• Energy Research

Recently, with the establishment of new thermal regulation, the energy efficiency of buildings has increased significantly, and various deep learning-based methods have been presented to accurately forecast the heating load demand of buildings. However, all of these methods are executed on a dataset with specific distribution and do not have the property of global forecasting, and have no guarantee of data privacy against cyber-attacks. This paper presents a novel approach to heating load demand forecasting based on Cyber-Secure Federated Deep Learning (CSFDL). The suggested CSFDL provides a global super-model for forecasting heating load demand of different local clients without knowing their location and, most importantly, without revealing their privacy. In this study, a CSFDL global server is trained and tested considering the heating load demand of 10 different clients in their building environment. The presented results, including a comparative study, prove the viability and accuracy of the proposed procedure.

Abstract This paper provides an answer to the problem of State Estimation (SE) with multiple simultaneous gross errors, based on Generalized Error Correntropy instead of Least Squares and on an interior point method algorithm instead of the conventional Gauss–Newton algorithm. The paper describes the mathematical model behind the new SE cost function and the construction of a suitable solver and presents illustrative numerical cases. The performance of SE with the data set contaminated with up to five simultaneous gross errors is assessed with confusion matrices, identifying false and missed detections. The superiority of the new method over the classical Largest Normalized Residual Test is confirmed at a 99% confidence level in a battery of tests. Its ability to address cases where gross errors fall on critical measurements, critical sets or leverage points is also confirmed at the same level of confidence.

AbstractRecently, the increasing prevalence of solar energy in power and energy systems around the world has dramatically increased the importance of accurately predicting solar irradiance. However, the lack of access to data in many regions and the privacy concerns that can arise when collecting and transmitting data from distributed points to a central server pose challenges to current predictive techniques. This study proposes a global solar radiation forecasting approach based on federated learning (FL) and convolutional neural network (CNN). In addition to maintaining input data privacy, the proposed procedure can also be used as a global supermodel. In this paper, data related to eight regions of Iran with different climatic features are considered as CNN input for network training in each client. To test the effectiveness of the global supermodel, data related to three new regions of Iran named Abadeh, Jarqavieh, and Arak are used. It can be seen that the global forecasting supermodel was able to forecast solar radiation for Abadeh, Jarqavieh, and Arak regions with 95%, 92%, and 90% accuracy coefficients, respectively. Finally, in a comparative scenario, various conventional machine learning and deep learning models are employed to forecast solar radiation in each of the study regions. The results of the above approaches are compared and evaluated with the results of the proposed FL-based method. The results show that, since no training data were available from regions of Abadeh, Jarqavieh, and Arak, the conventional methods were not able to forecast solar radiation in these regions. This evaluation confirms the high ability of the presented FL approach to make acceptable predictions while preserving privacy and eliminating model reliance on training data.

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.

Improving the accuracy of photovoltaic (PV) power forecasting is crucial to ensure more effective use of energy resources. Improvements are especially important for regions for which historical solar radiation data do not exist. This paper proposes a cyber-secure forecasting model called federated deep learning (FDL) to forecast PV power generation in various regions across Iran. The training process in each client is done by a convolutional neural network (CNN). Then, a generalizable global supermodel is generated based on the features extracted in each client, which has the ability to generalize and forecast for regions where there is no training data. Preserve data privacy and ideal performance against cyber-attacks are prominent features of the proposed method. The use of the proposed method is illustrated with a case study for Iran. The proposed FDL network is designed with 9 clients and three different scenarios were developed to test the robustness of the suggested method. In the first scenario, the PV power generation forecasting is done via the proposed technique and other conventional methods. The performance accuracy (2) of the generated global supermodel in this scenario for PV power generation forecasting in the regions of Khomein, Meybod, Varzaneh, Taleghan, and Shiraz are obtained as 0.981, 0.989, 0.986, 0.983, and 0.987 respectively. However, it was observed that other conventional deep learning-based models such as CNN and long short-term memory were not able to provide any forecasting for these regions. The second scenario models the scaling attack as a specific pattern of false data injection attack, to evaluate the performance of forecasting models against the data integrity attack. In the third scenario, cyber-attack detection is performed based on data visualization and image processing procedures. The results presented in different scenarios emphasize the high accuracy and generalizability of the global cyber-secure supermodel in PV power generation forecasting in different regions of Iran.

Abstract The paper provides the theoretical proof of earlier published experimental evidence of the favorable properties of a new method for State Estimation – the Generalized Correntropy Interior Point method (GCIP). The model uses a kernel estimate of the Generalized Correntropy of the error distribution as objective function, adopting Generalized Gaussian kernels. The problem is addressed by solving a constrained non-linear optimization program to maximize the similarity between states and estimated values. Solution space is searched through a special setting of a primal-dual Interior Point Method. This paper offers mathematical proof of key issues: first, that there is a theoretical shape parameter value for the kernel functions such that the feasible solution region is strictly convex, thus guaranteeing that any local solution is global or uniquely defined. Second, that a transformed system of measurement equations assures an even distribution of leverage points in the factor space of multiple regression, allowing the treatment of leverage points in a natural way. In addition, the estimated residual of GCIP model is not necessarily zero for critical (non-redundant) measurements. Finally, that the normalized residuals of critical sets are not necessarily equal in the new model, making the identification of bad data possible in these cases.

Classical Weighted Least Squares (WLS) State estimation (SE) in power systems is known for not performing well in the presence of Gross Errors (GE). The alternative using Correntropy proved to be appealing in dealing with outliers. Now, a novel SE method, generalized correntropy interior point method (GCIP) is being proposed, taking advantage of the properties of the Generalized Correntropy and of the Interior Point Method (IPM) as solver. This paper discusses how the choice of different central path neighborhoods, an essential concept in IPM, is critical in the identification of gross errors. The simulation results indicate that a one-sided infinity norm neighborhood successfully identifies outliers in the SE problem, making GCIP a competitive method.

Dynamic line rating (DLR) is considered a key concept in transmission lines that can guarantee the variable nature of renewable energy sources with minimal economic constraints. So far, various schemes have been selected for DLR forecasting that offers acceptable capacity but require measuring instruments and communication networks with precise calibration on the conductor surface, which in addition to high economic costs, are always available for cyber attackers. In this study, to forecast the DLR values, a deep learning-based technique called long short-term memory (LSTM) is proposed. Additionally, a novel data integrity attack detection approach based on image processing is developed to maintain the performance of the forecasting model against cyber-attacks. The LSTM forecasts the DLR values of an overhead transmission line located in Tabriz, Iran, using meteorological parameters as input data. The forecasting results confirm the high performance of the LSTM model with minimal error values. Then, a scaling attack is applied as a known data integrity attack on the input variables of wind speed and wind direction to evaluate the performance of the LSTM network against cyber-attacks. The results of this scenario show that a cyber-attack can significantly reduce the accuracy of the forecasting. To prevent this, the image processing-based technique detects and clearly displays the cyber-attacks in each of the input variables by converting the input data parameters to 2-D images.