Thermal Exchange Optimization Research Articles

Competition of Three Chaotic Meta-heuristic Algorithms with Physical Inspiration for Optimal Design of Truss Structures

Chaos maps create a significant improvement in the optimization results of meta-heuristic algorithms by creating a balance between the stages of exploration and exploitation. The optimization algorithms of structures are strongly non-linear and non-convex, having several local optima. Chaotic functions, while creating chaotic jumps, provide the conditions for escaping from local optima to global optima. Most of the meta-heuristic algorithms fall into the trap of local optima and suffer some kind of premature convergence. In this paper, by forming three scenarios, chaos functions can be embedded into the exploration, exploitation or both stages at the same time, and improve the results of meta-heuristic algorithms. The considered algorithms are inspired by physical phenomena, with the possibility of accessing classical and regular relations, the effectiveness of chaos functions in meta-heuristic algorithms are increased. Nowadays, chaotic algorithms are widely utilized by researchers and are considered as a challenging topic. In the present research, the effects of logistic and Gaussian chaos functions on the optimization results of three physically inspired meta-heuristic algorithms are investigated. These algorithms include Chaotic Thermal Exchange Optimization (CTEO), Chaotic Big Bang-Big Crunch (CBB-BC), and Chaotic Tug-of-War Optimization (CTWO).

Solving the Energy Management Problems Using Thermal Exchange Optimization

Solving the Energy Management Problems Using Thermal Exchange Optimization

An optimized metastructure switchable between ultra-wideband angle-insensitive absorption and transmissive polarization conversion: a theoretical study.

An optimized metastructure (MS) switchable between ultra-wideband (UWB) angle-insensitive absorption, and transmissive linear-to-circular (LTC) polarization conversion (PC), is proposed, which is a theoretical study. The structural parameters of this MS are optimized by the thermal exchange optimization algorithm. By modulating the chemical potential (μc) of the graphene-based hyperbolic metamaterial embedded in the MS, the MS can achieve UWB absorption in the absorption state and LTC PC in the transmission state. At normal incidence, in the absorption state, the MS exhibits absorptivity exceeding 0.9 within 7-15.45 THz, with a relative bandwidth (RBW) of 75.28%. By elevating μc, an UWB LTC PC is realized, with a RBW of 118.8%, achieving transmittance above 0.9 and the axial ratio below 3 dB. When prioritizing the angular stability, in the absorption state, the MS secures the angular stability of 75° for TE waves and 65° for TM ones. In the transmission state, the angular stability of PC reaches 60°, with RBW = 100.7%. Moreover, by manipulating μc, the tunability of UWB absorption is realized. The optimized MS provides a reference for designing multifunctional intelligent terahertz modulators, with promising application potential in domains like electromagnetic shielding, communication systems, and THz modulation.

Physics-inspired Metaheuristics for Construction Site Layout Planning Problem

In the construction industry, material handling plays an important role. Finding proper locations for construction facilities not only can affect the expenses, but also it can impact on the process of handling of construction materials. Therefore, in order to supply engineering demands and materials, the construction site layout planning problem (CSLP) within a short-distance transportation is considered as an NP-hard problem. Thus, the researchers are extensively using metaheuristics in order to solve the construction site layout planning problems. This study presents a comparative study of ten physics-inspired metaheuristics with regard to their efficacy in how they can address a real construction site layout problem. In this vein, two case studies are examined in terms of the site layout planning. Finally, the findings reveal that Gravitational Search Algorithm (GSA) and Thermal Exchange Optimization (TEO) have the ability to come up with better solutions, in comparison to other considered optimization algorithms.

