Teaching Learning Based Optimization Research Articles

Integration method of large-scale photovoltaic system in distribution network based on improved multi-objective TLBO algorithm

The increasing integration of distributed generations brings great challenges to the power grid. In this paper, a distributed photovoltaic (PV) integration methodology in distribution network is established for large-scale PV penetration. Firstly, a PV integration model was formulated with the aim of maximizing PV integration capacity and enhancing the voltage profile. Specially, the PV large-scale integration model for county-wide promotion is proposed by considering various typical integration scenarios. Additionally, a novel improved multi-objective Teaching-Learning based optimization (TLBO) algorithm, namely, IM-TLBO, was proposed to seek an optimal Pareto front of the PV integration model. The IM-TLBO algorithm innovatively incorporates the elite reverse learning search strategy to enhance exploration in the solution space. Moreover, the differentiated teaching guided by optimal individual and central location is employed to improve the efficiency of the “teaching” process. Meanwhile, a cyclic crowded sort deletion based on crowding distance is developed to enhance the diversity of elite individuals and the distribution characteristics of the Pareto Frontier. Finally, the performance of IM-TLBO is tested in benchmark functions. Also, a simulation case in IEEE 33 bus system is performed to verify the proposed PV integration method. It is observed that the proposed method in this paper can not only realize the overall optimal integration of roof distributed PV, but also improve voltage profile. The results of IM-TLBO are compared to other classical algorithms, and it is shown that IM-TLBO outperformed them in terms of convergence, distribution and diversity.

Hyper-heuristic strategies for optimal power flow problem with FACTS devices allocation in wind power integrated system

This research provides hyper-heuristic methodologies for solving Optimal Power Flow (OPF) issues in power system networks with Flexible AC Transmission Systems (FACTS) devices. OPF can be treated as one of the demanding challenges in the power system operating networks. To address the problems of loss and cost reduction, three types of FACTS devices will be studied in this paper: Static VAR Compensator (SVC), Thyristor-Controlled Series Compensator (TCSC), and Thyristor-Controlled Phase Shifter (TCPS). Two high level hyper-heuristic (HHH) approaches, called Exponential Monte Carlo with counter (EMCQ) and randomly select-Only Improving (OI), are employed as high-level metaheuristic to select and leverage the effectiveness of four low-level metaheuristics (LLH). These low-level metaheuristics comprise the Moth-Flame Optimizer (MFO), Barnacles Mating Optimizer (BMO), Teaching-Learning Based Optimization (TLBO) and Gradient-Based Optimizer (GBO). The usage of HHH solving the OPF problem is tested on the modified IEEE 30 bus system that integrates the thermal generators with the wind power. Findings of the study demonstrated the promising results by HHH which manages to outperform all the selected LLH algorithms.

A novel problem-solving method by multi-computational optimisation of artificial neural network for modelling and prediction of the flow erosion processes

This research aims to forecast, using various criteria, the flow of soil erosion that will occur at a particular geographical location. As for the training dataset, 80% of the dataset from the sample sites, four hybrid algorithms, namely heap-based optimizer (HBO), political optimizer (PO), teaching-learning based optimization (TLBO), and backtracking search algorithm (BSA) combined with artificial neural network (ANN) was used to create an erosion susceptibility model and establishes a unique and original approach. After it was confirmed to be successful, the algorithms were applied to create a susceptibility map for this area, demonstrating the integrity of the results. The AUC values were computed for every optimisation algorithm used in this study. The optimal estimated accuracy indices for populations of 450 were determined to be 0.9846 using the BSA-MLP training databases. The maximum AUC value for the HBO-MLP training databases with different swarm sizes was 0.9736. A swarm size of 350–300 is considered optimal for forecasting erosion susceptibility mapping in hybrid models. With the same swarm size constraints, the AUC value for training in the TLBO-MLP scenario was 0.996. After 150 swarm size conditions were used to train the PO-MLP model, the AUC values were 0.9845. According to these findings, the TLBO-MLP and PO-MLP algorithms worked best with populations of 50 and 150, respectively.

