Self-adaptive Evolution Algorithm Research Articles

Historical knowledge transfer driven self-adaptive evolutionary multitasking algorithm with hybrid resource release for solving nonlinear equation systems

In reality, there are many extremely complex nonlinear optimization problems. How to locate the roots of nonlinear equation systems (NESs) more accurately and efficiently has always been a major numerical challenge. Although there are many excellent algorithms to solve NESs, which are all limited by the fact that the algorithm can solve at most one NES in a single run. Therefore, this paper proposes a historical knowledge transfer driven self-adaptive evolutionary multitasking algorithm framework (EMSaRNES) with hybrid resource release to solve NESs. Its core is that in one run, EMSaRNES can efficiently and accurately locate the roots of multiple NESs. In EMSaRNES, self-adaptive parameter method is proposed to dynamically adjust parameters of the algorithm. Secondly, adaptive selection mutation mechanism with historical knowledge transfer is designed, which dynamically adjusts the evolution of populations with or without knowledge sharing according to changes in the current population diversity, thereby balancing population diversity and convergence. Finally, hybrid resource release strategy is developed, which archives the roots that meet the accuracy requirements, and then three distributions are selected to generate new populations, thus ensuring that the population diversity is maintained at high level. After a variety of experiments, it has been proven that compared to comparative algorithms EMSaRNES has superior performance on 30 general NESs test sets. In addition, the results on 18 extremely complex NESs test sets and two real-life application problems further prove that EMSaRNES finds more roots in the face of complex problems and real-life problems.

A multi-objective optimization approach for sustainable and personalized trip planning: A self-adaptive evolutionary algorithm with case study

In the modern tourism landscape, the fusion of sustainability and personalized travel plans marks a significant paradigm shift. This paper presents a novel multi-objective optimization approach for crafting sustainable and personalized tourist trip plans. The proposed model is designed to provide tailored recommendations to tourists, simultaneously minimizing total costs, environmental impacts, and maximizing individual preferences. These recommendations encompass choices such as hotel and resting place selection, daily sequence of attractions, precise visit schedules, and preferred modes of transportation. Addressing intricacies within an urban multi-modal transport system, including factors like traffic lights, weather conditions, and distinct features of each transport mode, the model ensures that tourists can explore scenic spots within their available time windows. To tackle uncertainties in travel time, travel costs, and visit durations, a practical fuzzy optimization approach is employed. For efficient resolution of the multi-objective optimization model, a self-adaptive evolutionary algorithm based on Non-Dominated Sorting Genetic Algorithm II (SA-NSGAII) is developed. The effectiveness of the proposed solution method is verified through comparisons with Augmented ε-Constraint (AUGMECON) and NSGA-II methods, utilizing various benchmark examples. Employing real data from Montreal, an empirical case study is conducted to illustrate the application of the sustainable and personalized trip planning model. The analysis of the solution results demonstrates how this approach can assist tourists in achieving a harmonious balance between sustainability objectives and making well-informed decisions based on their individual preferences.

Diabetes Prediction and Classification Using Self-adaptive Evolutionary Algorithm with Convolutional Neural Network

Diabetes Prediction and Classification Using Self-adaptive Evolutionary Algorithm with Convolutional Neural Network

SaE-GBLS: an effective self-adaptive evolutionary optimized graph-broad model for EEG-based automatic epileptic seizure detection.

Epilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem. To obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset. The experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches.

