Reliable Optimization Technique Research Articles

Developing a Deep Learning and Reliable Optimization Techniques for Solar Photovoltaic Power Prediction

Due to its significant solar energy generation, solar PV power facilities have recently been utilized. Although PV power stations are highly preferable, the state’s fundamental drawback is that its output current qualities are unpredictable. Consequently, to ensure a balance and complete functioning, it would be crucial to build systems that allow accurate future projections of solar PV production in the short or medium term. Research postulates a strategy for using deep learning to estimate the short-term electricity generated by solar photovoltaic facilities. This study offers a novel method for predicting photovoltaic systems output power utilizing a Hybrid Deep Neural Network framework, making significant advancements in the field of deep learning applications to transmission system prediction issues. CNN and LSTM are combined in the postulated HDNN paradigm. Traditional deep learning techniques are employed in the initial stage. The effectiveness assessments of these techniques are instead presented in greater detail after they have been trained using firefly optimization techniques. The method with the highest reliability is chosen out of all the techniques used in previous research. Deep learning and power efficiency create a combination that appears to have a successful future, predominantlyin improving sustainable management and the digitalization of the electrical sector.

Systematic Reliability Optimization (ASRO)

Reliability optimization is a critical aspect of modern engineering systems and products, particularly with the growing complexity and interconnectedness of systems. This paper delves into the significance of reliability optimization and the techniques employed to achieve it. It highlights the benefits of optimizing reliability, including reduced costs, enhanced customer retention, and a competitive advantage. The paper discusses the challenges of balancing performance, cost, and reliability, especially in real-world systems with intricate nonlinear interactions between subcomponents. It introduces various reliability optimization techniques, including redundancy analysis, physics-based models, accelerated testing, and data-driven methods. The paper emphasizes the potential of advanced sensing and AI-based methods for reliability optimization. It highlights the importance of AI in optimizing the design and management of complex cyber-physical systems (CPS), where failures can have severe economic and safety consequences. The paper also discusses the empirical review of over 50 studies since 2016, which provides insights into the effectiveness of various optimization approaches across industry verticals. In conclusion, reliability optimization is crucial for the development and operation of modern engineering systems and products. Advanced sensing and AI-based methods offer promising solutions for optimizing reliability in complex systems, particularly CPS. By systematically optimizing reliability, companies can reap significant benefits and ensure the successful operation of their products and services.

Parameter Estimation Techniques for Photovoltaic System Modeling

In improving PV system performance, the parameters associated with electrical photovoltaic equivalent models play a pivotal role. However, due to the increased mathematical complexities and non-linear traits of PV cells, the precise prediction of these parameters is a challenging task. To estimate the parameters associated with PV models, a reliable, robust, and accurate optimization technique is needed. This paper introduces a new algorithm, Rat Swarm Optimizer (RSO), for obtaining the optimum PV cell and module parameters. The proposed method maintains an adequate balance between the exploration and exploitation phases to overcome premature particle issues. The results obtained using RSO are compared with those of other algorithms, i.e., Particle Swarm Optimization (PSO), Ant Lion Optimizer (ALO), Salp Swarm Algorithm (SSA), Harris Hawks Optimization (HHO), and Grasshopper Optimization (GOA), in this work. The modified one-diode model (MODM) and modified two-diode model (MTDM) are used to analyze the parameters of the mono-crystalline PV cell using the suggested RSO. The obtained findings imply that the parameters estimated by the suggested RSO are more accurate than those calculated by the other algorithms taken into consideration in the paper. The statistical results are compared, and it is clear that RSO is a very accurate, fast, and dependable approach for the parameter estimation of PV cells.

Optimal planning and design of a microgrid with integration of energy storage and electric vehicles considering cost savings and emissions reduction

The focus of this study is on the concurrent coordination of electric vehicles and responsive loads in a microgrid setting, with the aim of minimizing operational costs and emissions while considering the variability of wind and photovoltaic power sources. The proposed approach employs electric vehicles for peak shaving and load curve adjustment. Additionally, responsive loads are utilized to provide the necessary resources to accommodate the inherent instabilities of wind and photovoltaic outputs. Moreover, a highly developed two-phase framework is provided for ascertaining the anticipated operational costs of a microgrid, encompassing both energy and reserve costs. The first phase attempts to minimize the costs associated with the production and retention of backup power, whereas the second phase focuses on decreasing the costs of adjusting unit schedules in reaction to variations in wind and photovoltaic energy generation. This research delivers an objective optimization problem, which is subsequently addressed through the utilization of the modified sparrow search algorithm (MSSA), a reliable and efficient optimization technique. The hourly findings obtained from a 24-hour study of an MG model demonstrate the superior performance of the MSSA algorithm relative to other established methodologies. The model under consideration has been executed within a microgrid that incorporates diverse distributed generations. The findings of the simulation indicate that the integration of electric vehicles and responsive loads results in a reduction of operational costs and emissions within the system. Additionally, the uncertainties associated with wind and photovoltaic sources are mitigated. The results obtained from the simulation demonstrate that the proposed MSSA algorithm outperforms other established optimization algorithms.