A Hybrid TLBO and Simplex Algorithm to Extract the Optimal Parameters of Photovoltaic Models

This work aims to improve photovoltaic (PV) system performance by extracting parameters for solar models, on extracting parameters for solar models to enhance the performance of photovoltaic (PV) systems. This paper proposes a hybrid method for figuring out the unknown electrical characteristics of single and dual diode models, integrating Teaching Learning Based Optimization (TLBO) with a simplex algorithm. The primary objective is to achieve optimal parameter extraction for the PV system. To overcome the challenge of local optima, a deterministic algorithm is employed in the hybrid method, leveraging the simplex algorithm’s faster convergence towards optimal parameters. Comparative analysis with other algorithms like Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), known for handling similar problems, reveals the superior and robust performance of the proposed hybrid approach. The results obtained from the developed method are validated against data from a commercial silicon R.T.C. France solar cell and simulation outcomes under various conditions, further confirming the results’ effectiveness and reliability.

A Fair Multi-Partner Profit Allocation for Islanded Micro-grid

A micro-grid (MG) is regarded as a localized small-scale power supply system designed for providing electrical power for a remote community, which may be connected to the grid. The paper considers six participants’ sites in a remote community. The peak energy consumption patterns for these participants must be different to ensure coalition for mutual benefits and this would facilitate efficient utilization of energy resources. This community concerned may include rural communities having participants such as schools, housing estates, industrial sites, etc. The propose approach would ensure that many participants and their needs are captured and optimized profit of the participants would ensure mutual benefits. In islanded MG, most of the cost/profit distributions in energy trading problems are done based on the self-interest of the participants. Some consider a fair (acceptable or reasonable) cost/profit distribution using the cooperative game theory (CGT) based on the Nash bargaining solution (NBS). However, this method leads to a high degree of dissatisfaction. To improve the fairness and mutual benefits for all MG participants, a new flexible approach is developed. Specifically, CGT which uses a generalized NBS (GNBS) has been proposed, which relaxes certain axiom of the NBS to ensure that fairness of game theory is achieved. The approach allows the profit of the MG participants to be shared using a mechanism based on the negotiation power (i.e. weighted fairness) so that the MG would attain an improved economic outcome. Empirical evaluation of the approach indicates that overall profits using CGT is higher when compared with an independent approach. Moreover, different in negotiation power is achieved in which higher profit is allocated to any participant based on participant's mutual agreement in achieving fair profit distribution. A robust optimization algorithm called Teaching-Learning-Based-Optimization (TLBO) is developed to obtain optimal results. The heuristics algorithms are used in testing the effectiveness of TLBO, which confirm that the TLBO is indeed powerful and robust enough to give quality solutions in solving energy-trading problems.

Intelligent Energy Management for Full-Active Hybrid Energy Storage Systems in Electric Vehicles Using Teaching–Learning-Based Optimization in Fuzzy Logic Algorithms

Intelligent Energy Management for Full-Active Hybrid Energy Storage Systems in Electric Vehicles Using Teaching–Learning-Based Optimization in Fuzzy Logic Algorithms

An Optimized Temperature Compensated Ring Oscillator with Low Power Consumption and Low Variation

In this paper a low power ring oscillator with three differential delay stages and one output buffer stage is designed for Radio Frequency Identification (RFID) applications. The proposed oscillator is designed with neural network model and its parameters are optimized with Teaching–Learning Based Optimization (TLBO) algorithm. The central frequency of the oscillator becomes independent of the temperature with the help of two temperature compensation techniques. In the first technique, the PMOS load transistor of each stage is connected to the NMOS diode connected - in series - transistor. Since these two transistors work in complement of each other, the temperature variation of each stage’s output voltage is decreased. In the second technique, the current variation of oscillator stages versus temperature is reduced since the diode connected transistor is employed in the current source structure. The simulation is done in 0.18 µm Complementary Metal-Oxide Semiconductor (CMOS) technology with the help of Cadence software and the chip area of the layout designed with this software is 19×25 µm2. The designed oscillator exhibits the following parameters: a central frequency of 7.5 MHz, the power dissipation is 238 nW and the frequency deviation is 210 ppm/̊C in the temperature range of 0 to 120ºC, the noise phase and the period jitter are -87.05 dBc/Hz and 0.578 ns (rms), respectively, at 100 KHz offset frequency and 10000 clock cycle.