Enhancing Electric Vehicle Reliability and Integration with Renewable Energy: A Multi-Faceted Review

Electric vehicles (EVs) are gaining attention due to their zero carbon emissions, but concerns about their reliability, especially critical components, persist. Previous research has primarily focused on EV drive motor reliability, neglecting the motor controller. To address this gap, this study assesses the reliability of the entire motor system in electric vans, including both drive motor and motor controller components. It predicts failure rates for these components, highlighting vulnerabilities and shortcomings in existing research, which can inform future design and maintenance. In addition, the integration of EVs and renewable energy resources has garnered attention, but concerns about component reliability have arisen. A novel approach called " Innovative Incentive-Driven Fuzzy Fault Tree Analysis " (IIFFTA) is introduced for power systems incorporating EVs and renewable energy, addressing vague and imprecise events and data deficiencies in conventional fault tree analysis. IIFFTA considers different component failure rates and probability values of fault occurrences, offering a more effective risk assessment method. Lastly, plug-in electric vehicles (PEVs) impact distribution systems, and this paper explores distribution feeder reconfiguration (DFR) as a reliability-enhancing strategy for coordinating vehicle-to-grid (V2G) services from PEV fleets within a stochastic framework. The study accounts for uncertainties related to network demand, energy prices, wind power generation, and PEV fleet behavior, employing a self-adaptive evolutionary algorithm (SOS) to address the stochastic optimization problem.

Techno-Economic Optimization Study of Interconnected Heat and Power Multi-Microgrids with a Novel Nature-Inspired Evolutionary Method

The world is once again facing massive energy- and environmental challenges, caused by global warming. This time, the situation is complicated by the increase in energy demand after the pandemic years, and the dramatic lack of basic energy supply. The purely “green” energy is still not ready to substitute the fossil energy, but this year the fossil supplies are heavily questioned. Consequently, engineering must take flexible, adaptive, unexpected directions. For example, even the natural gas power plants are currently considered “green” by the European Union Taxonomy, joining the “green” hydrogen. Through a tight integration of highly intermittent renewable, or other distributed energy resources, the microgrid is the technology of choice to guarantee the expected impacts, making clean energy affordable. The focus of this work lies in the techno-economic optimization analysis of Combined Heat and Power (CHP) Multi-Micro Grids (MMG), a novel distribution system architecture comprising two interconnected hybrid microgrids. High computational resources are needed to investigate the CHP-MMG. To this aim, a novel nature-inspired two-layer optimization-simulation algorithm is discussed. The proposed algorithm is used to execute a techno-economic analysis and find the best settings while the energy balance is achieved at minimum operational costs and highest revenues. At a lower level, inside the algorithm, a Sequential Least Squares Programming (SLSQP) method ensures that the stochastic generation and consumption of energy deriving from CHP-MMG trial settings are balanced at each time-step. At the upper level, a novel multi-objective self-adaptive evolutionary algorithm is discussed. This upper level is searching for the best design, sizing, siting, and setting, which guarantees the highest internal rate of return (IRR) and the lowest Levelized Cost of Energy (LCOE). The Artificial Immune Evolutionary (AIE) algorithm imitates how the immune system fights harmful viruses that enter the body. The optimization method is used for sensitivity analysis of hydrogen costs in off-grid and on-grid highly perturbed contexts. It has been observed that the best CHP-MMG settings are those that promote a tight thermal and electrical energy balance between interconnected microgrids. The results demonstrate that such mechanism of energy swarm can keep the LCOE lower than 15 c€/kWh and IRR of over 55%.

A self-adaptive evolutionary algorithm using Monte Carlo Fragment insertion and conformation clustering for the protein structure prediction problem

A self-adaptive evolutionary algorithm using Monte Carlo Fragment insertion and conformation clustering for the protein structure prediction problem

Stock market prediction and portfolio composition using a hybrid approach combined with self-adaptive evolutionary algorithm

