Learner Phase Research Articles

An Improved Teaching-Learning-Based Optimization Algorithm with Reinforcement Learning Strategy for Solving Optimization Problems.

This paper presents an improved teaching-learning-based optimization (TLBO) algorithm for solving optimization problems, called RLTLBO. First, a new learning mode considering the effect of the teacher is presented. Second, the Q-Learning method in reinforcement learning (RL) is introduced to build a switching mechanism between two different learning modes in the learner phase. Finally, ROBL is adopted after both the teacher and learner phases to improve the local optima avoidance ability of RLTLBO. These two strategies effectively enhance the convergence speed and accuracy of the proposed algorithm. RLTLBO is analyzed on 23 standard benchmark functions and eight CEC2017 test functions to verify the optimization performance. The results reveal that proposed algorithm provides effective and efficient performance in solving benchmark test functions. Moreover, RLTLBO is also applied to solve eight industrial engineering design problems. Compared with the basic TLBO and seven state-of-the-art algorithms, the results illustrate that RLTLBO has superior performance and promising prospects for dealing with real-world optimization problems. The source codes of the RLTLBO are publicly available at https://github.com/WangShuang92/RLTLBO.

Improving teaching–learning-based-optimization algorithm by a distance-fitness learning strategy

The teaching–learning-based optimization (TLBO) algorithm, composed of a teacher phase and a learner phase, is one of the most popular global optimization approaches. It is inevitable for TLBO to suffer from premature convergence and entrapment in local optima when dealing with complex optimization problems. To solve this problem, a novel TLBO variant named distance-fitness learning TLBO (DFL-TLBO), which employs a brand new distance-fitness learning (DFL) strategy to enhance searchability, is proposed. The DFL strategy guides the whole population to learn from the teacher and a distance-fitness optimum (DFO) candidate simultaneously according to a differential operator to improve the exploitation and exploration capability, respectively. Experimental results on the tests of CEC 2014 reveal that DFL successfully improves the exploitation and exploration capability of TLBO in balance. The statistical test results and the convergence analysis results indicate that the DFL-TLBO algorithm ranks best and is significantly better than other compared algorithms in solving global optimization problems.

Production Wastage Avoidance Using Modified Multi-Objective Teaching Learning Based Optimization Embedded With Refined Learning Scheme

Teaching learning-based optimization (TLBO) is a popular algorithm used to solve various optimization problems. Nevertheless, conventional TLBO and some improved variants tends to suffer with premature convergence due to rapid loss of population diversity, especially when handling the challenging optimization problems. Furthermore, it is not practical to tackle real-world multiobjective problems using prior approach given the frequent changes of customers’ requirements. Motivated by these challenges, an improved variant known as Modified Multi-objective Teaching Learning Based Optimization-Refined Learning Scheme (MMTLBO-RLS) was proposed as a posterior approach to solve challenging multiobjective optimization problems, including the prediction of optimum turning parameters to machine Polyether ether ketone material (PEEK). Substantial modifications were introduced for teacher and learner phases of MMTLBO-RLS to achieve better balancing of exploration and exploitation searches without incurring excessive computational cost. For modified teacher phase of MMTLBO-RLS, each learner was guided by a unique teacher solution and unique mean position to perform searching with better diversity. Meanwhile, two new learning strategies are incorporated into the modified learner phase of MMTLBO-RLS, enabling all learners to enhance their knowledge more efficiently based on their learning preferences. A systematic approach was followed to develop modelling equations required for optimization. The developed algorithm was then employed in single objective optimization as well as multiobjective optimization to cater its performances in any real-world environment. The prediction model reports that surface roughness of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.1042~\mu m$ </tex-math></inline-formula> and material removal rate of 22.8991 cm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> /minute can be achieved. The predicted results differ from validation results by less than 2.69% in any case of optimization. A benchmarking on the performance of MMTLBO-RLS in solving CEC 2009 multiobjective benchmark functions was further carried out with other seven meta-heuristic algorithms. The superior performance of MMTLBO-RLS proves that it is not only suitable to be used in industries to produce the parts of PEEK with supportive quality and quantity, but it is also able to solve other multiobjective optimization problems with competitive performances.