Modeling and Optimization of Cost-Based Hybrid Flow Shop Scheduling Problem using Metaheuristics

The cost-based hybrid flow shop (CHFS) scheduling has been immensely studied due to its huge impact on productivity. For any profit-oriented organization, it is important to optimize total production costs. However, few researchers have studied hybrid flow shops (HFS) with total production cost utilization. This paper aims to develop a computational model and test the exploration capability of metaheuristics algorithms while optimizing the CHFS problem. Carlier and Neron defined three hypothetical benchmark problems for computational experiments. The popular optimization algorithms PSO, GA, and ACO were implemented on the CHFS model with ten optimization runs. The experimental results proven that ACO performed well regarding mean fitness value for all benchmark problems. Besides this, CPU time for PSO was very high compared to other algorithms. In the future, other optimization algorithms will be tested for the CHFS model, such as Teaching Learning Based Optimization (TLBO) and the Crayfish Optimization Algorithm (COA).

Adam teaching learning optimization enabled LeNet for autism spectrum disorder detection using brain MRI

The autism spectrum disorder (ASD) is a complicated, lifetime, neuro-developmental circumstance of highly unknown causes. It is greatly more ordinary than formerly believed, frequency only to mental retardation amongst serious developmental disorders. Even though, a heritable element is demonstrated in the etiology of ASD, reputed risk genes are still to be detected. Therefore, Adam Teaching Learning Optimization-LeNet (ATLO-LeNet) is introduced for the detection of ASD utilizing brain Magnetic Resonance Imaging (MRI). Here, input considered is provided for the image pre-processing, wherein extraction of Region of Interest (ROI) is performed and median filter is used to eradicate noises. Then, extraction of the pivotal region is completed by the devised ATLO and hence, output-1 is obtained. On the other side, features are mined from an input MRI image. The extracted features include statistical features as well as texture features. From extracted features, output-2 is attained. By considering the output-1 and output-2, ASD classification is completed by LeNet. The LeNet is trained by ATLO, which is the amalgamation of the Adam algorithm and Teaching–Learning-Based Optimization (TLBO). Moreover, ATLO-LeNet acquired a maximum accuracy of 0.916, Negative Predictive Value (NPV) of 0.916and Positive Predictive Value (PPV) of 0.917 whereas it attained a minimum False Positive Rate (FPR) of 0.132 and False Negative Rate (FNR) of 0.152.

An Efficient Optimization Approach for Designing Machine Models Based on Combined Algorithm

Many intrusion detection algorithms that use optimization have been developed and are commonly used to detect intrusions. The process of selecting features and the parameters of the classifier are essential parts of how well an intrusion detection system works. This paper provides a detailed explanation and discussion of an improved intrusion detection method for multiclass classification. The proposed solution uses a combination of the modified teaching–learning-based optimization (MTLBO) algorithm, the modified JAYA (MJAYA) algorithm, and a support vector machine (SVM). MTLBO is used with supervised machine learning (ML) to select subsets of features. Selection of the fewest features possible without impairing the accuracy of the results in feature subset selection (FSS) is a multiobjective optimization issue. This paper presents MTLBO as a mechanism and investigates its algorithm-specific, parameter-free idea. This study used the modified JAYA (MJAYA) algorithm to optimize the C and gamma parameters of the support vector machine (SVM) classifier. When the proposed MTLBO-MJAYA-SVM algorithm was compared with the original TLBO and JAYA algorithms on a well-known intrusion detection dataset, it was found to outperform them significantly.