This work presents a new approach to maximize financial market investment returns. It incorporates two Evolutionary Algorithms (EAs) combined with fundamental and technical investment strategies. The first EA (simple) maintains its evolutionary parameters static during evolution. The second (self-adaptive) introduces the variation operators’ parameters’ values in the representation for them to evolve. The EA is responsible for optimizing the weight that financial ratios from the F-Score have on composing static/dynamic portfolios. Furthermore, it is also responsible for defining the importance that selected technical indicators have on revealing the best timing for market positions placement. Results showed that both cases surpassed the S&P500 returns, performing their best results using a self-adaptive EA combined with a static portfolio and a sliding window of 2 years of train/test. The technical case study showed better results in “bear markets” since it predicted some market declines. Its best subtest achieved returns on average 2.2x and in its best 3.5x higher than the benchmark. Its Sharpe Ratio achieved, on average, 4.9x and in its best 9x higher results than the benchmark. The fundamental case study displayed best in the “bull market”, achieving high market prices. Its best subtest achieved returns on average 2.4x and in its best 3.2x higher than the benchmark. Its Sharpe Ratio achieved, on average, 4.4x and in its best 6.5x higher results than the benchmark.

15. ZHX2 IS A CANDIDATE GENE UNDERLYING BRAIN OXYMORPHONE CONCENTRATION AND OXYCODONE STATE-DEPENDENT LEARNING OF OPIOID REWARD IN A BALB/C REDUCED COMPLEXITY CROSS

Appearance of PEVs (Plug-in Electric Vehicles) in future transportation sector brings forward opportunities and challenges from grid perspective. Increased utilization of PEVs will result in problems such as greater total loss, unbalanced load factor, feeder congestion and voltage drop. PEVs are mobile energy storages dispersed all over the network with benefits to both owners and utilities in case of V2G (Vehicle-to-Grid) possibility. The intelligent bidirectional power flow between grid and large number of vehicles adds complexity to the system and requires operative tools to schedule V2G energy and subdue PEV impacts. In this paper, DFR (Distribution Feeder Reconfiguration) is utilized to optimally coordinate PEV operation in a stochastic framework. Uncertainty in PEVs characteristics can be due to several sources from location and time of grid connection to driving pattern and battery SoC (State-of-Charge). The proposed stochastic problem is solved with a self-adaptive evolutionary swarm algorithm based on SSO (Social Spider Optimization) algorithm. Numerical studies verify the efficacy of the proposed DFR to improve the system performance and optimal dispatch of V2G.

Optimizing triple bottom-line objectives for sustainable health-care waste collection and routing by a self-adaptive evolutionary algorithm: A case study from tehran province in Iran

The methods to collect and transport various types of medical waste are vital to the management of healthcare waste. The lack of a safe plan for the timely collection and transportation of such wastes may have an undesirable impact on the environment and public health. The present research addresses a real-life healthcare waste collection vehicle routing problem (HWCVRP) for small medical centers in Iran that produce minor amounts of waste and lack on-site facilities to treat wastes of various kinds. This problem involves social, environmental, and economic objective functions, aiming to achieve sustainable development. The social objective function is optimized based on a novel definition of risk in medical waste collection and designed to reduce public health risk by minimizing the time of waste collection from centers that produce a larger volume of more hazardous waste. Furthermore, the present paper provides a comprehensive estimate of fuel consumption in vehicles to be accurately minimized to diminish the environmental hazards involved in sustainable transportation. Also, the economic objective function is set to minimize the variable and fixed costs of transportation. A self-adaptive multi-objective evolutionary algorithm is generated with numerous effective operators to solve the model. Specific metrics are employed to compare the performance of the proposed meta-heuristic algorithm with those of multiple other evolutionary algorithms. The results reveal the effectiveness of the proposed method in reaching high-quality non-dominated solutions. Ultimately, a real-life case study is used to implement the proposed approach and to evaluate its performance.

A novel multi-surrogate multi-objective decision-making optimization algorithm in induction heating

