Diaa Salman

The use of hybrid Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) models for solar panel Maximum Power Point (MPP) prediction is examined in this work. Improved solar energy forecasting accuracy is essential for grid integration and power-generating optimization. A novel CNN-GRU architecture that captures both temporal and spatial patterns present in solar energy data using a dataset that includes temperature, irradiance, and MPP characteristics is utilized. A comparison study with alternative hybrid architectures and individual GRU and CNN models. Model performance is evaluated by use of evaluation metrics such as coefficient of determination (R²), Mean Squared Error (MSE), and Mean Absolute Error (MAE). Results show that the CNN-GRU model achieves better accuracy in forecasting voltage (Vmp) and current (Imp) at the MPP than individual architectures. Furthermore, residual analysis and prediction against actual comparisons prove the efficacy and robustness of the suggested method. The practical ramifications of this study for renewable energy management and grid stability advance solar energy forecasting methods.

Unit Commitment (UC) is a power system nonlinear programming with mixed integers issue. As Electric Vehicles (EVs) and renewable energy sources are incorporated into the power system, the UC problem becomes more challenging. With the continued increase of wind and solar-based renewable energy in the utility power system on the supply side, the random features of the supply and demand sides of the power grid will become increasingly apparent, affecting the system's security, stability, and economical operation. In that sense, UC has theoretical and practical importance. The optimal scheduling of thermal, wind, solar, and EV units has been studied. The purpose of optimal scheduling is to minimize unit operating expenses. This study examines how the integration of a large percentage of renewable energy sources like wind and solar affects the effectiveness of short-term power system planning and control in urban areas where EVs charging stations and conventional demand coexist. Particle Swarm Optimization (PSO)is used to minimize the system's operational costs. The IEEE 24-bus test system is used to evaluate the study. Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are compared and used to forecast the day ahead performance of the load demand, wind and solar energy, and EVs stations demand to be used in the proposed case study. It has been found that in forecasting the load demand, solar power, and EVs charging demand, LSTM performs better than GRU with MSE of 5.2%, 3.6%, and 8.6%, respectively, and for wind power prediction, GRU outperforms LSTM with MSE of 3.9%. Moreover, the results show the robustness of the proposed methodology with optimal production costs of $340686.

Forecasting solar power production accurately is critical for effectively planning and managing renewable energy systems. This paper introduces and investigates novel hybrid deep learning models for solar power forecasting using time series data. The research analyzes the efficacy of various models for capturing the complex patterns present in solar power data. In this study, all of the possible combinations of convolutional neural network (CNN), long short-term memory (LSTM), and transformer (TF) models are experimented. These hybrid models also compared with the single CNN, LSTM and TF models with respect to different kinds of optimizers. Three different evaluation metrics are also employed for performance analysis. Results show that the CNN-LSTM-TF hybrid model outperforms the other models, with a mean absolute error (MAE) of 0.551% when using the Nadam optimizer. However, the TF-LSTM model has relatively low performance, with an MAE of 16.17%, highlighting the difficulties in making reliable predictions of solar power. This result provides valuable insights for optimizing and planning renewable energy systems, highlighting the significance of selecting appropriate models and optimizers for accurate solar power forecasting. This is the first time such a comprehensive work presented that also involves transformer networks in hybrid models for solar power forecasting.

As renewable energy sources become more prevalent in the grid, grid operators face new issues in maintaining system reliability in the face of changing conditions while also maximizing renewable energy usage. The need for system robustness increases as more renewable energy, such as wind power, is used in the system. In this paper, short-term power system planning and _ control performance is being investigated; dynamic programming (DP) asa robust optimization technique is being applied to decrease power system operational expenses. The proposed methodology is being tested on an IEEE 14-bus test system. Gated recurrent unit (GRU) and hybrid gated recurrent unit with long short term memory (GRU/LSTM) are two machine learning algorithms being utilized to forecast the performance of short-term wind generation and load demand. The prediction results show that GRU/LSTM outperforms GRU with a mean square error of 0.045 and 0.043 for load and wind prediction, respectively, to achieve the plan of UC with minimum production costs of 508933.8$ for the day ahead.

The rate of growth of countries all over the world is increasing dramatically and is unavoidable, resulting in an increase in energy consumption. Moreover, fast residential and commercial development contributes to an increase in construction energy usage. Energy consumption forecasting has become critical for predicting power consumption. One of the most significant factors in power system design and operation is load forecasting. Load forecasting for power systems is a critical feature in both the economy and developed businesses. In this research a well-defined machine learning algorithm termed Recurrent Neural Networks (RNN) is exploited to forecast the day and year ahead performance of the load demand of France.

Unit Commitment (UC) is a complicated integrational optimization method used in power systems. There is previous knowledge about the generation that has to be committed among the available ones to satisfy the load demand, reduce the generation cost and run the system smoothly. However, the UC problem has become more monotonous with the integration of renewable energy in the power network. With the growing concern towards utilizing renewable sources for producing power, this task has become important for power engineers today. The uncertainty of forecasting the output power of renewable energy will affect the solution of the UC problem and may cause serious risks to the operation and control of the power system. In power systems, wind power forecasting is an essential issue and has been studied widely so as to attain more precise wind forecasting results. In this study, a recurrent neural network (RNN) and a support vector machine (SVM) are used to forecast the day-ahead performance ...

Unit Commitment (UC) is a complicated integrational optimization method used in power systems. There is previous knowledge about the generation that has to be committed among the available ones to satisfy the load demand, reduce the generation cost and run the system smoothly. However, the UC problem has become more monotonous with the integration of renewable energy in the power network. With the growing concern towards utilizing renewable sources for producing
power, this task has become important for power engineers today. The uncertainty of forecasting the output power of renewable energy will affect the solution of the UC problem and may cause serious
risks to the operation and control of the power system. In power systems, wind power forecasting is an essential issue and has been studied widely so as to attain more precise wind forecasting results. In this study, a recurrent neural network (RNN) and a support vector machine (SVM) are used to forecast the day-ahead performance of the wind power which can be used for planning the day-ahead performance of the generation system by using UC optimization techniques. The
RNN method is compared with the SVM approach in forecasting the wind power performance; the results show that the RNN method provides more accurate and secure results than SVM, with an
average error of less than 5%. The suggested approaches are tested by applying them to the standard IEEE-30 bus test system. Moreover, a hybrid of a dynamic programming optimization technique and
a genetic algorithm (DP-GA) are compared with different optimization techniques for day ahead, and the proposed technique outperformed the other methods by 93,171$ for 24 h. It is also found that the uncertainty of the RNN affects only 0.0725% of the DP-GA-optimized UC performance. This study may help the decision-makers, particularly in small power-generation firms, in planning the
day-ahead performance of the electrical networks.