A multi-objective elitist feedback teaching–learning-based optimization algorithm and its application

Students generally attempt to improve themselves with different manners in their spare time. Inspired by this fact, this paper presents a multi-objective elitist feedback teaching–learning-based optimization (MEFTO) algorithm for multi-objective optimization problems. To promote the exploration capacity and convergence of the basic teaching–learning-based optimization (TLBO), a feedback phase that simulates the spare-time learning phenomenon is introduced at the end of the learner phase. Students should compare their score with the average class score to select an appropriate means for further improvement. Poorly performing students can learn from the teacher directly for rapid improvement, whereas high-performing students prefer to motivate themselves for reinforcement learning. Non-dominated sorting is incorporated to permit this heuristic to solve problems with several objectives. Crowding distance calculation is adopted to maintain the diversity of the obtained solution set in a single run. Elitism strategy is also employed to provide a great improvement for the algorithm. The performance of the MEFTO algorithm is compared with seven other well-known algorithms by using a set of unconstrained benchmark test problems and three constrained engineering optimization problems. The qualitative and quantitative results indicate that the proposed algorithm can provide considerably competitive results and outperforms the other algorithms.

Trajectories of self-regulatory driving practices: Role of learner phase practice

IntroductionPrevious research suggests that driving practice in diverse contexts may contribute to earlier licensure and improve driving skills among teen drivers. However, few studies have examined the role of practice diversity in driving outcomes post-licensure. Specifically, examining self-regulatory driving practices post-licensure may provide insight into the extent to which teens choose to avoid driving various environments. The current study examined the relationship between learner phase driving practice diversity and teen self-regulatory driving practices over the first six months of licensure. MethodsFifty-six newly licensed 16-year-olds reported pre-licensure practice diversity, driving exposure and, self-regulatory driving practices at three timepoints (within 2 weeks of licensure and at 3 and 6 months post-licensure). ResultsMulti-level models revealed self-regulatory driving practices significantly decreased over the first six months of independent driving. Practice in complex environments (e.g., on a commercial road, on a highway, etc.) was associated with fewer self-regulatory driving practices at baseline. Practice in simple environments (e.g., in a residential area, in a parking lot) was associated with more self-regulatory driving practices at baseline. Practice driving at night and in bad weather conditions predicted greater post-licensure self-regulation of driving in those specific environments. ConclusionThis study reinforces the importance of practice diversity for teens before independent driving, as early practice can have implications for self-regulatory driving practices immediately upon licensure. Future research examining this topic may inform parent-based interventions to maximize teen driver safety during the critical post-licensure period.

Learner drivers (and their parent-supervisors) benefit from an online hazard perception course incorporating evidence-based training strategies and extensive crash footage

We previously found that a six-session online hazard perception training course, which incorporates evidence-based learning strategies and footage of over a hundred real crashes, improved hazard perception skill and reduced risk-taking intentions in novice drivers who had passed their on-road driving test within the previous three years. However, one issue with targeting crash-prevention training at individuals who are already driving unsupervised is that drivers are at their highest crash risk immediately after they pass their on-road driving test. That is, the training may arrive too late to protect drivers while they are at their most vulnerable. It is also possible that it may prove difficult to persuade drivers to complete an unsupervised training course if they are already licensed to drive independently. Given that learner drivers cannot drive unsupervised, and that they are typically supervised by a parent, one potential strategy is to target the training at learners and to ask their parents to provide one-on-one mentoring throughout the course. We therefore recruited learner driver/parent-supervisor dyads to participate in a randomized control study, with the objective of examining the effects of the hazard perception training course on aspects of driving behaviour associated with crash risk (as measured using validated computer-based tests). Outcome measures included two hazard perception skill assessments (a response time hazard perception test and a verbal response hazard prediction test), and three tests assessing aspects of risk-taking propensity in driving (speed choice, following distance, and gap acceptance). Learners who completed the course (N = 26) significantly improved their scores on both hazard perception skill measures, and also chose safer following distances, compared with a waitlist control group (N = 23). However, the training did not significantly reduce learners’ speed choice or gap acceptance propensity. The hazard perception skill of parent-supervisors, who observed the course but did not complete it, also improved on both hazard perception measures, relative to controls. Additionally, both learners and their parent-supervisors reported a range of positive effects on the learners’ real-world driving performance. These results suggest that this type of hazard perception training could be beneficial if deployed during the learner phase of driver licensing.