A Mayfly-Based Approach for CMOS Inverter Design with Symmetrical Switching

This paper presents a novel approach to designing a CMOS inverter using the Mayfly Optimization Algorithm (MA). The MA is utilized in this paper to obtain symmetrical switching of the inverter, which is crucial in many digital electronic circuits. The MA method is found to have a fast convergence rate compared to other optimization methods, such as the Symbiotic Organisms Search (SOS), Particle Swarm Optimization (PSO), and Differential Evolution (DE). A total of eight different sets of design parameters and criteria were analyzed in Case I, and the results confirmed compatibility between the MA and Spice techniques. The maximum discrepancy in fall time across all design sets was found to be 2.075711 ns. In Case II, the objective was to create a symmetrical inverter with identical fall and rise times. The difference in fall and rise times was minimized based on Spice simulations, with the maximum difference measuring 0.9784731 ns. In Case III, the CMOS inverter was designed to achieve symmetrical fall and rise times as well as propagation delays. The Spice simulation results demonstrated that symmetry had been successfully achieved, with the minimum difference measuring 0.312893 ns and the maximum difference measuring 1.076540 ns. These Spice simulation results are consistent with the MA results. The results conclude that the MA is a reliable and simple optimization technique and can be used in similar electronic topologies.

Towards Unique Circuit Synthesis of Power Transformer Winding Using Gradient and Population Based Methods

The aim of the paper is to synthesize a nearly unique, physically realizable and mutually coupled ladder circuit representation of a two-winding transformer by identifying the most accurate and reliable optimization technique such that prior knowledge in selecting the initial guess and search space is avoided. To this end, magnitude and phase of the driving-point impedance function are captured by performing sweep frequency response analysis (SFRA). Then, two widely used population-based algorithms namely, particle swarm optimization (PSO) and artificial bee colony (ABC) and one gradient-based sequential quadratic programming (SQP) algorithm are implemented. Two case studies are considered namely, i) 15 MVA, 66/11.55 kV transformer and, ii) 111 kVA, 7.33/1.22 kV transformer. The performance of the aforementioned algorithms is compared using three evaluation parameters namely, repeatability, accuracy and reliability

Construction of Early Warning Model for Financial Economic Cycle Using Genetic Algorithm

Economic crises occur when the economy experiences drastic fluctuations, which in turn cause heavy losses to society and the economy. Economic crises happen when there are significant losses to society and the economy as a result of the economy experiencing abrupt changes or deep recessions. The term “economic cycle early warning mechanism” refers to a collection of theories and techniques for keeping track of, assessing, forecasting, and choosing policies regarding finances in light of the particular economic phenomenon known as economic cycle fluctuations. The traditional early warning mechanism has been unable to keep up with the demands of economic cycle early warning due to the growth of economic globalisation, and the phenomenon of incomplete early warning and poor early warning accuracy frequently occurs. A genetic algorithm simulates the natural selection and genetic mechanisms of Darwin’s theory of biological evolution. It is a computational model of the biological evolution process. It is a technique for looking for the best answer by simulating the course of natural evolution. Genetic algorithms have advanced incredibly quickly in recent years. It has been widely applied in machine learning, neural networks, control system optimization, and the social sciences as an effective, useful, and reliable optimization technique. In order to optimize the early warning mechanism and increase the thoroughness and accuracy of early warning, this paper investigates the early warning mechanism of financial and economic cycles by combining genetic algorithms. A mathematical model of the economic cycle was built during the experiment and tested in accordance with the genetic algorithm’s basic operating principle. The findings demonstrate that the genetic algorithm-based early warning system for the financial economic cycle is more complete and accurate, with a 6.4% increase in accuracy.