Short-Term Electricity Load Forecasting Using a New Intelligence-Based Application

Electrical load forecasting plays a crucial role in planning and operating power plants for utility factories, as well as for policymakers seeking to devise reliable and efficient energy infrastructure. Load forecasting can be categorized into three types: long-term, mid-term, and short-term. Various models, including artificial intelligence and conventional and mixed models, can be used for short-term load forecasting. Electricity load forecasting is particularly important in countries with restructured electricity markets. The accuracy of short-term load forecasting is crucial for the efficient management of electric systems. Precise forecasting offers advantages for future projects and economic activities of power system operators. In this study, a novel integrated model for short-term load forecasting has been developed, which combines the wavelet transform decomposition (WTD) model, a radial basis function network, and the Thermal Exchange Optimization (TEO) algorithm. The performance of this model was evaluated in two diverse deregulated power markets: the Pennsylvania-New Jersey-Maryland electricity market and the Spanish electricity market. The obtained results are compared with various acceptable standard forecasting models.

A multi-objective thermal exchange optimization model for solving optimal power flow problems in hybrid power systems

This study addresses the challenges associated with optimal power flow (OPF) management in hybrid power systems incorporating diverse energy sources, particularly focusing on the unpredictability of renewable energy sources (RESs). A novel analytics approach is introduced using Multi-Objective Thermal Exchange Optimization (MOTEO). MOTEO is based on modeling energy transfer grounded on Newton’s Law of Cooling. The model integrates innovative non-dominated sorting and crowing distance strategies to effectively solve the multi-objective optimization problem. The proposed hybrid OPF model incorporates four primary types of energy resources: thermal, wind, solar, and small-hydro, offering a holistic approach to power management in hybrid systems. Our model’s practical applicability and efficiency are validated through rigorous testing on a modified IEEE 30-Bus system, benchmarked against other contemporary optimization methodologies. The results demonstrate that the MOTEO model successfully identifies optimal solutions for the multi-objective optimal power flow (MOOPF) problem while maintaining compliance with stringent power system constraints. This novel contribution enhances the field of analytics by providing a robust and efficient model to handle the complex problem of OPF in hybrid systems, thereby ensuring increased system reliability.

Multi-objective optimal design of a fuzzy adaptive robust fractional-order PID controller for a nonlinear unmanned flying system

In this study, a fuzzy adaptive robust fractional-order proportional-integral-derivative (FARFOPID) controller is introduced for stabilization of a nonlinear unmanned flying system. At first, a proportional-integral-derivative scheme improved by the fractional-order technique is employed to control the complicated dynamics of the considered system. An adaptive mechanism based on sliding surfaces is proposed to update the effective gains of the fractional-order PID controller. To improve the performance of the controller in the presence of disturbances and uncertainties, fuzzy systems are used to adjust the parameters of the sliding surfaces. The fuzzy systems, considered in this article, employ the singleton fuzzifier, product inference engine and center average defuzzifier as well as triangular-trapezoidal membership functions. Then, the multi-objective thermal exchange optimization (MOTEO), which has presented a high convergence speed and good performance for global search problems, is utilized to determine the controller parameters in such a way that control efforts and system errors would be minimized, simultaneously. Finally, simulation results clearly depict the effectiveness and efficiency of the proposed approach to handle the regarded unmanned flying system in comparison with other controllers.

Intelligent Energy-Aware Thermal Exchange Optimization with Deep Learning Model for IoT-Enabled Smart Healthcare.

In recent years, Internet of Things (IoT) and advanced sensor technologies have gained considerable interest in linking different medical devices, patients, and healthcare professionals to improve the quality of medical services in a cost-effective manner. The evolution of the smart healthcare sector has considerably enhanced patient safety, accessibility, and operational competence while minimizing the costs incurred in healthcare services. In this background, the current study develops intelligent energy-aware thermal exchange optimization with deep learning (IEA-TEODL) model for IoT-enabled smart healthcare. The aim of the proposed IEA-TOEDL technique is to group the IoT devices into clusters and make decisions in the smart healthcare sector. The proposed IEA-TEODL technique constructs clusters using the energy-aware chaotic thermal exchange optimization-based clustering (EACTEO-C) scheme. In addition, the disease diagnosis model also intends to classify the collected healthcare data as either presence or absence of the disease. To accomplish this, the proposed IEA-TODL technique involves several subprocesses such as preprocessing, K-medoid clustering-based outlier removal, multihead attention bidirectional long short-term memory (MHA-BLSTM), and weighted salp swarm algorithm (WSSA). The utilization of outlier removal and WSSA-based hyperparameter tuning process assist in achieving enhanced classification outcomes. In order to demonstrate the enhanced outcomes of the IEA-TEODL approach, a wide range of simulations was conducted against benchmark datasets. The simulation results inferred the enhanced outcomes of the IEA-TEODL technique over recent techniques under distinct evaluation metrics.