Purpose Most of optimal design or control engineering problems present conflicting objectives that need to be simultaneously minimized or maximized. Often, however, it is a priori known that some functions have greater importance than other. This paper aims to present a novel multi-surrogate, multi-objective, decision-making (DM) optimization algorithm, which is suitable for time-consuming simulations. Its performances have been compared, on the one hand with a standard decision-making algorithm (iTDEA), on the other with a self-adaptive evolutionary algorithm (AMALGAM*). The comparison concerns numerical tests and an optimal control task in induction heating. Design/methodology/approach In particular, the algorithm makes use of surrogates (meta-models) to concentrate the field evaluations at the most promising areas of the design space. The effect of the decision-maker is instead to drive the search to given regions of the Pareto front. The synergy between surrogates and the decision-maker leads to a greater effectiveness of the optimization search. For the field analysis of the optimal control task, a coupled electromagnetic-thermal FEM model has been developed. Findings The novel algorithms outperform both iTDEA and AMALGAM* in all done tests. Practical implications The algorithm could be applied to other computationally intensive multi-objective real-life problems whenever a preference between the objectives is known. Originality/value The combination of surrogates and a decision-maker is beneficial with time-consuming multi-objective optimization problems.

Assessment of Water Resources Management Strategy under Different Evolutionary Optimization Techniques

Competitive optimization techniques have been developed to address the complexity of integrated water resources management (IWRM) modelling; however, model adaptation due to changing environments is still a challenge. In this paper we employ multi-variable techniques to increase confidence in model-driven decision-making scenarios. Here, water reservoir management was assessed using two evolutionary algorithm (EA) techniques, the epsilon-dominance-driven self-adaptive evolutionary algorithm (-DSEA) and the Borg multi-objective evolutionary algorithm (MOEA). Many objective scenarios were evaluated to manage flood risk, hydropower generation, water supply, and release sequences over three decades. Computationally, the -DSEA’s results are generally reliable, robust, effective and efficient when compared directly with the Borg MOEA but both provide decision support model outputs of value.

An evolutionary discretized Lambert approach for optimal long-range rendezvous considering impulse limit

Abstract In this paper, an approach is presented for finding the optimal long-range space rendezvous in terms of fuel and time, considering limited impulse. In this approach, the Lambert problem is expanded towards a discretized multi-impulse transfer. Taking advantage of an analytical form of multi-impulse transfer, a feasible solution that satisfies the impulse limit is calculated. Next, the obtained feasible solution is utilized as a seed for generating individuals for a hybrid self-adaptive evolutionary algorithm to minimize the total time, without violating the impulse limit while keeping the overall fuel mass the same as or less than the one associated with the analytical solution. The algorithm eliminates similar individuals and regenerates them based on a combination of Gaussian and uniform distribution of solutions from the fuel-optimal region during the optimization process. Other enhancements are also applied to the algorithm to make it auto-tuned and robust to the initial and final orbits as well as the impulse limit. Several types of the proposed algorithm are tested considering varieties of rendezvous missions. Results reveal that the approach can successfully reduce the overall transfer time in the multi-impulse transfers while minimizing the fuel mass without violating the impulse limit. Furthermore, the proposed algorithm has superior performance over standard evolutionary algorithms in terms of convergence and optimality.

An augmented self-adaptive parameter control in evolutionary computation: A case study for the berth scheduling problem

The demand for international seaborne trade has substantially increased over the last three decades and is predicted to continue increasing during the upcoming years. A marine container terminal, as an important node in supply chains, should be able to successfully cope with increasing demand volumes. Berth scheduling can significantly influence the general throughput of marine container terminals. In this study, a mixed-integer linear programming mathematical model is proposed for the berth scheduling problem, aiming to minimize the summation of waiting costs, handling costs, and late departure costs of the vessels that are to be served at a marine container terminal. An innovative Evolutionary Algorithm is designed to solve the developed mathematical model. The proposed solution algorithm relies on the augmented self-adaptive parameter control strategy, which is developed in order to effectively change the algorithmic parameters throughout the search process. Performance of the designed algorithm is evaluated against nine alternative state-of-the-art metaheuristic-based algorithms, which have been frequently used for berth scheduling in the marine container terminal operations literature. The results demonstrate that all the developed algorithms have a high level of stability and return competitive solutions at convergence. The computational experiments also prove superiority of the designed augmented self-adaptive Evolutionary Algorithm over the alternative algorithms in terms of different performance indicators.

