Article
Green & Sustainable Science & Technology
Christina Brester, Viivi Kallio-Myers, Anders Lindfors, Mikko Kolehmainen, Harri Niska
Summary: The effective integration of solar PV output into overall energy consumption planning and control depends on accurate PV forecasting. However, the availability of numerical weather prediction (NWP) data poses a challenge in training data-driven PV forecasting models. In this study, an artificial neural network (ANN) is trained on weather observations and tested on NWP data, showing better performance than a physical model.
Article
Thermodynamics
Abdelhak Keddouda, Razika Ihaddadene, Ali Boukhari, Abdelmalek Atia, Muesluem Arici, Nacer Lebbihiat, Nabila Ihaddadene
Summary: This study proposes artificial neural network (ANN) and regression models for predicting the power output of photovoltaic (PV) modules, considering the effects of climatic conditions and operating temperature. The models were trained using experimental data and selected attributes such as solar irradiation, temperature, wind speed, and humidity. The ANN model showed higher accuracy compared to linear regression models, while the Rational-PowerLaw (RPL) and Power-Law (PL) models captured the nonlinearity of the system and achieved excellent precision. The proposed models outperformed others in the literature, demonstrating superior performance and accuracy.
ENERGY CONVERSION AND MANAGEMENT
(2023)
Article
Chemistry, Physical
Feng Zhang, Mingying Wu, Xinting Hou, Cheng Han, Xinhe Wang, Zhongbing Liu
Summary: This study used the quasiMonte Carlo method to analyze the influence of parameter uncertainty on the output power performance of photovoltaic cells. Results showed that factors such as current temperature coefficient, series resistance and parallel resistance play significant roles. In a normal working environment, lower surface temperature contributes to higher output power and fill factor.
JOURNAL OF POWER SOURCES
(2021)
Article
Energy & Fuels
Junxiong Ge, Guowei Cai, Mao Yang, Liu Jiang, Haimin Hong, Jinyu Zhao
Summary: In this paper, a SSA-ELM model based on weather type division is proposed for photovoltaic power day ahead prediction, taking into account the high frequency fluctuations in the solar panel power generation sequence of photovoltaic users. By using the power sequence convergence effect, cluster prediction is made on all photovoltaic panels to reduce the randomness of distributed photovoltaic, and the accuracy is further improved by dividing weather types. The proposed method is validated using historical data of distributed PV users in a region of Gansu province, showing lower prediction error compared to a comparison model, with a minimum root mean square error of 0.02 in bad weather and an average annual accuracy rate of 93.2%, proving its applicability in different output types.
FRONTIERS IN ENERGY RESEARCH
(2023)
Article
Thermodynamics
Xiao-Jian Dong, Jia-Ni Shen, Zi-Feng Ma, Yi-Jun He
Summary: Accurate prediction of cell temperature and output power is crucial for the optimal design and operation of photovoltaic systems. This study proposes a hybrid modeling approach based on a universal radial basis function neural network to model the cell temperature and circuit parameters. The effectiveness of the proposed approach is validated using experimental data from commercial and laboratory PV plants, indicating its potential for accurate output power prediction across different PV types and weather conditions.
Article
Energy & Fuels
Ellen David Chepp, Arno Krenzinger
Summary: The study focuses on the impact of shading on PV systems caused by dirt, dust, and surrounding elements. A methodology for shading prediction and losses assessment was proposed, demonstrating the feasibility for evaluating shading impact despite limitations for large systems.
Article
Thermodynamics
Liyao Xie, Hongmin Li, Yan Zhang, Xu Liu, Yulong Zhao
Summary: This study improves the internal flow channel structure of PV panel cooling systems using topology optimization techniques, resulting in better cooling performance and increased power output. The results show that the topology optimized flow channel configuration is more effective in reducing solar cell temperature and increasing net power output compared to the traditional straight channel configuration.
CASE STUDIES IN THERMAL ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Reem Shadid, Yara Khawaja, Abdullah Bani-Abdullah, Maryam Akho-Zahieh, Adib Allahham
Summary: This study experimentally analyzed the effects of dust and weather on the photovoltaic power output of different types and orientations of solar module systems. The results showed that both dust accumulation and wet conditions led to a decrease in PV power production.
Article
Thermodynamics
Lingwei Zheng, Ran Su, Xinyu Sun, Siqi Guo
Summary: This paper proposes a framework for reverse determination of weather types from historical PV output data, using symbol-sequence histograms to describe PV output volatility and partitionally clustering and proposing a classification rule for weather types. A prediction method combining phase-space reconstruction with an extremely learning machine based single-layer forward net is developed to predict the symbol-sequence histograms. Experimental results show that, compared with weather information from a weather-service supplier, the PV-output prediction errors are significantly reduced by 15.55% (MAPE) and 12.69% (rRMSE).
