Electrical load forecasting is crucial to achieving better efficiency, reliability, and power quality in modern power systems. Applying short‐term load forecasting, a balance can be preserved between supply and demand; the cost of electricity production will also be decreased. Several methods are proposed for short‐term load forecasting in smart grids in recent years and each of them has its own advantages and weaknesses. Among these methods, popularity is increasing in machine learning techniques. This study is to review three common artificial intelligence load forecasting methods, including long short‐term memory, group method of data handling, and adaptive neuro‐fuzzy inference system that have been used to forecast load in a smart grid consisting of a photovoltaic, wind turbine, battery energy storage system, and electric vehicle charging stations. The performance of these methods is evaluated given accuracy and the system's hardware requirements. The noisy condition of the system is also investigated when these methods are used for load forecasting. The results show that the long short‐term memory model is more accurate than the group method of data handling and adaptive neuro‐fuzzy inference system models. However, this method requires much better hardware requirements.

Except in trivial cases, an unknown angle is always extracted from a knowledge of its sine and cosine. These two numbers determine the angle unambiguously; and yet no universally accepted notation expresses that angle as a function of those numbers in a single statement. Some authors use “atan2” for this purpose. I argue that this name is not appropriate, and its description as a “four‐quadrant inverse tangent” is misleading. I propose two interchangeable names “” as candidates for the sought‐after function.

To understand the influences of beam height and side‐to‐midspan ratio on the mechanical characteristics of straddle monorail large‐span continuous steel truss rail beams, the first phase of Wuhu Rail Transit Line 2, a section of continuous steel truss rail beams, is taken as the engineering background. The specific numerical values of the beam heights and side‐to‐midspan ratios of some large‐span bridges, which have been built in China and abroad, are analyzed and counted. Combined with the unique characteristics of continuous steel truss rail beams, the two design variables of side‐to‐midspan ratio and beam height are scientifically valued. The two‐variable direct grid search method is used, and the finite element software Midas Civil is employed to calculate and analyze the mechanical properties of the selected structural system. The main beam deflection, vertical fundamental frequency, beam end corner, and six other aspects are taken as the research focus of the optimization analysis. The above six aspects coordinate bridge strength, stiffness, and stability. They also consider comprehensively and enhance the scientificity of the results. Data indicate that when the side‐to‐midspan ratio and beam height are small, it is beneficial to the structural stress and deformation. However, to prevent the occurrence of the reaction force of the support, the side‐to‐midspan ratio should be greater than 0.2; when the beam height is constant, the ratio increases from 0.56 to 0.74, and the safety factor increases by about 14%. The side‐to‐midspan ratio of 0.56 and the beam height of 1.86 m are the recommended solutions. The scheme features reasonable structural stress and deformation, material saving, and low cost.

The measurement quality of a software defined radio system was investigated and discussed for medical diagnostics in the frequency band of interest 500 MHz–2 GHz. A calibration approach was proposed in order to deal with the random phase problem, and the obtained performance was evaluated and benchmarked against a vector network analyser. The results suggest that the measurement quality of the software defined radio system is mainly limited by the signal leakage from the transmitter to the receiver. Good agreement between the measurement data obtained with the software defined ratio system and the network analyser was achieved when the transmission loss is less than 70 dB. With some a priori knowledge of the measured object, the software defined radio system is able to perform accurate measurement when the transmission loss is even higher.

Here, a novel control technique for Five‐Phase Induction Motor (FPIM) drives using a field‐programmable gate array (FPGA) controller is proposed. Open‐loop control is analysed in terms of the performance and measurement of various power quality factors, such as voltage harmonics, current harmonics, total harmonic distortion, crest factor, unbalanced, short and long‐term flickering, K‐factor, real power, reactive power, apparent power, and power factor. This study experimentally demonstrated a closed‐loop system with both PID and DTC controls for the FPIM. Diminished torque pulsation is obtained by efficiently utilizing the voltage vectors from the total states of 2⁵ = 32. A novel EG voltage vector sequence was proposed for DTC techniques and compared with small, medium, and large voltage vector sequences. Proposed innovative control programming techniques in spartan‐6 XC6SLX25 series FPGA for switching the five‐phase two‐level inverter to reduce the total harmonics distortion by less than 2%.