High-Dimensional Multiple Bubbles Prediction Based on Sparse Constraints

Many bubble test methods do not have the ability to predict multiple bubbles in a high dimensional space now. Therefore, we propose a data-driven, self-adaptive evolutionary bubble prediction algorithm named WSADF. First, according to the invariance principle, we speculate that if there are inherent degrees of freedom for high dimensional time series, then comovement causality analysis (CCA) can be improved to select the decisive high dimensional time series that must reflect the prominent comovement causality. The optimization problem of the high dimensional space can be solved in the low dimensional space and maintain the inherent relationships among the time series by using CCA. Second, the learning parameters of hidden neurons have the ability of self-adaptive differential evolution. The neurons in the network are used to model the individuals' signals from the perspective of evolution. Third, a self-adaptive evolutionary neural network can be used to simulate the operation of the entire market's signals. The generalized sup augmented Dickey-Fuller test is improved to suit changing market environmental conditions. Thus, the WSADF algorithm has the ability to predict multiple bubbles in high dimensional space. An empirical application of the methodology is conducted on different types of markets (e.g., the USDCNH and CSI300 closing prices), which has successfully identified and forecasted multiple bubbles from 2015 to 2017.

A self-adaptive evolutionary algorithm for dynamic vehicle routing problems with traffic congestion

The Dynamic Vehicle Routing Problem (DVRP) is a complex variation of classical Vehicle Routing Problem (VRP). The aim of DVRP is to find a set of routes to serve multiple customers at minimal total travelling cost while the travelling time between point to point may vary during the process because of factors like traffic congestion. To effectively handle DVRP, a good algorithm should be able to adjust itself to the changes and continuously search for the best solution under dynamic environments. Because of this dynamic nature of DVRP, evolutionary algorithms (EAs) appear highly appropriate for DVRP as they search in a parallel manner with a population of solutions. Solutions scattered over the search space can better capture the dynamic changes. Solutions for new changes are not built from scratch as they can inherit problem-specific knowledge from parent solutions. However, the performance of EA is highly dependent on the utilised configuration. To address this issue, we propose a self-adaptive EA for DVRP. The proposed EA evolves a set of configurations including parameter values, operator types, combination of operators and order of operator invocation. The configurations are then encoded into DVRP solutions. So the search can use different configuration during a search process to effectively handle the dynamic changes and guide the search process towards promising areas. Two well known routing problems with traffic congestion, vehicle routing and the travelling salesman, were used to evaluate the performance of the proposed EA. The results demonstrate that under same conditions on both problems the proposed self-adaptive EA is better than standard EA and other algorithms from literature.

A Self-Adaptive Evolutionary Algorithm for the Berth Scheduling Problem: Towards Efficient Parameter Control

Since ancient times, maritime transportation has played a very important role for the global trade and economy of many countries. The volumes of all major types of cargo, which are transported by vessels, has substantially increased in recent years. Considering a rapid growth of waterborne trade, marine container terminal operators should focus on upgrading the existing terminal infrastructure and improving operations planning. This study aims to assist marine container terminal operators with improving the seaside operations and primarily focuses on the berth scheduling problem. The problem is formulated as a mixed integer linear programming model, minimizing the total weighted vessel turnaround time and the total weighted vessel late departures. A self-adaptive Evolutionary Algorithm is proposed to solve the problem, where the crossover and mutation probabilities are encoded in the chromosomes. Numerical experiments are conducted to evaluate performance of the developed solution algorithm against the alternative Evolutionary Algorithms, which rely on the deterministic parameter control, adaptive parameter control, and parameter tuning strategies, respectively. Results indicate that all the considered solution algorithms demonstrate a relatively low variability in terms of the objective function values at termination from one replication to another and can maintain the adequate population diversity. However, application of the self-adaptive parameter control strategy substantially improves the objective function values at termination without a significant impact on the computational time.