Frequency Stability of Multi-source Power System using Whale Optimization Algorithm

The Whale Optimization Algorithm (WOA), an evolutionary computing approach, is presented in this study and is used to auto regulated frequency of many composed power systems including thermoelectric power station, hydroelectric, and gas power plants. The purpose of this process follows the concept of a hunting mechanism of fish through water bubbles. The WOA is first applied to a single region with a multi-source power system for optimal gain adjustment of proportional integral controllers (PID). This approach is then applied to two areas, each having six generating sources with AC and AC-DC links. The credible achievements of the WOA-based PID controller are compared with previously constructed optimization approaches like Teaching Learning Based Optimization (TLBO), Differential evolution (DE) and Optimal Controller (OC), which is demonstrated in terms of frequency error, settling time and damping ratio. The performance indices of the purposed controller are analyzed through different objective functions like integral square error (ISE), integral time absolute error (ITAE), integral absolute error (IAE) and integral time squared error (ITSE). By using step load agitation, the simulation results indicate that the suggested technique is computationally stable.

Multi-Objective Optimization of Welding Processes Using Modified Rao Algorithms

The welding community faces a challenging problem in choosing the best welding methods since they are multi-input processes. Modern manufacturing industries have requirements to get fast and optimum process parameters to utilize complete resources in an optimum way. This work attempts to improve the performance of submerged arc welding (SAW), friction welding (FW), and gas tungsten arc welding (GTAW) processes by optimizing their parameters. The newly developed Rao algorithms and their modified versions known as quasi-oppositional Rao (QO Rao), self-adaptive multi-population elite Rao (SAMPE Rao), and improved Rao (I-Rao) are used. This paper contains four multi-objective optimization case studies of SAW, FW, and GTAW processes. A weighted approach is employed to tackle the multi-objective optimization problems effectively. The outcomes achieved using the Rao, QO Rao, SAMPE Rao, and I-Rao algorithms are compared with those obtained by the established optimization algorithms such as accelerated cuckoo optimization algorithm (ACCOA), cuckoo optimization algorithm (COA), plant propagation algorithm (PPA), teaching–learning-based optimization (TLBO) algorithm, Jaya algorithm, quasi-oppositional Jaya (QO Jaya) algorithm, genetic algorithm (GA), particle swarm optimization (PSO) algorithm, and heat transfer search (HTS) algorithm. The effectiveness of the Rao algorithms and their modified versions has been clearly demonstrated as these algorithms have provided superior solutions while requiring fewer generations to achieve them.

FACTS placement for reactive power planning with weak node constraints using an improved symbiotic search algorithm

In this paper, an economically feasible and reliable operation of the IEEE 57 bus system for Optimal Power Flow (OPF) is proposed. The Improved Symbiotic Organisms Search (ISOS) algorithm is proposed for effective reactive power planning as an OPF issue. Further, the optimal position of Flexible AC Transmission Systems (FACTS) is taken into consideration, by including the existing system controlling variables like reactive power generators output, transformer tapping and capacitors connected at shunt. The objective of the work is two-fold; i.e., to reduce the energy loss and to enhance the voltage profile within the prescribed limit by ensuring the economic operation and investment cost of FACTS in the system. In this work, two FACTS devices like Static Var Compensator (SVC) and Thyristor-Controlled Series Controller (TCSC) have been taken into consideration. Voltage sensitivity indicator and reactive power flow are two tools that are utilised in order to locate weak nodes for the implementation of FACTS. Finally, the performance of the ISOS algorithm is compared with that of three other state- of-the -art optimization techniques, such as, Symbiotic Organisms Search (SOS), Differential Evolution (DE) and Teaching Learning Based Optimization (TLBO). A Non-parametric statistical analysis is also performed to investigate the dominance of the ISOS algorithm over others.

