• Energy Research
• 2025-2025close
• ES close
• Energies close

In this paper, a new methodology for fault detection and diagnosis in photovoltaic systems is proposed. This method employs a novel Euclidean distance-based tree algorithm to classify various considered faults. Unlike the decision tree, which requires the use of the Gini index to split the data, this algorithm mainly relies on computing distances between an arbitrary point in the space and the entire dataset. Then, the minimum and the maximum distances of each class are extracted and ordered in ascending order. The proposed methodology requires four attributes: Solar irradiance, temperature, and the coordinates of the maximum power point (Impp, Vmpp). The developed procedure for fault detection and diagnosis is implemented and applied to classify a dataset comprising seven distinct classes: normal operation, string disconnection, short circuit of three modules, short circuit of ten modules, and three cases of string disconnection, with 25%, 50%, and 75% of partial shading. The obtained results demonstrate the high efficiency and effectiveness of the proposed methodology, with a classification accuracy reaching 97.33%. A comparison study between the developed fault detection and diagnosis methodology and Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbors algorithms is conducted. The proposed procedure shows high performance against the other algorithms in terms of accuracy, precision, recall, and F1-score.

In this paper, a new methodology for fault detection and diagnosis in photovoltaic systems is proposed. This method employs a novel Euclidean distance-based tree algorithm to classify various considered faults. Unlike the decision tree, which requires the use of the Gini index to split the data, this algorithm mainly relies on computing distances between an arbitrary point in the space and the entire dataset. Then, the minimum and the maximum distances of each class are extracted and ordered in ascending order. The proposed methodology requires four attributes: Solar irradiance, temperature, and the coordinates of the maximum power point (Impp, Vmpp). The developed procedure for fault detection and diagnosis is implemented and applied to classify a dataset comprising seven distinct classes: normal operation, string disconnection, short circuit of three modules, short circuit of ten modules, and three cases of string disconnection, with 25%, 50%, and 75% of partial shading. The obtained results demonstrate the high efficiency and effectiveness of the proposed methodology, with a classification accuracy reaching 97.33%. A comparison study between the developed fault detection and diagnosis methodology and Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbors algorithms is conducted. The proposed procedure shows high performance against the other algorithms in terms of accuracy, precision, recall, and F1-score.

The transformation of energy markets is at a crossroads in the search for how they must evolve to become ecologically friendly systems and meet the growing energy demand. Currently, methodologies based on bibliographic data analysis are supported by information and communication technologies and have become necessary. More sophisticated processes are being used in energy systems, including new digitalization models, particularly driven by artificial intelligence (AI) technology. In the present bibliographic review, 342 documents indexed in Scopus have been identified that promote synergies between AI and the energy transition (ET), considering a time range from 1990 to 2024. The analysis methodology includes an evaluation of keywords related to the areas of AI and ET. The analyses extend to a review by authorship, co-authorship, and areas of AI’s influence in energy system subareas. The integration of energy resources, including supply and demand, in which renewable energy sources play a leading role at the end-customer level, now conceived as both producer and consumer, is intensively studied. The results identified that AI has experienced notable growth in the last five years and will undoubtedly play a leading role in the future in achieving decarbonization goals. Among the applications that it will enable will be the design of new energy markets up to the execution and start-up of new power plants with energy control and optimization. This study aims to present a baseline that allows researchers, legislators, and government decision-makers to compare their benefits, ambitions, strategies, and novel applications for formulating AI policies in the energy field. The developments and scope of AI in the energy sector were explored in relation to the AI domain in parts of the energy supply chain. While these processes involve complex data analysis, AI techniques provide powerful solutions for designing and managing energy markets with high renewable energy penetration. This integration of AI with energy systems represents a fundamental shift in market design, enabling more efficient and sustainable energy transitions. Future lines of research could focus on energy demand forecasting, dynamic adjustments in energy distribution between different generation sources, energy storage, and usage optimization.

The transformation of energy markets is at a crossroads in the search for how they must evolve to become ecologically friendly systems and meet the growing energy demand. Currently, methodologies based on bibliographic data analysis are supported by information and communication technologies and have become necessary. More sophisticated processes are being used in energy systems, including new digitalization models, particularly driven by artificial intelligence (AI) technology. In the present bibliographic review, 342 documents indexed in Scopus have been identified that promote synergies between AI and the energy transition (ET), considering a time range from 1990 to 2024. The analysis methodology includes an evaluation of keywords related to the areas of AI and ET. The analyses extend to a review by authorship, co-authorship, and areas of AI’s influence in energy system subareas. The integration of energy resources, including supply and demand, in which renewable energy sources play a leading role at the end-customer level, now conceived as both producer and consumer, is intensively studied. The results identified that AI has experienced notable growth in the last five years and will undoubtedly play a leading role in the future in achieving decarbonization goals. Among the applications that it will enable will be the design of new energy markets up to the execution and start-up of new power plants with energy control and optimization. This study aims to present a baseline that allows researchers, legislators, and government decision-makers to compare their benefits, ambitions, strategies, and novel applications for formulating AI policies in the energy field. The developments and scope of AI in the energy sector were explored in relation to the AI domain in parts of the energy supply chain. While these processes involve complex data analysis, AI techniques provide powerful solutions for designing and managing energy markets with high renewable energy penetration. This integration of AI with energy systems represents a fundamental shift in market design, enabling more efficient and sustainable energy transitions. Future lines of research could focus on energy demand forecasting, dynamic adjustments in energy distribution between different generation sources, energy storage, and usage optimization.

