Yazar "Moradzadeh, Arash" seçeneğine göre listele

Listeleniyor 1 - 5 / 5
  • Küçük Resim
    Öğe
    A Cyber-Secure generalized supermodel for wind power forecasting based on deep federated learning and image processing
    (Elsevier Ltd, 2022) Moayyed, Hamed; Moradzadeh, Arash; Mohammadi-Ivatloo, Behnam; Aguiar, A. Pedro; Ghorbani, Reza
    Accurate wind power forecasting is one of the most important operations within the economic dispatch problem to increase the performance of power and energy systems. Accordingly, this study proposes a cyber-resilient hybrid approach based on the Federated Learning and Convolutional Neural Network (CNN) procedure for short-term wind power generation forecasting in different regions of Iran. Generalizability, data independence, forecasting for regions where no training data is available, and preserving the security and privacy of data are prominent features of the proposed method. The federated network was designed with an architecture of 9 clients to perform the training process and extract the salient features from the data associated with each region in each client via the CNN technique. Then, the generalized global supermodel is produced based on the extracted features in each client to forecast the wind power in new and unknown regions such as Mahshahr, Bojnord, and Lootak that had no training data available and had no effect on global supermodel generation. Various scenarios were developed to test the robustness of the suggested methodology. In the first scenario, wind power forecasting is performed based on the suggested technique. In this scenario, the accuracy of the generalized supermodel to forecast wind power generation in each of the Mahshahr, Bojnord, and Lootak regions is 84%, 85%, and 74%, respectively. The second scenario models the scaling attack by changing the wind speed parameters to evaluate the performance of forecasting models against the data integrity attack. In this scenario, an evaluation of the forecast results based on various performance metrics is conducted highlighting the accuracy reduction of the forecast model, due to the damage caused by cyber-attacks on the input data. In the third scenario, the detection of cyber-attack is done based on the image processing-based technique. The presented results emphasize the accurate performance and high generalizability of the cyber-resilient global supermodel in forecasting wind power in various regions of Iran.
  • Küçük Resim
    Öğe
    Deep learning-based cyber resilient dynamic line rating forecasting
    (Elsevier, 2022) Moradzadeh, Arash; Mohammadpourfard, Mostafa; Genc, Istemihan; Şeker, Şahin Serhat; Mohammadi-Ivatloo, Behnam
    Increased integration of renewable energy resources into the grid may create new difficulties for ensuring a sustainable power grid which drives electric utilities to use a number of cost-effective techniques such as Dynamic line rating (DLR) that enable them to run power networks more efficiently and reliably. DLR forecasting is a technique devised to accurately forecast the maximum current carrying capacity of overhead transmission lines. DLR offers many advantages, including increased renewable energy penetration without system reinforcement, improved grid dependability, and lower congestion costs. So far, many solutions have been proposed for DLR forecasting, which, despite estimating the exact capacity of the DLR, have some problems, such as installing multiple sensors and measurement devices and communication networks with precise calibration, and also neglect cyberattacks which may lead to operators making inappropriate operational choices. To address these issues, in this paper, a novel hybrid deep learning-based DLR forecasting approach called the autoencoder bidirectional long short-term memory (AE-BiLSTM) is efficiently and precisely developed. Several scenarios were developed to test the robustness and accuracy of the proposed methodology using real-world data with and without cyber-attacks. Detection of cyber-attack is done based on the increase in the least square errors of forecasting models. Then, the carefully designed hybrid AE-BiLSTM method reconstructs the falsified measurement data and provides reliable DLR forecasting. Also, a comparative study is carried out. The numerical results demonstrated that the proposed hybrid approach can significantly provide acceptable performance even under cyber-attacks and forecast DLR values with the least possible error, outperforming the existing conventional and deep learning-based techniques.
  • Küçük Resim
    Öğe
    Electric load forecasting under False Data Injection Attacks using deep learning
    (Elsevier Ltd, 2022) Moradzadeh, Arash; Mohammadpourfard, Mostafa; Konstantinou, Charalambos; Genc, Istemihan; Kim, Taesic; Mohammadi-Ivatloo, Behnam
    Precise electric load forecasting at different time horizons is an essential aspect for electricity producers and consumers who participate in energy markets in order to maximize their economic efficiency. Moreover, accurate prediction of the electric load contributes toward robust and resilient power grids due to the error minimization of generators scheduling schemes. The accuracy of the existing electric load forecasting methods relies on data quality due to noisy real-world environments, and data integrity due to malicious cyber-attacks. This paper proposes a cyber-secure deep learning framework that accurately predicts electric load in power grids for a time horizon spanning from an hour to a week. The proposed deep learning framework systematically integrates Autoencoder (AE), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) models (AE-CLSTM). The feasibility of the proposed solution is validated by using realistic grid data acquired from the distribution network of Tabriz, Iran. Compared to other load forecasting methods, the proposed method shows the highest accuracy in both a normal case with real-world noise and a stealthy False Data Injection Attack (FDIA). The proposed load forecasting method is practical and suitable for mitigating noise in real-world data and integrity attacks.