A comparative study of different optimization algorithms for the optimum operation of the Mahabad dam reservoir

In this study, the performance of the Differential Evolution (DE) Algorithm, the Genetic Algorithm (GA) and Teaching-Learning Based Optimization (TLBO) Algorithm are compared for the optimum operation of the Mahabad dam reservoir. The Reservoir supplies agricultural, environmental, municipal and industrial water demands of the area. The desktop reserve model is used for estimating the minimum environmental demand. Six alternative agricultural water management scenarios are proposed and a sensitivity analysis is performed on the agricultural demands under different scenarios. The results of the study indicate that both DE and GA algorithms performed nearly equally; however, the DE Algorithm reached its result more quickly with the reliability of 74.19 % compared to the results of the GA and TLBO. A 30 % decrease in agricultural demand in the fifth scenario with 87.56 % reliability provides the best results.

A multi-objective QoS-aware IoT service placement mechanism using Teaching Learning-Based Optimization in the fog computing environment

A multi-objective QoS-aware IoT service placement mechanism using Teaching Learning-Based Optimization in the fog computing environment

Evaluation of response characteristics using sensitivity analysis and TLBO technique of powder mixed wire EDM of Ti6Al4V alloy

The development of Powder Mixed Wire Electric Discharge Machining (PMWEDM) aims to enhance both precise dimension and surface quality, making it a more efficient method for the cost-effective production of precise dies and tools compared to conventional Wire Electric Discharge Machining (WEDM. This approach effectively eliminates the need for secondary operations. The present study is focused on the parametric influence of surfactant with powder mixed WEDM process parameters during die corner cutting on Ti6Al4V material in the presence of surfactant and powder with dielectric. A sensitivity analysis was conducted to determine the significant influence of machining parameters and powder properties in conjunction with the dielectric. To empirically explore these variables, a central composite full factorial design based on response surface methodology was utilized. The design involved varying the pulse on-time (Ton) within the range of 30–90 µs, pulse off-time (Toff) within 3–11 µs, gap voltage (GV) within 40–80 V, and powder concentration (PC) within 2–10 g/L. The mathematical model was developed to predict the responses such as corner inaccuracy (CI) and surface roughness (SR) using RSM. The results conclude that the sensitiveness of powder concentration is highest. Apart from this, positive sensitiveness towards surface roughness is determined for three inputs: pulse on time, pulse off time, and powder concentration. In comparison, powder concentration shows positive sensitiveness towards corner inaccuracy. An artificial intelligence technique namely, Teaching learning-based optimization (TLBO) algorithm has been used to determine the best output. The minimum output for both responses, i.e. corner inaccuracy of 12982.67 µm2 and surface roughness of 1.199 µm, was obtained using TLBO technique. Further improvement for surface finish and corner accuracy in addition powder (3 g/L) with dielectric in WEDM process is found to be a value of 50.77% and 23.01%, respectively, compared with conventional WEDM process. SEM was employed to observe and analyze the topographical changes that occurred during powder mixed and without powder mixed in WEDM process.

Multi-robot path planning using learning-based Artificial Bee Colony algorithm

Multi-robot path planning (MRPP) in continuous and known environment is studied in this paper via proposing a novel local path planning approach. To plan optimal collision-free paths for multiple robots simultaneously, a novel implementation method suitable for the meta-heuristic algorithms is devised, and an improved artificial bee colony (ABC) algorithm is developed. Three enhancements to the ABC algorithm are made in this context. Firstly, to better lead the search direction, the global best individual is involved in the search equations of employed bee phase and scout bee phase. Meanwhile, to boost exploitation capability, the learning method of teaching-learning based optimization (TLBO) algorithm is incorporated into the onlooker bee phase. The proposed learning-based ABC (ABCL) algorithm is used to determine the subsequent positions for all the robots based on their current coordinates considering the path length, safety and planning efficiency. The experimental studies on benchmark functions show that ABCL is outstanding in solving different types of optimization problems compared against seven effective meta-heuristic algorithms. More importantly, MRPP simulation results prove that ABCL outperforms its competitors in terms of generating optimal collision-free paths and running time. Compared with the original ABC, ABCL improves these two aspects on average for all tasks by 2.1% and 12.6%, respectively. Therefore, with the proposed implementation method, ABCL can be considered as an effective MRPP solution.

