International Journal of Smart Electrical Engineering
Volume:12 Issue: 3, Summer 2023

The DC-DC converters are one of the most widely used power electronics infrastructure in the modern systems including renewable generations. With development of DC-DC converters, the control system of the DC-DC converters role is becoming more and more. To this end, model predictive control (MPC) is known as one of the potential solutions. Although MPC is an easily implemented control system, it needs a high computational complexity due to the dependency on solving an iterative optimization problem. To overcome this problem, this study develops an artificial intelligence-based on one-dimensional convolutional neural network (1D-CNN) based MPCs. While 1D-CNN benefits from the inherent strong feature extraction/selection capability and lower computational complexity than other deep methods, it still cannot properly track the dynamic changes due to fixed weights during the training process. Thus, this paper integrates the dynamic weighting training process and proposed dynamic weighing 1D-CNN for the implementation of intelligent MPC for the DC-DC converters. The numerical results show an efficient performance of the proposed system and also verifies the superiority of the proposed method in comparison with the conventional MPC and several state-of-the arts shallow and deep-based MPC for the DC-DC converters in terms of the total harmonic distortion (THD).

This paper presents power management and dynamic assessment of a small hybrid wind and photovoltaic (PV) energy system integrated with battery storage as the auxiliary power source. The system consists of a small wind turbine, photovoltaic cells, a battery, and an electric power converter. The load is supplied with the contribution of all renewable energy sources through an energy management system. Excess wind and photovoltaic energy is redirected to charge the battery. This hybrid energy system is stand-alone, reliable, and ultra-high efficient. A boost converter and a DC/AC inverter are utilized to produce a constant and reliable AC output voltage. The control strategy of voltage regulators is based on PI controllers that are tuned using the particle swarm optimization (PSO) algorithm. The dynamic response of the system to variations in the power source and the load is investigated. Simulation results show the strong self-adaption of the system to sudden operational variations. The combination of wind and PV sources is well-suited for the geographical regions with both windy and sunny days. This standalone system is ideal for suburban and rural areas remote from the electrical grids.

Wireless body area network (WBAN) is a type of wireless communication network, which consists of tiny bio-sensor nodes attached to or implanted in the human body, to continuously monitor the patient by medical staff. Energy efficient routing in WBANs is of utmost importance, as bio-sensors are highly resource-constrained. Although many heuristic- and metaheuristic-based routing protocols have been proposed for WBANs, they suffer from some drawbacks: low solution quality of heuristics and low speed of metaheuristics in online routing. To overcome these drawbacks and simultaneously benefit from the advantage of both techniques, we present an ensemble heuristic-metaheuristic protocol (called CHM) as an adjustable routing solution for WBANs. In CHM, a multi-criteria heuristic based on the residual energy, distance to sink, path loss, and history of becoming a relay node, is used to select proper cluster heads. Furthermore, a metaheuristic algorithm using a genetic algorithm is applied to automatically tune the heuristic protocol. Simulation results in MATLAB using IEEE 802.15.6 on different WBANs demonstrate the performance of the introduced CHM protocol when compared with the existing routing protocols in terms of prolonging the application-specific network lifetime definition.

The most crucial approach for power and control system implementation is optimal power flow because it yields the lowest operating costs and maintains the safety margins for the control variables. An essential component of the flexible AC transmission system (FACTS) is the unified power flow controller (UPFC). It is designed to provide multiple types of energy system compensation and can be utilized for controlling the reactive and active electrical power in transmission lines and bus voltages independently and at the same time. Considerable studies have been published in the UPFC engineering applications area using various techniques. Due to its versatile capabilities, UPFC is recognized as one of the most promising FACTS devices for modern power systems. UPFC is used to improve reactive power mismatch control and system stability. A brief review of UPFC applications for increasing power system flexibility and controllability has been conducted and summarized. This paper also discusses the utilization of artificial intelligence in the placement of UPFC in power systems.

This paper aims to study the appropriate data mining method to extract the rules from a data set and examining the benefits of using the cuckoo algorithm to extract association rules and compare the execution time of the cuckoo algorithm and genetic algorithm (GA). Therefore, an algorithm is proposed that includes two parts: preprocessing and mining. The first part presents the procedures related to the calculation of cuckoo fit values and in the second part of the algorithm, which is the main achievement of this research. Support and confidence The best position can show the least confidence and support.These mining results can be used to continue mining the association rules. The proposed algorithm is based on the cuckoo search. It hides the sensitive relationship rules with a lower time cost and, at the same time, controls the peripheral effects of non-sensitive rules in a better way. This aim is achieved using recurring to the objective function. The GA is set to be the evaluation criterion to show the prominence of the proposed method. In this method, we compare the speed of the cuckoo algorithm with the genetic algorithm, which uses genetic evolution as a problem-solving model. In general, it is an algorithm based on repetition, most of its parts are selected as random processes, and these algorithms are part of the fitting function. It was chosen as a criterion and we paid .It is scientifically proven that the cuckoo algorithm outperforms the GA in the execution time.

The most widespread application of renewable energy is heat production, mainly related to biofuels and solar water heaters (SWHs). Considering that SWHs are essential in energy supply, the present work aims to investigate the heat requirement of a residential apartment in Pakistan using a radiator system in 32 investigated stations. The daily water requirement is 160 L, and the ideal water temperature is 50 oC. It should be considered that hot sanitary water is needed for all 365 days. The investigations were carried out with TSOL Pro 5.5 software to simulate the heat of the desired locations. Also, after the analysis, we found that the selected location's SWH and thermal energy supply have high efficiency. The total heat supply using renewable energies is 18-42% for the investigated stations, and the rest of the required heat is supplied with fossil fuel. Since SWHs are one of the simplest and most economical ways to provide hot water for homes, offices, schools, hospitals, etc., Pakistani people can save a large amount of energy by investing in this field. Considering that Pakistan has good radiation potential, we hope that the present work results will lead to more use of SWHs.

In this study, a novel sliding mode adaptive controller is developed for three-link PUMA robot, regards to high-gain fuzzy observer in an uncertainty condition. The studied system has uncertain nonlinear functions, multiple inputs and outputs, and non-measurable scenarios, and therefore requires an observation design. To design the controller, fuzzy systems were initially utilized to approximate non-linear uncertain functions, and then a sup posable observer is available to estimate non-measurable system states. Finally, by combining the adaptive fuzzy controller and feedback lineari zation method, a high-gain observer-based fuzzy control was developed. In order to this approach is used as enhance performance indicators of the control system. Fuzzy Takagi-Sugeno systems were employed to find the control gain. In the proposed control method, the convergence of tracking the desired reference signal of the system can be guaranteed by designing the adaption's parameters. The simulation results demonstrated the validity of the control method. .

The interface between brain and computer has received increasing attention in the last decade of scientific progress The most common use of this type of technology is the direct control of a computer cursor by a person or animal using brain computer interfaces (BCIs) based on electrophysiological signals. brain computer interface systems can benefit the elderly in many ways, such as: teaching motor/cognitive abilities, controlling household appliances, communicating with others, and controlling the exoskeleton. Exchange can be done between software, computer hardware, peripherals, humans and a combination of them. This paper presents a limb movement classification system based on the electroencephalogram signal. The system contains five parts: preprocessing using wavelet transform, feature extraction, feature reduction and classification. The experimental results are shown that the support vector machine classifier with non-linear kernel and nearest neighbor classifier has an efficiency higher than 80%. The best indicators for support vector machine classification with nonlinear kernel and nearest neighbor are shown by the simulation results.