Comparison of Three Chaotic Meta-heuristic Algorithms for the Optimal Design of Truss Structures with Frequency Constraints

The main reasons for the success of using chaos maps in meta-heuristic algorithms are fast optimization of non-linear and non-convex problems. One of these cases is the control of the natural frequencies of structures to prevent the destructive and dangerous phenomenon of resonance. Natural frequencies have useful information about the dynamic behavior of structures, and by applying dynamic constraints, a significant improvement is achieved in the optimal design of structural weight. Applying frequency limits with traditional and gradient-based methods is very difficult and time-consuming, and in most cases, the calculation process stops at local optima. Recent research shows that chaos maps play a major role in escaping from local optima and reaching global optima. By combining these maps with meta- heuristic algorithms, while avoiding premature convergence, the access to global optima is accelerated and improved, and the ideal state of balance between the exploration and exploitation stages is realized. Today, chaotic algorithms are widely accepted by researchers and are considered as a challenging topic. In a recent research, six chaotic meta- heuristic algorithms have been investigated for the formation and improvement of results with the optimal design of truss structures. In this part the chaotic algorithms include Chaotic Water Evaporation Optimization (CWEO), Chaotic Tug-of-War Optimization (CTWO) and Chaotic Thermal Exchange Optimization (CTEO) are examined.

A Novel Prairie Dog-Based Meta-Heuristic Optimization Algorithm for Improved Control, Better Transient Response, and Power Quality Enhancement of Hybrid Microgrids.

The growing demand for electricity driven by population growth and industrialization is met by integrating hybrid renewable energy sources (HRESs) into the grid. HRES integration improves reliability, reduces losses, and addresses power quality issues for safe and effective microgrid (MG) operation, requiring efficient controllers. In this regard, this article proposes a prairie dog optimization (PDO) algorithm for the photovoltaic (PV)-, fuel cell (FC)-, and battery-based HRESs designed in MATLAB/Simulink architecture. The proposed PDO method optimally tunes the proportional integral (PI) controller gain parameters to achieve effective compensation of load demand and mitigation of PQ problems. The MG system has been applied to various intentional PQ issues such as swell, unbalanced load, oscillatory transient, and notch conditions to study the response of the proposed PDO controller. For evaluating the efficacy of the proposed PDO algorithm, the simulation results obtained are compared with those of earlier popular methodologies utilized in the current literature such as bee colony optimization (BCO), thermal exchange optimization, and PI techniques. A detailed analysis of the results found emphasizes the efficiency, robustness, and potential of the suggested PDO controller in significantly improving the overall system operation by minimizing the THD, improving the control of active and reactive power, enhancing the power factor, lowering the voltage deviation, and keeping the terminal voltage, DC-link voltage, grid voltage, and grid current almost constant in the event of PQ fault occurrence. As a result, the proposed PDO method paves the way for real-time employment in the MG system.

