Mansfield

Sydney, Australia (SPX) Apr 15, 2025

The Solar Energy Research Institute of Singapore (SERIS) at the National University of Singapore (NUS) has launched a commercial spin-off called the “PV Doctor,” marking a significant leap forward in managing and optimizing solar photovoltaic (PV) system performance. Officially unveiled on April 2, 2025, the platform leverages 15 years of R and D into the behavior of PV systems in diverse climates and aims to restore and maintain peak energy output for solar installations worldwide.

The PV Doctor combines AI-based analytics with routine monitoring and benchmark comparisons to ensure that solar assets operate at maximum efficiency. In addition to diagnostics, the service provides corrective action plans and hands-on rectification, helping system owners recover lost energy output and maximize returns on investment.

“Our mission is to ensure that every PV system under our care performs at its peak potential,” the founders stated. “By integrating deep expertise with real-time diagnostics, we can prevent losses before they escalate.”

Many PV systems are sold under the misleading premise of being maintenance-free, despite the reality that even minor oversight can result in substantial inefficiencies. Global preventable losses from underperforming systems are estimated at $10 billion annually. PV Doctor targets this gap by offering root-cause analysis and active management for both healthy and ailing systems. Its Smart O&M algorithm tracks performance in real-time, detecting anomalies before they degrade output.

Initially trialed by SERIS across Asia, the Smart O&M services quickly proved their value. In just under a year, PV Doctor systems reached over 200 MWp of assets under management, covering 400 sites in 10 countries. In Singapore, more than 3% of all PV installations are already being managed by the platform.

PV Doctor’s capabilities are structured around six core services:

1. Smart O&M – This foundational offering provides real-time performance monitoring, automatic issue detection, and root-cause analysis. The system integrates seamlessly with inverter portals, using a combination of sensor inputs, satellite data, and machine learning to pinpoint losses from pollution, shading, grid disruptions, and component failures.

2. Preventive O&M – For owners seeking a passive role, this service delivers scheduled maintenance, inspections, and early fault resolution, ensuring systems remain operational without owner involvement.

3. Rectification and Special Investigations – PV Doctor tackles complex issues such as potential-induced degradation or mechanical defects, especially common in low-tilt systems near the equator. Thorough diagnostics precede tailored interventions to restore full performance.

4. Repowering – Older or obsolete systems can be upgraded with the latest high-efficiency modules and inverters. Repowering revitalizes aging assets, increases output, and prolongs operational lifespan.

5. Audits and Performance Assessments – Independent third-party assessments support transactions and compliance needs. PV Doctor uses thermal imaging, satellite-derived irradiance, and electrical testing to deliver objective performance evaluations.

6. Technical Support – Beyond system operations, the platform assists stakeholders across the solar value chain with project planning, risk analysis, component selection, and due diligence for acquisitions.

PV Doctor positions itself as an essential partner for solar developers, asset managers, EPC firms, and investors, offering scalable solutions from residential systems to large-scale solar farms.