Evaluation of fuzzy membership functions for linguistic rule-based classifier focused on explainability, interpretability and reliability

Objective:Decision support systems focus on their interpretability with a different caution. The majority of approaches utilize reliable optimization techniques to achieve high recognition accuracy. However, accuracy improvement is done at the cost of the readability of the decision support system. This paper proposes a novel technique of linguistic rule extraction focused on: explainability, interpretability, and reliability, called EasIeR. Methods:Proposed solution performs a direct analysis of the learning set without omitting real data imperfections. The proposed algorithm processes the imprecision of data with linguistic values described by fuzzy membership functions and the uncertainty of knowledge employing a fuzzy belief function. It describes the learning set with the most appropriate fuzzy if-then rules. For this purpose, a new method of evaluation of membership functions in a set of rules and their iterative refinement is proposed. Results:EasIeR achieves the best results of trade-off criteria between the generalization quality and the interpretability of the knowledge base when compared with state-of-art fuzzy rule-based classification approaches. Achieving the simplest rule base and competitive generalization quality is verified by cross-validation experiments with benchmark data sets. Significance:The new method of rule evaluation allows for better determination of their quality in decision support, and the selection algorithm quickly provides a clear and easy to interpret knowledge base. This rule evaluation technique will be proficient for all fuzzy rule-based classification systems.

Comparative analysis of the application of artificial neural network-genetic algorithm and response surface methods-desirability function for predicting the optimal conditions for biodiesel synthesis from chrysophyllum albidum seed oil

Efficient and sustainable commercial production of biodiesel requires process optimization and modeling using artificial intelligence techniques. Artificial neural network-genetic algorithm (ANN-GA) and response surface methodology (RSM) were used to predict the optimal process conditions for biodiesel synthesis from novel chrysophyllium albidum seed oil. Application of Levenberg -Marquardt algorithm and full factorial central composite design-desirability function analysis were carried out for ANN and RSM respectively. The biodiesel obtained at the optimum conditions was characterized using gas chromatography-mass spectrophotometer (GC–MS), Fourier transform infrared (FTIR), AOAC and ASTM D standard methods. The ANN and RSM correlation coefficients were 0.98 and 0.95 respectively. The best RSM fitted model was second order polynomial while the ANN best architecture topology consists of three layers: input layer with four input variables, hidden layer with ten hidden neurons and an output layer with single output variable. Optimization of the process shows that: RSM optimum conditions for biodiesel yield of 85.91wt% validated at 86.85wt% were 65.62 °C, 2.14wt% catalyst concentration, 62.04 min and 5.88 methanol: oil molar ratio with overall desirability of 1.00. ANN-GA gave 9.40% faster reaction time and required 15.88% less energy, 3.76% more alcohol and 16.82% less catalyst with 1.86wt% more biodiesel yield than RSM optimized conditions. Ascertained fuel properties, GC–MS and FTIR characterizations confirmed unsaturation and good cold-flow qualities of the biodiesel. Overall results presented ANN-GA as better than RSM and a reliable modeling and optimization technique for viable and sustainable production of biodiesel from chrysophyllum albidum seed.

Optimal Placement of Unified Power Flow Controller by TOPSIS Method for Loss Minimization

In order to eliminate active and reactive power losses in the power system, this paper proposes TOPSIS and DE algorithm for determining the best location and parameter settings for the Unified Power Flow Controller (UPFC). To mitigate power losses, the best UPFC allocation can be achieved by re-dispatching load flows in power systems. The cost of incorporating UPFC into the power system. As a consequence, the proposed objective feature in this paper was created to address this problem. The IEEE 14-bus and IEEE 30-bus systems were used as case studies in the MATLAB simulations. When compared to particle swarm optimization, the results show that DE is a simple to use, reliable, and efficient optimization technique than (PSO). The network’s active and reactive power losses can be significantly reduced by putting UPFC in the optimum position determined by TOPSIS ranking method. Index Term: Differential Evolution (DE); Particle Swarm Optimization (PSO); Unified Power Flow Controller (UPFC).

Solving multi objective power flow problem using enhanced sine cosine algorithm

In the electrical power system optimal power flow is a solution for power management with multi variable equality and inequality constraints. Different algorithms were used to solve the optimum power flow (OPF). This paper proposes the optimal power flow using efficient and reliable optimization technique of enhanced sine cosine algorithm (ESCA). The proposed algorithm used to solve the multi objective power flow function problems such as generating cost, losses, emission of power plant and to improve the voltage stability. In this IEEE standard 30 bus system with four different multi objective functions have been tested and results obtained by Enhanced sine cosine algorithm are compared with other evolutionary algorithms. The results show that ESCA gives better results than other techniques in terms of convergence speed and global optimal solutions.