Optimum design of slot and magnet structure of permanent magnet synchronous generator with teaching‐learning‐studying‐based optimization

AbstractFrom the point of production to consumption, electrical energy should be utilized effectively and qualitatively. Efficiency at the electricity consumption stage is not sufficient, and the desired criteria must be met at the production stage. The efficient and high‐quality generation of electrical energy is directly related to the performance of the generator used. In order to achieve the desired criteria for a generator design, many issues should be considered together. In order for this study to do, a 14‐pole and 5 kW permanent magnet synchronous generator (PMSG) was designed using the innovative optimizer named the weighted mean of vectors (INFO), the jumping spider optimization algorithm (JSOA), the teaching–learning‐based optimization (TLBO), the pelican optimization algorithm (POA) and the teaching‐learning‐studying‐based optimization (TLSBO) algorithms. The generator performance was optimized within the determined inequality constraints by the offset and embrace value and six parameters of the stator slot structure. The generator designed with the parameters determined by the TLSBO was more successful than the generators designed according to all the other proposed algorithms. The total harmonic distortion (THD) value decreased by 51.983% compared to the initial design at approximately the same efficiency.

Two Feedback PID Controllers Tuned with Teaching–Learning-Based Optimization Algorithm for Ball and Beam System

The proportional integral derivative (PID) controller continues to be the most popular and widely used in the industry despite the development of various artificial intelligence-based controllers due to its simplicity and ease of use. Setting PID parameters, especially in non-linear systems, is still a significant problem. This study presents a cascade PID tuning technique based on the teaching–learning-based optimization (TLBO) algorithm. The proposed method is tested for the position control of a non-linear ball and beam system. A comparative analysis of the proposed method is done with the conventional tuning method and particle swarm optimization-tuned cascade PID controller. The optimization was carried out using integral time absolute error, integral time error, and integral square error as objective functions. It was observed that the evolutionary algorithm-based controller tuned by TLBO gives a much better response regarding rise time, settling time, and overshoot. To test the effectiveness and validity of the proposed controller robust analysis of the proposed controller is carried out with a step disturbance applied at t = 3 s. The comparative study proves that TLBO-tuned response is better than other controllers. Sensitivity analysis of the proposed controller is also performed by varying system parameters.

Predicting water quality through daily concentration of dissolved oxygen using improved artificial intelligence

As an important hydrological parameter, dissolved oxygen (DO) concentration is a well-accepted indicator of water quality. This study deals with introducing and evaluating four novel integrative methods for the prediction of DO. To this end, teaching–learning-based optimization (TLBO), sine cosine algorithm, water cycle algorithm (WCA), and electromagnetic field optimization (EFO) are appointed to train a commonly-used predictive system, namely multi-layer perceptron neural network (MLPNN). The records of a USGS station called Klamath River (Klamath County, Oregon) are used. First, the networks are fed by the data between October 01, 2014, and September 30, 2018. Later, their competency is assessed using the data belonging to the subsequent year (i.e., from October 01, 2018 to September 30, 2019). The reliability of all four models, as well as the superiority of the WCA-MLPNN, was revealed by mean absolute errors (MAEs of 0.9800, 1.1113, 0.9624, and 0.9783) in the training phase. The calculated Pearson correlation coefficients (RPs of 0.8785, 0.8587, 0.8762, and 0.8815) plus root mean square errors (RMSEs of 1.2980, 1.4493, 1.3096, and 1.2903) showed that the EFO-MLPNN and TLBO-MLPNN perform slightly better than WCA-MLPNN in the testing phase. Besides, analyzing the complexity and the optimization time pointed out the EFO-MLPNN as the most efficient tool for predicting the DO. In the end, a comparison with relevant previous literature indicated that the suggested models of this study provide accuracy improvement in machine learning-based DO modeling.