Adaptive teaching–learning-based optimization with experience learning to identify photovoltaic cell parameters

Parameter identification of photovoltaic cell and module plays a key role in the simulation, evaluation, control, and optimization of photovoltaic systems. In order to improve the accuracy and reliability of the identified parameters, in this paper, a new adaptive teaching–learning-based optimization with experience learning referred as ELATLBO, is proposed. In ELATLBO, the population is first sorted according to the objective function value, and then it is divided into two parts: fit solutions with good objective function values and inferior solutions with poor objective function values. The fit solution that selects the teacher phase with experience learning is used for local search to improve the exploitation capability of the algorithm. While the inferior solution that selects the learner phase with experience learning is applied for global search to enhance the exploration capability of the algorithm. The performance of ELATLBO is verified by testing the photovoltaic cells and module parameter identification problems, i.e., the single diode model, the double diode model, and the single diode photovoltaic module. The simulated result shows that the proposed ELATLBO exhibits remarkable performance on the accuracy and reliability when compared with other reported parameter identification techniques, especially for the double diode model.

Development and application of hybrid teaching-learning genetic algorithm in fuel reloading optimization

The problems of fuel reloading optimization is a complex multi-objective discrete optimization problem with multiple local optimums. In recent years, great process has been made in solving these problems by using meta-heuristic optimization algorithms. Teaching-learning based optimization algorithm (TLBO) is one kind of novel meta-heuristic optimization algorithms. However, it is seldom used to solve the problems of fuel reloading optimization, because its original purpose is to solve continuous optimization problems. In this paper, a hybrid teaching-learning genetic algorithm (HTLGA) is developed, which could be directly applied to solve the problems of fuel reloading optimization. This hybrid algorithm takes TLBO as main part, combines three operators of genetic algorithms (GA) which are coding, crossover and mutation. The optimization solutions which are represented as students in TLBO are further divided into top students, ordinary students and poor students in HTLGA. The calculation phases “Teacher phase” and “Learner phase” in TLBO are improved into “Teacher phase”, “Discussion phase” and “Self-study phase” in HTLGA. For testing the optimization ability of HTLGA, it is applied to solve the problems of fuel reloading optimization for the 1/6 core of thorium-based block-type HTGRs. The results showed that the developed HTLGA has more powerful optimization ability than TLBO and GA.

An efficient Balanced Teaching-Learning-Based optimization algorithm with Individual restarting strategy for solving global optimization problems