A new data envelopment analysis-based model for failure mode and effect analysis with heterogeneous information

Failure mode and effect analysis (FMEA) is a multi-disciplined and group-based reliability optimization technique extensively used in diverse industries. When applied in real-life situations, however, the traditional FMEA method has been found to be less effective because of its inherent deficiencies. In the risk analysis process, different types of evaluation information may be involved because of heterogeneous features of risk factors. Moreover, the increasing complexity of products and systems necessitates the participation of a large group of experts with various backgrounds and expertise in FMEA. Thus, in the paper, we develop a new risk analysis model based on data envelopment analysis (DEA) for FMEA within the large group environment. Multiple types of information, including crisp values, interval numbers, and uncertain linguistic terms, are applied for describing different risk factors. The individual risk evaluation information is clustered by an extended fuzzy equivalence clustering method. A modified DEA model is proposed for deriving the risk priority ranking of the identified failure modes. Finally, the effectiveness and applicability of the presented new FMEA model are testified by a case study of blood transfusion and a comparison analysis with relevant existing methods.

An Improved Cuckoo Search Algorithm for Maximum Power Point Tracking of Photovoltaic Systems under Partial Shading Conditions

The problem of partial shading has serious effects on the performance of photovoltaic (PV) systems. Adding a bypass diode in shunt to each PV module avoids hot-spot phenomena, but causes multi-peaks in the power–voltage (P–V) characteristics of the PV array, which cause traditional maximum power point tracking (MPPT) techniques to become trapped in local peaks. This problem has forced researchers to search for smart techniques to track global peaks and prevent the possibility of convergence at local peaks. Swarm optimization techniques have been used to fill this shortcoming; unfortunately, however, these techniques suffer from unacceptably long convergence time. Cuckoo search (CS) is one of the fastest and most reliable optimization techniques, making it an ideal option to be used as an MPPT of PV systems under dynamic partial shading conditions. The standard CS algorithm has a long conversion time, high failure rate, and high oscillations at steady state; this paper aims to overcome these problems and to fill this research gap by improving the performance of the CS. The results obtained from this technique are compared to five swarm optimization techniques. The comparison study shows the superiority of the improved CS strategy introduced in this paper over the other swarm optimization techniques.

Tap changer optimisation using embedded differential evolutionary programming technique for loss control in power system

Over-compensation and under-compensation phenomena are two undesirable results in power system compensation. This will be not a good option in power system planning and operation. The non-optimal values of the compensating parameters subjected to a power system have contributed to these phenomena. Thus, a reliable optimization technique is mandatory to alleviate this issue. This paper presents a stochastic optimization technique used to fix the power loss control in a high demand power system due to the load increase, which causes the voltage decay problems leading to current increase and system loss increment. A new optimization technique termed as embedded differential evolutionary programming (EDEP) is proposed, which integrates the traditional differential evolution (DE) and evolutionary programming (EP). Consequently, EDEP was for solving optimizations problem in power system through the tap changer optimizations scheme. Results obtained from this study are significantly superior compared to the traditional EP with implementation on the IEEE 30-bus reliability test system (RTS) for the loss minimization scheme.

Short Term Hydro-Thermal Scheduling Using Backtracking Search Algorithm

In this article, a new optimization technique, the backtracking search algorithm (BSA), is proposed to solve the hydrothermal scheduling problem. The BSA has mainly unique five steps: (i) Initialization; (ii) Selection – I; (iii) Mutation; (iv) Crossover; and (v) Selection – II; which have been applied to minimize fuel cost of the hydro-thermal scheduling problem. The BSA is very fast, robust, reliable optimization technique and gives an accurate, optimized result. Mutation and crossover are very effective steps of the BSA, which help to determine the better optimum value of the objective function. Here, four hydro and three thermal power generating units are considered. Performance of each committed generating units (hydro and thermal) are also analyzed using a new proposed algorithm, the BSA. A multi-reservoir cascaded hydroelectric with a nonlinear relationship between water discharge rate and power generation is considered. The valve point loading effect is also considered with a fuel cost function. The proposed optimum fuel cost obtained from the BSA shows the better result as compared to other techniques like particle swarm optimization (PSO), teaching learning-based optimization (TLBO), quasi-oppositional teaching learning-based optimization (QOTLBO), real-coded genetic algorithm (RCGA), mixed-integer linear programming (MILP) and krill herd algorithm (KHA), etc.

Reliable Computational Prediction of the Supramolecular Ordering of Complex Molecules under Electrochemical Conditions.