Improvement of extreme learning machine using self-adaptive evolutionary algorithm for estimating discharge capacity of sharp-crested weirs located on the end of circular channels

Weirs are used in different shapes such as rectangular, triangular and circular to control and measure the flow in open channels. To design a weir properly, determining its discharge coefficient is very important. In this study, the discharge coefficient of sharp-crested weirs located on circular channels is modeled by the self-adaptive optimization of extreme learning algorithm using the differential evolutionary algorithm (SaDE-ELM). Also, Monte Carlo simulations (MCs) are used to study the compatibilities of SaDE-ELM models. However, the k-fold cross validation method (k=5) is used to investigate the abilities of the used numerical models. According to the input parameters, four models of SaDE-ELM are introduced. Study of the numerical results shows that the superior model simulates the discharge coefficient as a function of the Froude number (Fr) and the ratio of the circular channel diameter to the weir crest height (D/P) and a relationship is provided for the superior model. The values of mean absolute relative error (MARE), root mean square error (RMSE) and correlation coefficient (R2) for the superior model are calculated 0.184, 0.002 and 0.997, respectively. However, the maximum error value for this model is less than 3%. Also, the results of the uncertainty analysis show that the superior model has an underestimated performance which its 95% prediction error interval is simulated between 0.000314 and −0.000314. In other words, the width of uncertainty band for the superior model is calculated equal to −0.000314.

A self-adaptive evolutionary algorithm for a fuzzy multi-objective hub location problem: An integration of responsiveness and social responsibility

In this paper, we present a new multi-objective model for a hub location problem under uncertainty. This model simultaneously considers economic, responsiveness and social aspects in designing a hub-and-spoke network. An M/M/c queuing system is used to calculate waiting time at each hub node and maximize responsiveness. Employment and regional development are selected as social responsibility measures in the proposed model. Furthermore, a hybrid two-phase solution method is proposed based on possibilistic programming, fuzzy multi-objective programming and an efficient algorithm, called self-adaptive differential evolution algorithm. Finally, several numerical experiments and sensitivity analyses are carried out to assess the proposed model and the solution method.

Using self-adaptive evolutionary algorithm to improve the performance of an extreme learning machine for estimating soil temperature

In this study, the self-adaptive evolutionary (SaE) agent is employed to structure the contributing elements to process the management of extreme learning machine (ELM) architecture based on a logical procedure. In fact, the SaE algorithm is utilized for possibility of enhancing the performance of the ELM to estimate daily soil temperature (ST) at 6 different depths of 5, 10, 20, 30, 50 and 100cm. In the developed SaE-ELM model, the network hidden node parameters of the ELM are optimized using SaE algorithm. The precision of the SaE-ELM is then compared with the ELM model. Daily weather data sets including minimum, maximum and average air temperatures (Tmin, Tmax and Tavg), atmospheric pressure (P) and global solar radiation (RS) collected for two Iranian stations of Bandar Abbas and Kerman with different climate conditions have been utilized. After primary evaluation, Tmin, Tmax and Tavg are considered as final inputs for the ELM and SaE-ELM models due to their high correlations with ST at all depths. The achieved results for both stations reveal that both ELM and SaE-ELM models offer desirable performance to estimate daily ST at all depths; nevertheless, a slightly more precision can be obtained by the SaE-ELM model. The performance of the ELM and SaE-ELM models are verified against genetic programming (GP) and artificial neural network (ANN) models developed in this study. For Bandar Abbass station, the obtained mean absolute bias error (MABE) and correlation coefficient (R) for the ELM model at different depths are in the range of 0.9116–1.5988°C and 0.9023–0.9840, respectively while for the SaE-ELM model they are in the range of 0.8660–1.5338°C and 0.9084–0.9893, respectively. In addition, for Kerman Station the attained MABE and RMSE for the ELM model vary from 1.6567 to 2.4233°C and 0.8661 to 0.9789, respectively while for the SaE-ELM model they vary from 1.5818 to 2.3422°C and 0.8736 to 0.9831, respectively.