  • Küçük Resim
    Öğe
    Photovoltaic array reconfiguration under partial shading conditions for maximum power extraction: A state-of-the-art review and new solution method
    (Elsevier Ltd, 2022) Rezazadeh, Sevda; Moradzadeh, Arash; Pourhossein, Kazem; Akrami, Mohammadreza; Mohammadi-Ivatloo, Behnam; Anvari-Moghaddam, Amjad
    Non-uniform irradiance due to partial shading conditions (PSCs) reduces the power delivered by the photovoltaic (PV) cell. The output power reduction in the PV arrays directly depends on the shading pattern and type of array configuration which is selected. So far, many dynamic and static reconfiguration methods have been used for maximum power point tracking under PSCs in the PV arrays. However, most conventional methods suffer from some major problems such as the need for additional equipment and sensors, complex wiring, the use of expensive sensors, production of complex switching matrices, high costs, and inability to reconfigure PV arrays with very small, large, and non-square sizes. Accordingly, this paper, after reviewing the dynamic and static PV array reconfiguration methods, presents a novel static-based technique called 8-Queen's for reconfiguring the PV modules corresponding to the Total-Cross-Tied (TCT) inter-connection PV array. The 8-Queen's technique has a great ability to apply on high dimensions and rectangular shapes PV arrays and is based on the movement of 8 queens on the chessboard so that none of the queens can attack the others. The effectiveness of the suggested method is expressed by implementing it on 7 cases of the TCT PV array in different sizes and various PSCs. In a comparative scenario, the performance and effectiveness of the proposed 8-Queen's technique are evaluated compared to other conventional methods. Indicators of global maximum power point (GMPP), fill factor, power efficiency, and mismatch losses evaluate the results of the employed methods. The evaluation of results represents the effectiveness of the 8-Queen's technique compared to other used methods. In addition, the performance evaluation of the proposed technique in real-world PV arrays is performed by modeling a sample PV array taking into account measurement errors. The results in this step also show that the proposed technique can also provide acceptable performance for solving problems related to maximum power point tracking under PSCs in PV systems.
  • Küçük Resim
    Öğe
    Short-term electricity demand forecasting via variational autoencoders and batch training-based bidirectional long short-term memory
    (Elsevier, 2022) Moradzadeh, Arash; Moayyed, Hamed; Zare, Kazem; Mohammadi-Ivatloo, Behnam
    Electricity load forecasting is a key aspect for power producers to maximize their economic efficiency in deregulated markets. So far, many solutions have been employed to forecast the consumption load in power grids. However, most of these methods have suffered in modeling the time-series state of data and removing noise from real-world data. Thus, the forecasting results in most cases did not have acceptable accuracy due to the mentioned problems. In this paper, in order to short-term electricity load forecast in Tabriz, Iran, a hybrid technique based on deep learning applications called Variational Autoencoder Bidirectional Long Short-Term Memory (VAEBiLSTM) is presented. Pre-processing, noise cancellation, and time-series state modeling of the data are prominent features of the developed load forecasting model. In addition, in order to prevent overfitting problems in the process of training large amounts of data, the training process is developed in the form of batch training. Load forecasting is done using meteorological and environmental data of Tabriz city as well as historical information and days of the week as input variables. In the hybrid method structure, the Variational Autoencoders are applied to the data for data preprocessing and reconstruction. Then, the normalized, noise-free data is utilized as a dataset for training the Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed training method for BiLSTM is based on batch training. To present the effectiveness of the proposed technique in a comparative approach, the conventional LSTM and Support Vector Regression (SVR) algorithms are also applied to the data. Each network is trained with input data related to the years of 2017 and 2018 to predict the electricity load of the Tabriz city separately for each of the four seasons of the 2019 year. The forecasting results obtained from each method are evaluated by different statistical performance indicators. It can be seen that the proposed model forecasts the load with the correlation coefficients (R) of 99.78%, 99.57%, 99.33%, and 99.76% for spring, summer, autumn, and winter, respectively. The presented results show that the proposed VAEBiLSTM method with the highest R values and minimum forecasting errors compared to the LSTM and SVR methods has high effectiveness and performance.