We propose a computationally lean, two-stage approach that reliably predicts self-assembly behavior of complex charged molecules on metallic surfaces under electrochemical conditions. Stage one uses ab initio simulations to provide reference data for the energies (evaluated for archetypical configurations) to fit the parameters of a conceptually much simpler and computationally less expensive force field of the molecules: classical, spherical particles, representing the respective atomic entities; a flat and perfectly conducting wall represents the metallic surface. Stage two feeds the energies that emerge from this force field into highly efficient and reliable optimization techniques to identify via energy minimization the ordered ground-state configurations of the molecules. We demonstrate the power of our approach by successfully reproducing, on a semiquantitative level, the intricate supramolecular ordering observed experimentally for PQP+ and ClO4– molecules at an Au(111)–electrolyte interface, including the formation of open-porous, self-host–guest, and stratified bilayer phases as a function of the electric field at the solid–liquid interface. We also discuss the role of the perchlorate ions in the self-assembly process, whose positions could not be identified in the related experimental investigations.

Reliability Optimization of Real-Time Satellite Embedded System Under Temperature Variations

In this paper, we propose a reliability optimization technique for low earth orbit (LEO) satellite systems that operate in highly varying temperatures. In the proposed technique, we harden the target satellite on-board computer considering two common reliability threats, soft-error and hard-error, at the same time. Based on an existing fault-tolerant scheduling, we show how the reliability and lifetime of the system can be quantified with respect to a given error handling policy. Then, using these models, we perform extensive reliability analyses and optimizations of the hardening degree for different functional safety requirements. We implemented the proposed technique in a widely adopted real-time operating system (RTOS), Real-Time Executive for Multiprocessor Systems (RTEMS), working on a real satellite on-board computer system, GR712RC. The proposed technique enables efficient explorations of the trade-off between the soft-error reliability (failure rate), hard-error reliability (expected lifetime), and other resource utilization indicators, like power consumption or CPU utilization. In particular, the proposed technique could be successfully utilized to co-optimize the lifetime and fault-tolerance concerning the unique ambient temperature profile of LEO satellites.

Assessment of techno-economic benefits for smart charging scheme of electricvehicles in residential distribution system

Connecting multiple electric vehicles (EVs) to a power system network for the purpose of charging has major setbacks like decrease in power quality, instability in voltage profile, and increase in power losses and thus electricity price. This paper focuses on devising an optimal charging scheme to reduce the negative impacts of EVs' presence in the distribution network by limiting the charging process to only off-peak demand periods when the electricity price is comparatively lower. The salp swarm algorithm, an efficient, fast, and reliable optimization technique, is used to obtain the optimal locations for the EVs and their charging schedule in a residential 107-bus radial distribution system (RDS). The proposed optimization technique minimizes the total charging cost of the EVs within the framework of operational constraints of a residential RDS and parking availability. This charging scheme takes care of benefit maximization from both consumer and power supply operators' perspectives by controlling the starting time of EV charging as well as the EV charging rate in order to arrive at the objective.

A decomposition-based reliability and makespan optimization technique for hardware task graphs

This paper presents an approach to optimize the reliability and makespan of hardware task graphs, running on FPGA-based reconfigurable computers, in space-mission computing applications with dynamic soft error rates (SERs). Thus, with rises and falls of the SER, the presented approach dynamically generates a set of solutions that apply redundancy-based fault tolerance (FT) techniques to the running tasks. The set of solutions is generated by decomposing the task graph into multiple subgraphs, applying a multi-objective optimization algorithm to the subgraphs separately, and finally combining and filtering out the obtained solutions of the subgraphs. In this regard, a heuristic has been proposed to decompose task graphs in such a way that a high coverage of the true Pareto set is attained. The experiments show that the presented approach covers 97.37% of the true Pareto set and improves the average computation time of generating the Pareto set from 6.29 h to 81.86 ms. In addition, it outperforms the NSGA-II algorithm in terms of the Pareto set coverage and computation time. Additional experiments demonstrate the advantages of the presented approach over the state-of-the-art adaptive FT techniques in dynamic environments.

Log-normal based mutation evolutionary programming technique for solving economic dispatch problem considering loss minimization

Electricity delivery to the consumer should be implemented in such a way that, cost is minimal, loss is minimal and voltage is within the acceptable limit. In general, the voltage level should be within 95% to 105% of the nominal limit in accordance to most international standard within the power engineering community. This phenomenon is addressed as secure voltage level. The dispatch of electricity is controlled by a dispatch body of the utility in a country. Economic dispatch requires a reliable optimization technique so loss is minimal. This paper presents Log-Normal Evolutionary Programming (LNEP) technique for solving Economic Dispatch (ED) problem considering loss minimization. Validations on the IEEE 6-bus and IEEE 26-bus test systems demonstrated that LNEP is feasible and convincing is addressing the issues. It was revealed that the proposed LNEP gives better solution to solve ED problem than the Classical EP and traditional load flow. Keywords: economic dispatch; evolutionary programming, optimization