Predict solar irradiance, wind speed with 98% accuracy

Download Research Paper

Solar industry faces some pertinent challenges today. Unpredictable and fluctuating future solar irradiance and wind speed are one of them. The present forecasting services are unable to provide accurate predictions. Thus, in the absence of standard forecasting projections, the renewable energy developers are not able to plan their future production and maintenance in a better way. Furthermore, it adversely impacts the investability and credibility of the existing and upcoming renewable energy projects, reducing their overall share in the energy market. As a result, the renewable utilities have to bear the burden of hefty penalties for not being able to meet their energy commitments.

In our technical research paper, we have attempted to work on a solution to the above problem by considering factors like, the inter-day and intra-day variability of the renewable resources, human or anthropogenic and local environmental factors, Global climatic events, Climate Change and the impact of different factors and the training models (statistical, machine learning, and deep learning). During our research and testing we blended climate science, satellite imagery/data, global meteorological databases, AI, ML, and Deep-Learning to take the predictions to the next level of forecasting accuracy band. 

Finally after careful validation, we developed an AI-based framework to automatically select the best models, factors, and their combinations to optimize the overall accuracy of the predictions. The results were equal to more than 98% accurate. 

To read more about our AI-based framework click on the button below and download our Technical Research paper on ‘Resource Forecasting’. 

Download Research Paper

PV Panel analytics

Do you validate your Solar PV Module's Thermal Coefficient?

Download Research Paper

PV Panel analytics

A solar PV system is based on a simple mechanism that converts sunlight into energy. However, the process is not as simple as it seems. Some of the incident energy falling on a solar panel is reflected and some other is dissipated as heat, causing the PV module to operate at a higher temperature rather than at ambient temperature. This rise in temperature of the solar PV modules can affect the energy production and overall performance of your solar plant.

The aim of our research was to study the sensitivity of the PV Modules towards rising temperature that negatively impacts the electrical conversion efficiency of a PV module and thus overall performance of the plant.

During our research to determine a PV module’s sensitivity towards the rising PV module temperature, we compared the thermal coefficients specified by the PV module manufacturer in the specification sheet with the thermal coefficients calculated by SmartHelio’s team.

Our team through rigorous research and validation developed a PV Panel Analytics Tool that provides access to real-time sophisticated analytics such as thermal coefficients and PV module degradation to its subscribers, by accessing the real-time raw data with a precision of seconds collected by our IoT devices. Our tool also helps your procurement team to find the most profitable PV module technology for your plant by comparing different technologies for multiple locations.

Read more about our research, Click on the download button below to download our research paper ‘Validating Thermal Coefficients in Outdoor Conditions’

Download Research Paper

Ground-breaking Research on Panel-level faults detection

Use of Edge Computing and AI on IoT hardware to identify solar Panel-level faults

Download full document

Ground-breaking Research on Panel-level faults detection

Module-level faults can have serious affect on the performance and reliability of any solar PV plant. These faults, if not detected timely, can pose safety hazards like fire accidents on site and eventually lead to significant asset damage and/or under-performance. A better fault detection technology through the use of Edge Computing IoT hardware and machine learning frameworks is the need of the hour. 

A Solar PV system could encounter several faults at module-level. These faults include electrical faults like line to line, line to ground, open circuit or non-electrical faults like glass breakage, bird pooping etc.. In our research we have identified and presented how better and real-time fault detection is possible using cost-effective Edge devices and Machine Learning frameworks. 

The purpose of the research was to identify and develop module-level fault detection frameworks with classification techniques to build low-cost edge-devices (IoT Sensors) that could be deployed at large scale in low-power-output PV arrays. 

Our research classifies the impact of non-electrical faults (glass breakage, delamination, bird poop etc.) on the current and voltage patterns of the panels. This has helped us to detect these non-electrical faults accurately based on their signature patterns and impact on electrical and thermal parameters of PV modules.  

Through the research we were able to classify more than six types of non-electrical module-level faults in a solar PV system with 93% accuracy using the low power edge devices. The research paper gives a clear idea with concrete results on the effectiveness of Machine Learning frameworks and cost-effective Edge Computing for sustainable, profitable and reliable solar PV systems. 

Click on the download button below to download our IoT-based research paper.

Download full document