Unbalanced loads and faults cause power quality problems in power grids, which may lead to system elements failure, particularly to synchronous generators. Faults detection and identification of the disturbance severity level are essential in the grids. Important equipment are often protected with dual protection systems. A backup protection operates and trips appropriate circuit breaker(s) only if the main protection fails to detect the disturbance presence or miss opening the breakers. This paper proposes a backup protection scheme for detecting and evaluating the disruption severity of voltage and current signals for protecting the synchronous generators. This scheme is based on a numerical technique of correlation applied for the electrical signals to detect and assess the fault situation. Different fault types are experimentally conducted on a motor‐generator set to test the proposed algorithm effectiveness using Data Acquisition Card (DAC) and LABVIEW software. The scheme has proven to be successful for fault detection and assessment. The algorithm has shown high reliability at various faults and operating conditions. Moreover, the practical results reveal that the scheme is able to evaluate the severity degree of disturbances/unbalances, and it is effective and secure considering the acceptable overloading, harmonics and temporary faults in power grids.

According to certain rules, some information granules are often induced from the information table, and then the corresponding granular computing models are established to deal with many kinds of data problems. Rough set is a kind of granular computing model which has been deeply studied, and its effectiveness in data processing has been widely proved. From the perspective of digital description, in this paper, the number of information granules, the base and dimension of information granule space induced from information table, is studied. In addition, the number of rough sets, the base and dimension of rough set space, and the accuracy of information granules are discussed.

The current image semantic segmentation methods cannot meet the requirements of high precision and high speed for remote sensing image analysis. The ENet network model builds a semantic segmentation network, which has the characteristics of few network parameters and fast operation speed. The attention mechanism module is integrated with the ENet network model, which can deeply mine image features in remote sensing datasets and ensure the accuracy of semantic segmentation. The author combines the ENet network with the attention mechanism to construct a new semantic segmentation network model. The model first constructed a remote sensing image semantic segmentation network model based on the ENet network, and simplified the model to further improve the speed of image segmentation and recognition. Then, the attention mechanism module is fused with the ENet network model, which can conduct deep and orderly mining of the image features of the remote sensing image data set. It can meet the accuracy requirements of remote sensing image semantic analysis. Simulations are performed based on three general datasets, and the experimental results show high accuracy and high speed.

Due to its stochastic nature, wind energy imposes unprecedented challenges on the power grid, and a properly scheduled reserve is essential to accommodate wind power's intermittency and volatility. Many power reserve scheduling studies have considered the uncertainties of the renewable energy integration but few address how different wind speed forecast techniques influence the scheduling of reserves in the congested transmission networks. Here, three forecasting techniques: Artificial neural network, autoregressive integrated moving average, and probability distribution function‐based model are adopted to forecast one day of wind speed at Taylor, Texas in 2012. To evaluate the impacts of the forecast techniques on power reserve scheduling, a stochastic reserve optimization model was developed to ensure the delivery of reserve in the event of transmission congestion and ramping constraints. A modified RTS‐96 test system was employed and the results claim that different forecast models significantly affect the amount of scheduled up and down reserves in a stochastic reserve optimization problem. The level of operating reserve that is induced by wind is not constant during all hours of the day. Dynamic up and down reserves will be needed with a large scale of wind farm integration.

This paper investigates a study on the efforts made by Iranian government to carry out the Kyoto protocol obligations (reducing pollution by about 54% by 2030). However, the devaluation of the national currency because of sanctions, prohibition of transactions, and a decrease in oil revenues and derivatives has caused problems in achieving this goal. Hence, on 15 November, 2019, Iranian Government decided to increase the fuel price by about 300% to simultaneously reduce environmental pollution and fuel smuggling. The final results show that smuggling is decreased by about 15%. Also, quotas and increased fuel prices caused daily fuel consumption to decrease significantly from 94 to 74 million litres per day. Despite the reduction in fuel consumption, little change is taking place as most pollution is due to diesel and worn‐out vehicles. The increase in fuel prices increases the producer and consumer price index by 1.54% and 2.62%, respectively. Inflation in consumer prices also reaches 15.92%. However, the currency exchange rate and its impact on import products can shift this to 102.15%. Also, because of the shortage of people's income, domestic automakers’ weaknesses, high tax cost of imported cars, and sanctions, most people prefer compressed natural gas (CNG) and public transportation.