Teaching-learning-based optimization (TLBO) is a population-based metaheuristic algorithm which simulates the teaching and learning mechanisms in a classroom. The TLBO algorithm has emerged as one of the most efficient and attractive optimization techniques. Even though the TLBO algorithm has an acceptable exploration capability and fast convergence speed, there may be a possibility to converge into a local optimum during solving complex optimization problems and there is a need to keep a balance between exploration and exploitation capabilities. Hence, a Balanced Teaching-Learning-Based Optimization (BTLBO) algorithm is proposed in this paper. The proposed BTLBO algorithm is a modification of the TLBO algorithm and it consists of four phases: (1) Teacher Phase in which a weighted mean is used instead of a mean value for keeping the diversity, (2) Learner Phase, which is same as the learner phase of basic TLBO algorithm, (3) Tutoring Phase, which is a powerful local search for exploiting the regions around the best ever found solution, and (4) Restarting Phase, which improves exploration capability by replacing inactive learners with new randomly initialized learners. An acceptable balance between the exploration and exploitation capabilities is achieved by the proposed BTLBO algorithm. To evaluate the performance of BTLBO algorithm, several experimental studies are conducted on standard benchmark suits and the results are compared with several TLBO variants and state-of-the-art population-based optimization algorithms. The results are in excellent agreement and confirm the efficiency of BTLBO algorithm with accelerated exploitation and exploration capabilities with an appropriate balance between such criteria for solving complex optimization problems.

Large-scale bound constrained optimization based on hybrid teaching learning optimization algorithm

Evolutionary computing is an exciting sub-field of soft computing. Many evolutionary algorithm based on the Darwinian principles of natural selection are developed under the umbrella of EC in the last two decades. EAs provide a set of optimal solutions in single simulation unlike traditional optimization techniques for dealing with large-scale global optimization and search problems. Teaching Learning based Optimization (TLBO) is one of the most recently developed EA. TLBO employs a group of learners or a class of learners to perform global optimization search process. The framework of the TLBO consists of two phases, including the Teacher Phase and Learner Phase. The Teacher Phase’ means learning from the teachers and the Learner Phase means learning through interaction among learners. In this paper, we have developed a hybrid TLBO (HTLBO) with aim at to further improve the exploration and exploitation abilities of the baseline TLBO algorithm. The performance of the proposed HTLBO algorithm examined upon using recently designed benchmark functions for the special session of the CEC2017 problems. The experimental results of the proposed algorithm are better than some well-known evolutionary algorithms in terms of proximity and diversity.

Associations between Graduated Driver Licensing restrictions and delay in driving licensure among U.S. high school students

IntroductionSome of the most vulnerable groups of teens choose to delay driving licensure (DDL). We assessed longitudinal associations between state-level Graduated Driver Licensing (GDL) restrictions and DDL among U.S. high school students. MethodsData from seven waves of the NEXT Generation Health Study (starting 10th-grade (2009–2010)), were analyzed in 2020 using Poisson regression. The outcome was DDL (delay vs. no-delay). Independent variables were driving restrictions (at learner and intermediate phases of licensure), sex, race/ethnicity, family affluence, parent education, family structure, and urbanicity. ResultsOf 2525 eligible for licensure, 887 (38.9%), 1078 (30.4%), 560 (30.7%) reported DDL 1–2 years, >2 years, no DDL, respectively. Interactions between GDL restrictions during the learner permit period and covariates were found. In states requiring ≥30 h of supervised practice driving, Latinos (Adjusted relative risk ratio [aRRR] = 1.55, p < .001) and Blacks (aRRR = 1.38, p < .01) were more likely to DDL than Whites. In states where permit holding periods were <6 months, participants with low (aRRR = 1.61, p < .001) and moderate (aRRR = 1.45, p < .001) vs. high affluence were more likely to DDL. Participants in single-parent households vs. both-biological parent households were also more likely to DDL (aRRR = 1.37, p < .05). In states where permit holding periods were ≥6 months, participants with low (aRRR = 1.33, p < .05) vs. high affluence were more likely to DDL. In states that allowed ≥3 passengers or no passenger restriction, participants living in non-urban vs. urban (aRRR = 1.52, p < .05) areas were more likely to DDL, and in states that allowed only 1 or no passenger, participants living in non-urban vs. urban areas (aRRR = 0.67, p < .001) were less likely to DDL. ConclusionsOur findings heighten concerns about increased crash risk among older teens who age out of state GDL policies thereby circumventing driver safety related restrictions. Significant disparities in DDL exist among more vulnerable teens in states with stricter GDL driving restrictions.