Under the Positive Energy Districts framework, cities authorities must be informed of the energy demand of districts to design tailor-made policies and strategies to promote the deployment of energy efficiency, sharing and transition actions. However, the diverse data sources and long procedures to collect data because of privacy permissions may result in a slow-down of the development of these roadmaps. To overcome these challenges, this paper is the outcome of the methodology developed under the UP2030 Project designed to estimate the energy demand and energy profile consumptions within urban areas to contribute to the stakeholders involved in decision making processes to inform them about the savings potential related with the use of energy in geographically delimitated areas. The methodology was validated in CIRCE’s headquarters, where the yearly energy estimation consumption is about 98% of the real energy consumed. The main finding of this study is obtaining a model that can estimate the energy usage for occupants’ comfort with minimal data required from the citizens’ side, which will allow stakeholders to consider global energy estimations at the district level in a fast and reliable way to design strategies in a timely manner as required by the energy transition and efficiency standards proposed by the European Union.

Under the Positive Energy Districts framework, cities authorities must be informed of the energy demand of districts to design tailor-made policies and strategies to promote the deployment of energy efficiency, sharing and transition actions. However, the diverse data sources and long procedures to collect data because of privacy permissions may result in a slow-down of the development of these roadmaps. To overcome these challenges, this paper is the outcome of the methodology developed under the UP2030 Project designed to estimate the energy demand and energy profile consumptions within urban areas to contribute to the stakeholders involved in decision making processes to inform them about the savings potential related with the use of energy in geographically delimitated areas. The methodology was validated in CIRCE’s headquarters, where the yearly energy estimation consumption is about 98% of the real energy consumed. The main finding of this study is obtaining a model that can estimate the energy usage for occupants’ comfort with minimal data required from the citizens’ side, which will allow stakeholders to consider global energy estimations at the district level in a fast and reliable way to design strategies in a timely manner as required by the energy transition and efficiency standards proposed by the European Union.

The efficient sizing and characterization of the load curves of distribution transformers are crucial challenges for electric utilities, especially given the increasing variability of demand, driven by emerging loads such as electric vehicles. This study applies clustering techniques and predictive models to analyze and predict the behavior of transformer demand, optimize utilization factors, and improve infrastructure planning. Three clustering algorithms were evaluated, K-shape, DBSCAN, and DTW with K-means, to determine which one best characterizes the load curves of transformers. The results show that DTW with K-means provides the best segmentation, with a cross-correlation similarity of 0.9552 and a temporal consistency index of 0.9642. For predictive modeling, supervised algorithms were tested, where Random Forest achieved the highest accuracy in predicting the corresponding load curve type for each transformer (0.78), and the SVR model provided the best performance in predicting the maximum load, explaining 90% of the load variability (R2 = 0.90). The models were applied to 16,696 transformers in the Ecuadorian electrical sector, validating the load prediction with an accuracy of 98.55%. Additionally, the optimized assignment of the transformers’ nominal power reduced installed capacity by 39.27%, increasing the transformers’ utilization factor from 31.79% to 52.35%. These findings highlight the value of data-driven approaches for optimizing electrical distribution systems.

The efficient sizing and characterization of the load curves of distribution transformers are crucial challenges for electric utilities, especially given the increasing variability of demand, driven by emerging loads such as electric vehicles. This study applies clustering techniques and predictive models to analyze and predict the behavior of transformer demand, optimize utilization factors, and improve infrastructure planning. Three clustering algorithms were evaluated, K-shape, DBSCAN, and DTW with K-means, to determine which one best characterizes the load curves of transformers. The results show that DTW with K-means provides the best segmentation, with a cross-correlation similarity of 0.9552 and a temporal consistency index of 0.9642. For predictive modeling, supervised algorithms were tested, where Random Forest achieved the highest accuracy in predicting the corresponding load curve type for each transformer (0.78), and the SVR model provided the best performance in predicting the maximum load, explaining 90% of the load variability (R2 = 0.90). The models were applied to 16,696 transformers in the Ecuadorian electrical sector, validating the load prediction with an accuracy of 98.55%. Additionally, the optimized assignment of the transformers’ nominal power reduced installed capacity by 39.27%, increasing the transformers’ utilization factor from 31.79% to 52.35%. These findings highlight the value of data-driven approaches for optimizing electrical distribution systems.