An innovative optimal 4E solar-biomass waste polygeneration system for power, methanol, and freshwater production

Modern polygeneration systems have increased the flexibility of production in energy systems. In this paper, a polygeneration system for producing power, freshwater, and methanol using solar and waste resources is defined. By using waste heat recovery in Brayton, Steam Rankine, organic Rankine, and Kalina systems, power has been produced in the proposed system. Methanol is also provided by using CO2 capture from exhaust flue gases and hydrogen produced by Proton Exchange Membrane electrolyzer. The integration of microbial fuel cells, multi-effect distillation, and reverse osmosis desalination has been used for muddy seawater recovery and freshwater production. The proposed system has been analyzed using energy, exergy, exergeoeconomic, and exergoenvironmental (4E) analyses for three biomass fuels. The Multi-Objective Dragonfly Algorithm, Multi-Objective Thermal Exchange Optimization, Multi-objective Salp Swarm Algorithm, and Multi-Objective Water Cycle Algorithm have been used for the optimization of the whole system. In the end, the studied system has been modeled hourly. In this research, machine learning has been used to facilitate modeling the desalination sector, CO2 capture sector, and methanol production sector. Also, it has played a significant role in reducing optimization run time. The modeling results show that Municipal solid waste is the most economical fuel for the study system with a payback of 4.28 years. Date palm waste has also caused fewer environmental impacts than other fuels. The comparison of the results of optimization indicates that Multi-objective Salp Swarm Algorithm is the fastest method for system optimization and can lead to 4.04% and 7.16% improvement in the system cost and environmental impact rate. In general, the energy and exergy efficiencies of the system in the optimal state are calculated as 29.25%, and 23.59%, respectively. The total optimal production of electricity, methanol, and freshwater in the whole system is calculated at 62.86 MW, 1820.78 kg/h, and 63.88 kg/s, respectively. The dynamic analysis of the proposed system also showed that the production of methanol throughout the year will be higher using Municipal solid waste fuel than other fuels.

Multi-objective optimal allocation of multiple capacitors and distributed generators considering different load models using Lichtenberg and thermal exchange optimization techniques

Integrating distributed generations (DGs) into the radial distribution system (RDS) are becoming more crucial to capture the benefits of these DGs. However, the non-optimal integration of renewable DGs and shunt capacitors may lead to several operational challenges in distribution systems, including high energy losses, poor voltage quality, reverse power flow, and lower voltage stability. Therefore, in this paper, the multi-objective optimization problem is expressed with precisely selected three conflicting goals, incorporating the reduction in both power loss and voltage deviation and improvement of voltage stability. A new index for voltage deviation called root mean square voltage is suggested. The proposed multi-objective problems are addressed using two freshly metaheuristic techniques for optimal sitting and sizing multiple SCs and renewable DGs with unity and optimally power factors into RDS, presuming several voltage-dependent load models. These optimization techniques are the multi-objective thermal exchange optimization (MOTEO) and the multi-objective Lichtenberg algorithm (MOLA), which are regarded as being physics-inspired techniques. The MOLA is inspired by the physical phenomena of lightning storms and Lichtenberg figures (LF), while the MOTEO is developed based on the concept of Newtonian cooling law. The MOLA as a hybrid algorithm differs from many in the literature since it combines the population and trajectory-based search approaches. Further, the developed methodology is implemented on the IEEE 69-bus distribution network during several optimization scenarios, such as bi- and tri-objective problems. The fetched simulation outcomes confirmed the superiority of the MOTEO algorithm in achieving accurate non-dominated solutions with fewer outliers and standard deviation among all studied metrics.

Intelligent Deep Convolutional Neural Network Based Object Detection Model for Visually Challenged People

Artificial Intelligence (AI) and Computer Vision (CV) advancements have led to many useful methodologies in recent years, particularly to help visually-challenged people. Object detection includes a variety of challenges, for example, handling multiple class images, images that get augmented when captured by a camera and so on. The test images include all these variants as well. These detection models alert them about their surroundings when they want to walk independently. This study compares four CNN-based pre-trained models: Residual Network (ResNet-50), Inception v3, Dense Convolutional Network (DenseNet-121), and SqueezeNet, predominantly used in image recognition applications. Based on the analysis performed on these test images, the study infers that Inception V3 outperformed other pre-trained models in terms of accuracy and speed. To further improve the performance of the Inception v3 model, the thermal exchange optimization (TEO) algorithm is applied to tune the hyperparameters (number of epochs, batch size, and learning rate) showing the novelty of the work. Better accuracy was achieved owing to the inclusion of an auxiliary classifier as a regularizer, hyperparameter optimizer, and factorization approach. Additionally, Inception V3 can handle images of different sizes. This makes Inception V3 the optimum model for assisting visually challenged people in real-world communication when integrated with Internet of Things (IoT)-based devices.