Self-regulation differences across learner and probationary drivers: The impact on risky driving behaviours

Risky driving behaviours are a known contributor to young drivers’ overrepresentation in road trauma, with self-regulation suggested as an important associated construct, but yet to be extensively explored. The aims of this study were to examine the utility of self-determination theory in explaining risky driving behaviours and to explore differences between young Learner and Provisional (P1)- licensed drivers in regard to their self-regulated safety orientation and engagement in risky driving behaviours. Learners (n = 1038) and P1(n = 589) drivers, aged 16–19 years, responded to a 91-item online survey, including self-regulated safety orientation items adapted from self-determination theory and inattentive and intentional risky driving behaviour items. Results showed that self-determination theory had good predictive power for the two types of risky driving behaviours for both licence groups. Learner and P1 drivers’ engagement in risky behaviours was similar, however, the relative importance of self-regulated safety orientation elements to reduced engagement in these behaviours differed. Learners’ engagement in intentional risky behaviours reflected greater perceived effort/importance and pressure/tension compared to P1 drivers. Greater effort/importance is an overarching indicator of internalised regulation concerning safe driving behaviours, which might be primed when first exposed to driving. However, greater perceived pressure/tension suggests that internalisation of self-regulatory processes is being suppressed during the Learner phase. This might stem from the required presence of driver trainers and supervisory drivers, as well as interactions with other road users. Whilst only tentative explanations in this first exploration, the findings suggest there is potential for greater efforts in Learner driver training and supervision to encompass the types of skills and learning that encourage the development of self-regulation to reduce risky driving behaviours during both the Learner and P1 stage. These findings contribute to the limited research regarding self-regulation by young novice drivers and informs a better understanding of the psychological influences of engagement in risky driving behaviours, including the first such examination among early independent licensed drivers.

A Surrogate-Assisted Multiswarm Optimization Algorithm for High-Dimensional Computationally Expensive Problems.

This article presents a surrogate-assisted multiswarm optimization (SAMSO) algorithm for high-dimensional computationally expensive problems. The proposed algorithm includes two swarms: the first one uses the learner phase of teaching-learning-based optimization (TLBO) to enhance exploration and the second one uses the particle swarm optimization (PSO) for faster convergence. These two swarms can learn from each other. A dynamic swarm size adjustment scheme is proposed to control the evolutionary progress. Two coordinate systems are used to generate promising positions for the PSO in order to further enhance its search efficiency on different function landscapes. Moreover, a novel prescreening criterion is proposed to select promising individuals for exact function evaluations. Several commonly used benchmark functions with their dimensions varying from 30 to 200 are adopted to evaluate the proposed algorithm. The experimental results demonstrate the superiority of the proposed algorithm over three state-of-the-art algorithms.

Monitor system and Gaussian perturbation teaching–learning-based optimization algorithm for continuous optimization problems

In this paper, an improved teaching optimization algorithm called monitor system and Gaussian perturbation (GP) teaching–learning-based optimization algorithm (MG-TLBO) is proposed based on several modified variants of TLBO. TLBO is simply divided into two phases: “Teacher phase” and “Learner phase.” To further improve the solution accuracy and efficiency, we introduce two mechanisms in the learner phase, namely, monitor system and self-regulated learning (SRL) theory. In the learner phase, we assume that the monitor is the most outstanding individual in the population and possesses self-learning ability to expand his or her own strengths. In addition, GP is deployed to model the SRL process. Therefore, three different versions of MG-TLBO are proposed and related experiments are carried out. The results show that all three MG-TLBOs are more effective than the original TLBO. Finally, comparison of the experimental results with other representative meta-heuristics confirms the validity of the new MG-TLBO. In particularly, the MG-TLBO exhibits an overwhelming advantage over the TLBO, which indicates that the MG-TLBO well balances the exploration and exploitation behavior. All the aforementioned evidence manifests that the MG-TLBO improves the accuracy and efficiency of the solution of the original TLBO.