Article
Energy & Fuels
Yutong Tan, Jinqing Peng, Yimo Luo, Zhengyi Luo, Charlie Curcija, Yueping Fang
Summary: A four-layer CdTe-based VPV glazing was developed in this study, and a numerical heat transfer model was established and validated for analyzing the energy and power generation performance in different climate zones in China. The energy reduction achieved with VPV glazing in air conditioning seasons varies across cities, but is higher compared to normal double glazing.
Article
Engineering, Electrical & Electronic
Sahbasadat Rajamand, Miadreza Shafie-khah, Joao P. S. Catala
Summary: This paper focuses on improving the performance and reducing the total cost of microgrids by utilizing energy storage systems and photovoltaic power prediction. The use of quantile nearest neighbour forecasting effectively overcomes PV uncertainty, while artificial neural networks combined with multi-layer perceptron and genetic algorithm optimize the size and location of ESSs in the system.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Engineering, Mechanical
Zaid Odibat
Summary: The study introduces remarks on generalized fractional integral and differential operators, and proposes a predictor-corrector algorithm for numerical simulation of initial value problems involving generalized Caputo-type fractional derivatives. The numerical solutions demonstrate the applicability and efficiency of the algorithm.
NONLINEAR DYNAMICS
(2021)
Article
Green & Sustainable Science & Technology
David Markovics, Martin Janos Mayer
Summary: This study compares 24 machine learning models for deterministic day-ahead power forecasting and finds that kernel ridge regression and multilayer perceptron are the most accurate models. Supplementary inputs like Sun position angles and irradiance values can significantly reduce the prediction error. Hyperparameter tuning is essential for optimizing the models' performance.
RENEWABLE & SUSTAINABLE ENERGY REVIEWS
(2022)
Article
Energy & Fuels
Shuai Hu, Yue Xiang, Hongcai Zhang, Shanyi Xie, Jianhua Li, Chenghong Gu, Wei Sun, Junyong Liu
Summary: Wind power generation is rapidly growing worldwide, but its stochastic nature presents challenges. This study proposes a hybrid short-term wind power forecasting method that integrates corrected numerical weather prediction and spatial correlation, improving forecasting accuracy.
Article
Multidisciplinary Sciences
M. G. Schultz, C. Betancourt, B. Gong, F. Kleinert, M. Langguth, L. H. Leufen, A. Mozaffari, S. Stadtler
Summary: The recent hype around artificial intelligence has renewed interest in applying successful deep learning methods in the field of meteorology. Evidence suggests that better weather forecasts can be achieved with the introduction of big data mining and neural networks. However, fundamental breakthroughs are needed before numerical weather models can be completely replaced by DL approaches.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2021)
Article
Engineering, Multidisciplinary
Mario Vasak, Goran Kujundzic
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS
(2018)
Article
Engineering, Civil
Hrvoje Novak, Vinko Lesic, Mario Vasak
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2019)
Article
Automation & Control Systems
Anita Martincevic, Mario Vasak, Vinko Lesic
CONTROL ENGINEERING PRACTICE
(2019)
Article
Automation & Control Systems
Mateja Car, Vinko Lesic, Mario Vasak
Summary: The article focuses on the mathematical modeling and control structure design of a grid-connected back-to-back voltage source inverter with an LC filter for current harmonics reduction. A cascaded three-loop control structure is designed to control the converter current, grid current, and dc link voltage. The proposed control structure shows robust performance for various parameter changes and grid impedance variations, as validated by simulations and experiments on a 7.5 kW converter.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Energy & Fuels
Mario Vasak, Anita Banjac, Nikola Hure, Hrvoje Novak, Danko Marusic, Vinko Lesic
Summary: The paper proposes a modular building energy management strategy based on a three-level hierarchical model predictive control, where building zones, central medium conditioning, and microgrid subsystems are controlled independently and then integrated for a holistic energy management strategy. Detailed simulations demonstrate significant cost reduction in building operation for typical summer days, showcasing the effectiveness of the proposed strategy.
IEEE TRANSACTIONS ON ENERGY CONVERSION
(2021)
Article
Engineering, Civil
Hrvoje Novak, Vinko Lesic, Mario Vasak
Summary: The paper presents a control system for energy-efficient train operation that includes a detailed train motion model and train traction system energy efficiency. By constructing a piecewise affine train model and solving a quadratic optimization problem through dynamic programming, the system can achieve significant energy consumption reductions. The developed control system is evaluated on a real case study scenario and shows promising results in energy-efficient train control.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Energy & Fuels
Mario Vasak, Anita Banjac, Nikola Hure, Hrvoje Novak, Marko Kovacevic
Summary: This paper introduces a strategy for modular building energy management based on a three-level hierarchical model predictive control. It optimizes the overall building operation and provides financially viable flexibility. The strategy is verified on three pilot buildings, showing its broad applicability. The analysis on characteristic days allows for an accurate assessment of the benefits of the advanced energy management system in building operation.