Modified Lévy flight distribution algorithm for global optimization and parameters estimation of modified three-diode photovoltaic model

Many real-world problems demand optimization, minimization of costs and maximization of profits, and meta-heuristic algorithms have proficiently proved their ability to achieve optimum results. This study proposes an alternative algorithm of Lévy Flight Distribution (LFD) by integrating Opposition-based learning (OBL) operator, termed LFD-OBL, for resolving intrinsic drawbacks of the canonical LFD. The proposed approach adopts OBL operator for catering search stagnancy to ensure faster convergence rate. We validate the usefulness of our approach through IEEE CEC’20 test suite, and compare results with original LFD and several other counterparts such as Moth-flame optimization, whale optimization algorithm, grasshopper optimisation algorithm, thermal exchange optimization, sine-cosine algorithm, artificial ecosystem-based optimization, Henry gas solubility optimization, and Harris’ hawks optimization. To further validate the efficiency of LFD-OBL, we apply it on parameters optimization of Solar Cell based on the Three-Diode Photovoltaic model. The qualitative and quantitative results of all the experiments performed in this study suggest superiority of the proposed method.

MOTEO: a novel multi-objective thermal exchange optimization algorithm for engineering problems

MOTEO: a novel multi-objective thermal exchange optimization algorithm for engineering problems

MOTEO: A novel physics-based multiobjective thermal exchange optimization algorithm to design truss structures

The present study investigates a novel Multiobjective Thermal Exchange Optimization (MOTEO) algorithm for truss design. Established on Newton’s law of cooling framework, this multiobjective version is revised and further improved from the single-objective version of Thermal Exchange Optimization using the nondominated sorting and crowding distancing methods. To evaluate the performance, eight structural optimization problems and five ZDT benchmark problems were examined, and the outcomes were contrasted with four state-of-the-art optimization methodologies. Minimizing the truss’s mass and maximizing nodal deflection are the two conflicting objectives considered subject to stress constraints for the 10-bar, 25-bar, 60-bar ring, 72-bar, 120-bar, 200-bar, and 942-bar truss problems. The statistical analysis is conducted on ten performance indicators results and obtained the best Pareto Fronts comparison. The findings revealed that MOTEO finds the best solutions with a shorter response time and has improved convergence, diversity, and spread behavior across Pareto Fronts.

Snake Optimizer: A novel meta-heuristic optimization algorithm

In recent years, several metaheuristic algorithms have been introduced in engineering and scientific fields to address real-life optimization problems. In this study, a novel nature-inspired metaheuristics algorithm named as Snake Optimizer (SO) is proposed to tackle a various set of optimization tasks which imitates the special mating behavior of snakes. Each snake (male/female) fights to have the best partner if the existed quantity of food is enough and the temperature is low. This study mathematically mimics and models such foraging and reproduction behaviors and patterns to present a simple and efficient optimization algorithm. To verify the validity and superiority of the proposed method, SO is tested on 29 unconstrained Congress on Evolutionary Computation (CEC) 2017 benchmark functions and four constrained real-world engineering problems. SO is compared with other 9 well-known and newly developed algorithms such as Linear population size reduction-Success-History Adaptation for Differential Evolution (L-SHADE), Ensemble Sinusoidal incorporated with L-SHADE (LSHADE-EpSin), Covariance matrix adaptation evolution strategy (CMAES), Coyote Optimization Algorithm (COA), Moth-flame Optimization, Harris Hawks Optimizer, Thermal Exchange optimization, Grasshopper Optimization Algorithm, and Whale Optimization Algorithm. Experimental results and statistical comparisons prove the effectiveness and efficiency of SO on different landscapes with respect to exploration–exploitation balance and convergence curve speed. The source code is currently available for public from: https://se.mathworks.com/matlabcentral/fileexchange/106465-snake-optimizer