Parameter Extraction of Photovoltaic Models Using a Dynamic Self-Adaptive and Mutual- Comparison Teaching-Learning-Based Optimization

Parameter extraction of solar cell models plays an important role in the simulation, evaluation, control, and optimization of the photovoltaic (PV) system. Although many meta-heuristic algorithms have been proposed to solve the parameter extraction, it is necessary to further improve the accuracy and reliability of these algorithms. In this paper, an optimized teaching-learning-based optimization (TLBO) is proposed, namely dynamic self-adaptive and mutual-comparison teaching-learning-based optimization (DMTLBO). DMTLBO enhances the basic TLBO by improving its teacher phase and learner phase: (i) In the teacher phase, two differentiated and personalized teaching strategies are proposed according to learners’ learning status. In these two strategies, an adaptive state transition weight factor $\omega $ and a dynamic gap weight factor $\beta $ are introduced to reflect the dynamic transformation of the learners’ learning state in the actual teaching situation. (ii) In the learner phase, a new learning strategy is proposed. The learner can communicate and learn with three different learners who are randomly selected and ranked. To verify the performance of the DMTLBO algorithm, it is used to extract the parameters of different PV models, such as the single diode model, the double diode model, and three PV modules. Among these PV models, the root mean square error values between the measured data and the calculated data of DMTLBO are 9.8602E-04 ± 2.07E-17, 9.8248E-04 ± 1.53E-06, 2.4251E-03 ± 2.15E-17, 1.7298E-03 ± 5.74E-14, and 1.6601E-02 ± 4.55E-10, respectively. Compared with other optimization algorithms, the experimental results show that DMTLBO can provide better or highly competitive convergence speed and extraction accuracy. Besides, the influence of the improved teacher phase and learner phase on DMTLBO and the changing process of both weight factors $\omega $ and $\beta $ are investigated.

Multivariable teaching-learning-based optimization (MTLBO) algorithm for estimating the structural parameters of the buried mass by magnetic data

This paper presents a nature-based algorithm, titled multivariable teaching-learning-based optimization (MTLBO) algorithm. MTLBO algorithm during an iterative process can estimates the best values of the buried structure (model) parameters in a multi-objective problem. The algorithm works in two computational phases: the teacher phase and the learner phase. The major purpose of the MTLBO algorithm is to modify the value of the learners and thus, improving the value of the model parameters which leads to the optimal solution. The variables of each learner (model) are the depth (z), amplitude coefficient (k), shape factor (q), angle of effective magnetization (θ) and axis location (x0) parameters. We employ MTLBO method for the magnetic anomalies caused by the buried structures with a simple geometric shape such as sphere and horizontal cylinder. The efficiency of the MTLBO is also studied by noise corruption synthetic data, as the acceptable results were obtained. We have applied the MTLBO for the interpretation of the four magnetic anomaly profiles from Iran, Brazil and India.

Multivariable Modified Teaching Learning Based Optimization (MM-TLBO) Algorithm for Inverse Modeling of Residual Gravity Anomaly Generated by Simple Geometric Shapes

This paper presents an improved nature-based algorithm, namely multivariable modified teaching learning based optimization (MM-TLBO) algorithm, as in an iterative process can estimates the best values for the model parameters in a multi-objective problem. The algorithm works in two computational phases: the teacher phase and the learner phase. The major purpose of the MM-TLBO algorithm is to improve the value of the learners and thus, improving the value of the model parameters which leads to the optimal solution. The variables of each learner (model) are the radius ( R), depth ( h), shape factor ( q), density contrast ( ρ) and axis location ( x0) parameters. We apply MM-TLBO and TLBO methods for the residual gravity anomalies caused by the buried masses with a simple geometry such as spheres, horizontal and vertical cylinders. The efficiency of these methods are also tested by noise corruption synthetic data, as the acceptable results were obtained. The obtained results indicate the better performance the MM-TLBO algorithm than the TLBO algorithm. We have utilized the MM-TLBO for the interpretation of the six residual gravity anomaly profiles from Iran, USA, Sweden and Senegal. The advantage of the MM-TLBO inversion is that it can estimates the best solutions very fast without falling into local minimum and reaches to a premature convergence. The considered primary population for the synthetic and real gravity data are thirty and fifty models. The results show which this method is able to achieve the optimal responses even if a small population of learners had been considered.