Article
Engineering, Civil
Marko Kovacevic, Mario Vasak
Summary: Charging electric vehicles poses a significant challenge to the power grid due to the variability in charging load. Coordinated charging and schedule optimization with demand response opportunities are well-known solutions. However, accurately predicting electric vehicle availability and parameters is crucial for determining the charging schedule and demand response potential. We propose a method using discrete-time signals that represent the EV population and enable prediction and optimization. This method preserves valuable information for charging schedule optimization and demand response.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Proceedings Paper
Engineering, Industrial
Dorijan Leko, Mario Vasak
Summary: The paper discusses a cyber-attack on a control system realized through distorting its feedback signal, and introduces a method for detecting this type of attack. The study investigates the extent of damage to the control system caused by a well-informed attacker trying to remain undetected. A demonstration on a simple double-integrator process shows that the invariant-set-based cyber-threat detection system can prevent significant damage even from a fully-informed attacker.
PROCEEDINGS OF 2021 IEEE 30TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE)
(2021)
Proceedings Paper
Automation & Control Systems
Dorijan Leko, Mario Vasak
Summary: This work outlines the non-conservative set-based characterization of Kalman filter state estimation error under bounded disturbances, with a focus on application in cyber-attack detection. The minimal robust positively invariant sets correspond to the least conservative characterization, demonstrating correct and non-conservative estimation error localization.
IECON 2021 - 47TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY
(2021)
Proceedings Paper
Automation & Control Systems
Marko Kovacevic, Branimir Brkic, Mario Vasak
Summary: This work focuses on optimizing problems within the predictive control framework to determine and utilize the flexibility of a microgrid in grid-microgrid energy exchange. By considering all main economical factors and using an online model predictive controller, the technical and economic feasibility of flexibility provision is confirmed.
PROCESS CONTROL '21 - PROCEEDING OF THE 2021 23RD INTERNATIONAL CONFERENCE ON PROCESS CONTROL (PC)
(2021)
Proceedings Paper
Automation & Control Systems
Nikola Hure, Anita Martincevic, Mario Vasak
PROCEEDINGS OF THE 2019 22ND INTERNATIONAL CONFERENCE ON PROCESS CONTROL (PC19)
(2019)
Proceedings Paper
Automation & Control Systems
Hrvoje Novak, Mario Vasak
2018 26TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED)
(2018)
Proceedings Paper
Automation & Control Systems
Danko Marusic, Vinko Lesic, Tomislav Capuder, Mario Vasak
2018 26TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED)
(2018)
Proceedings Paper
Automation & Control Systems
Petra Bucic, Vinko Lesic, Mario Vasak
2018 26TH MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION (MED)
(2018)
Article
Energy & Fuels
Siddharth Sradhasagar, Omkar Subhasish Khuntia, Srikanta Biswal, Sougat Purohit, Amritendu Roy
Summary: In this study, machine learning models were developed to predict the bandgap and its character of double perovskite materials, with LGBMRegressor and XGBClassifier models identified as the best predictors. These models were further employed to predict the bandgap of novel bismuth-based transition metal oxide double perovskites, showing high accuracy, especially in the range of 1.2-1.8 eV.
Article
Energy & Fuels
Wei Shuai, Haoran Xu, Baoyang Luo, Yihui Huang, Dong Chen, Peiwang Zhu, Gang Xiao
Summary: In this study, a hybrid model based on numerical simulation and deep learning is proposed for the optimization and operation of solar receivers. By applying the model to different application scenarios and considering multiple performance objectives, small errors are achieved and optimal structure parameters and heliostat scales are identified. This approach is not only applicable to gas turbines but also heating systems.
Article
Energy & Fuels
Mubashar Ali, Zunaira Bibi, M. W. Younis, Muhammad Mubashir, Muqaddas Iqbal, Muhammad Usman Ali, Muhammad Asif Iqbal
Summary: This study investigates the structural, mechanical, and optoelectronic properties of the BaCuF3 fluoroperovskite using the first-principles modelling approach. The stability and characteristics of different cubic structures of BaCuF3 are evaluated, and the alpha-BaCuF3 and beta-BaCuF3 compounds are found to be mechanically stable with favorable optical properties for solar cells and high-frequency UV applications.
Article
Energy & Fuels
Dong Le Khac, Shahariar Chowdhury, Asmaa Soheil Najm, Montri Luengchavanon, Araa mebdir Holi, Mohammad Shah Jamal, Chin Hua Chia, Kuaanan Techato, Vidhya Selvanathan
Summary: A novel recycling system is proposed in this study to decompose and reclaim the constituent materials of organic-inorganic perovskite solar cells (PSCs). By utilizing a one-step solution process extraction approach, the chemical composition of each layer is successfully preserved, enabling their potential reuse. The proposed recycling technique helps mitigate pollution risks, minimize waste generation, and reduce recycling costs.
Article
Energy & Fuels
Peijie Lin, Feng Guo, Xiaoyang Lu, Qianying Zheng, Shuying Cheng, Yaohai Lin, Zhicong Chen, Lijun Wu, Zhuang Qian
Summary: This paper proposes an open-set fault diagnosis model for PV arrays based on 1D VoVNet-SVDD. The model accurately diagnoses various types of faults and is capable of identifying unknown fault types.