TEO-MCRP: Thermal exchange optimization-based clustering routing protocol with a mobile sink for wireless sensor networks

Sensor nodes consume their energy quickly due to their continuous perception, routing, and internal circuit mechanisms in Wireless Sensor Networks (WSNs). Especially, the nodes that are close to the sink node consume their energy more quickly, causing the hot spot problem. In this direction, the development of robust clustering and adaptive mobile routing methods is extremely significant to ensure energy efficiency in WSNs. For this purpose, a new mobile clustering routing protocol based on Thermal Exchange Optimization (TEO) inspired by Newton's cooling law, called TEO-MCRP, is presented for heterogeneous WSNs. In the present protocol, two different algorithms are proposed for Cluster Head (CH) selection and Mobile Sink (MS) path detection with objective functions including independent fitness parameters. With the manner of minimizing these objective functions, effective CH selection and MS trajectory determination have been performed for each mobile round using the temperature equations in the TEO algorithm. In parallel, an MS node gathers data from all CHs and transmits all data to the Base Station (BS). The performance results strikingly illustrate that the proposed protocol is better than other algorithms. Due to minimizing packet conflicts and losses, the packet delivery rate was achieved at 99.784% in the network

Modified Seagull Optimization Algorithm based MPPT for augmented performance of Photovoltaic solar energy systems

The changing weather conditions and Partial Shading Situation (PSS) create numerous challenges in harvesting available maximum power from the solar Photovoltaic (PV) systems. The limitations of classical and bio-inspired optimization-based Maximum Power Point Tracking (MPPT) methods are incapable of extracting maximum power under PSS. Therefore, this paper presents a Modified Seagull Optimization Algorithm (MSOA) based MPPT approach by incorporating Levy Flight Mechanism (LFM) and the formula for heat exchange in Thermal Exchange Optimization (TEO) in the original Seagull Optimization Algorithm (SOA) for accurate tracking of Global Maximum Power Point (GMPP) under transient and steady state operating conditions. The MSOA increases the capability of optimization in finding the optimal value of boost DC-DC converter’s duty cycle, D, for operating at GMPP. The superiority of the presented MPPT approach is contrasted with SOA MPPT under uniform irradiation situation and partial shading situations using Matlab Simulink platform. With the presented MSOA MPPT, the settling time and percentage maximum overshoot are reduced by 0.92 times and 0.55 times in comparison to SOA MPPT with increased efficiency. The hardware results validated the simulation results proving the proposed MSOA MPPT as an efficient MPPT for solar PV systems.

Breast Cancer Diagnosis by Convolutional Neural Network and Advanced Thermal Exchange Optimization Algorithm.

A common gynecological disease in the world is breast cancer that early diagnosis of this disease can be very effective in its treatment. The use of image processing methods and pattern recognition techniques in automatic breast detection from mammographic images decreases human errors and increments the rapidity of diagnosis. In this paper, mammographic images are analyzed using image processing techniques and a pipeline structure for the diagnosis of the cancerous masses. In the first stage, the quality of mammogram images and the contrast of abnormal areas in the image are improved by using image contrast improvement and a noise decline. A method based on color space is then used for image segmentation that is followed by mathematical morphology. Then, for feature image extraction, a combined gray-level cooccurrence matrix (GLCM) and discrete wavelet transform (DWT) method is used. At last, a new optimized version of convolutional neural network (CNN) and a new improved metaheuristic, called Advanced Thermal Exchange Optimizer, are used for the classification of the features. A comparison of the simulations of the proposed technique with three different techniques from the literature applied on the MIAS mammogram database is performed to show its superiority. Results show that the accuracy of diagnosing cancer cases for the proposed method and applied on the MIAS database is 93.79%, and sensitivity and specificity are obtained 96.89% and 67.7%, respectively.