Cooperated teaching-learning-based optimisation for distributed two-stage assembly flow shop scheduling

ABSTRACT Two-stage assembly flow shop scheduling problem with layout has been extensively considered in single factory; however, distributed two-stage assembly flow shop scheduling problem (DTAFSP) with layout in each factory is not studied fully; moreover, teaching-learning-based optimisation is seldom used to solve DTAFSP. In this paper, a cooperated teaching-learning-based optimisation (CTLBO) is proposed to minimise makespan. Multiple classes are constructed. The whole search procedure consists of two stages and each stage possesses two teacher's phases and a learner phase. Class cooperation between the best class and the worst one is implemented by exchanging search times and search ability at the second stage and seldom adopted in the existing works. Extensive experiments are conducted and CTLBO is compared with the existing methods to test its performances. Computational results demonstrate that CTLBO has very competitive performances on solving the considered DTAFSP.

A hybrid adaptive teaching–learning-based optimization and differential evolution for parameter identification of photovoltaic models

Photovoltaic (PV) systems play an important role in today’s power systems because they can convert solar energy directly into electricity. However, theirs conversion performance depends mainly on the PV models unknown parameters. Due to the complex characteristics of the equivalent circuit equation of the PV model, parameter identification of PV models remains a very popular and challenging task in PV system optimization. In this paper, a hybrid adaptive teaching–learning-based optimization (TLBO) with differential evolution (DE), referred to as ATLDE, is proposed to accurately and reliably identify the unknown parameters of PV models. In ATLDE, three improvements are introduced: i) the learners’ ranking probability is presented to adaptively choose the teacher or learner phase of TLBO; ii) based on the learners’ ranking probability, an enhanced teaching manner with an adaptive teaching factor TF is proposed to make use of the exploitation abilities of better learners in the teacher phase; iii) DE is embedded in the learner phase to improve population diversity and encourage wider exploration of the search space. In order to verify the performance of ATLDE, it is applied to parameter identification of different PV models, including the single diode model, the double diode model, and two PV panel module models. The experimental results demonstrate that our approach has great competitiveness in terms of accuracy and reliability. Therefore, the proposed algorithm can be an effective and efficient alternative for PV model parameter identification problems.

Parameter extraction of solar photovoltaic models with an either-or teaching learning based algorithm

This paper presents an advanced variant of teaching learning based algorithm (TLBO) called either-or teaching learning based algorithm (EOTLBO) to extract accurate and reliable parameters of solar photovoltaic (PV) models. EOTLBO synergizes three enhanced strategies to accelerate the convergence rate and boost the search efficiency of TLBO. (i) A median learner based teacher phase excluding the mean position used in the original TLBO is designed to avoid infeasible and inefficient learners and to form a rational and advisable moving mechanism around the teacher. (ii) A higher-achieving learner based learner phase using three sorted learners is devised to directionally guide the target learner to jump out of local optima and to move towards a more promising region. (iii) A chaotic map based either-or teaching-learning strategy is developed to give each dimension of each learner a chance to go through either the median learner based teacher phase or the higher-achieving learner based learner phase. EOTLBO is applied to three PV cells/modules including seven cases. Compared with the original TLBO, four non-TLBO variants, and five TLBO variants, experimental results verify the superior performance of EOTLBO in terms of both the quality of final solutions and the convergence speed on all cases. In addition, the current-voltage characteristics yielded by EOTLBO agree well with the measured data independently of different PV models at different operating conditions.