Heuristic Optimization Research Articles

Data-Driven Heuristic Optimization for Complex Large-Scale Crude Oil Operation Scheduling

This paper addresses the challenging scheduling of crude oil operations (SCOO) problem, characterized by the intricate sequencing of activities involving discrete events and continuous variables. Given the NP-Hard nature of scheduling problems due to their combinatorial complexity, this study employs a data-driven optimization approach. Initially, historical operational data relevant to the SCOO are scrutinized; however, due to data limitations, small-scale instances are solved using a mathematical programming model to generate data. Subsequently, operational solution data are processed using the Apriori algorithm, a renowned data mining technique. The insights gained are translated into heuristic rules, laying the groundwork for a novel data-driven heuristic algorithm tailored for the SCOO problem. This algorithm is then applied to a 45-day scheduling scenario, demonstrating the efficacy of the proposed approach.

Experimental-based groundwater salinization from the carbonate aquifer of eastern Saudi Arabia: Insight into machine learning coupled with meta-heuristic algorithms

Groundwater (GW) salinization of coastal aquifers has become a serious problem for attaining sustainable water resource management in Saudi Arabia and other parts of the world. Therefore, it is crucial to assess the extent of this salinization to protect and manage our water resources effectively. This research proposed real fieldwork GW samples at several locations supported with experimental based on chromatography (IC) and inductively coupled plasma mass spectrometry (ICP-MS) to analyze several GW physical, chemical, and hydro-geochemical elements. In this study, we model GW salinization with machine learning algorithms such as support vector regression, gaussian process regression, artificial neural networks, and least squares ensemble boosting regression tree. The performance of the standalone models was optimized with metaheuristic optimization-based algorithms such as fuzzy hybridized genetic algorithm (ANFIS-GA) and particle swarm optimization (ANFIS-PSO). The outcomes based on three variable input combinations were validated using several performance indicators and graphical methods. The quantitative analysis indicated that GPR-Combo1(MAE = 0.006 mg/L), Ensm- Combo2 (MAE = 0.025 mg/L), and GPR- Combo3 (MAE = 0.078 mg/L) proved merit among the standalone combinations. Where combo 1, 2, and 3 stand for model combinations derived from feature selection. The cumulative probability function (CPF) demonstrated that heuristic optimization ANFIS-GA (MAE = 0.0025 mg/L, MAPE = 0.19183) and ANFIS-PSO (MAE = 0.0018 mg/L, MAPE = 0.0723) outperformed the standalone error accuracy and served reliable approach. Both the standalone models and heuristic algorithms used for GW salinization modeling have demonstrated promising results in accurately predicting salinity. This approach could aid in effectively managing the GW resources for sustainable development.

Novel process optimization based on machine learning: A study on biohydrogen production from waste resources

The biomass poultry litter and sewage sludge co-gasification is a good thermochemical method to produce hydrogen energy meanwhile to mitigate the consumption of fossil fuels. However, the operation optimization in the complex process system is important while computationally difficult because of high nonlinearity and many first-principle constraints. To address the optimization of this biohydrogen production process, a methodology framework for achieving the optimal operations is thus presented. The complete process system is first simulated and decomposed into upstream gasification process and downstream hydrogen purification for reducing computational complexity through the thermodynamic equilibrium-based simulation. Totally 1400 data points by pairing total 15 operating conditions with a composite sustainability index objective are generated through the random sampling and data classification strategies, which are then used for the construction of the artificial neural network (ANN)-based prediction models. ANN models of two subprocesses demonstrate the satisfactory prediction accuracy with R2 value of 0.98 and 0.99, respectively, which are then integrated with mixed-integer linear programming (MILP) for the optimization of upstream process and downstream process step-by-step. The MILP problems based on the ANN models are solved with lower optimization time of 45∼100 s compared to the heuristic algorithm optimization (3–6 h) based on the thermodynamic equilibrium-based simulation. The optimal sustainability index values of two processes are 0.80 and 0.91 which are both improved compared to the existing optimization results (0.79 and 0.84). This study emphasizes the optimization potential of the integration approach of machine learning-based modelling and mathematical programming for developing the optimal waste-to-energy processes.

Ensemble variational Bayesian approximation for the inversion and uncertainty quantification of Darcy flows in heterogeneous porous media with random parameters

The inversion and uncertainty quantification of physical parameters are important for many science and engineering problems. For nonlinear parameter inversion problems of flows in hydrocarbon reservoirs, estimating the true posterior probability distribution function for the random parameter is difficult when the dimension of the parameter is relatively high. Inversion methods such as gradient-based or heuristic optimization methods searching for the maximum a posterior are generally point-estimate, while uncertainty quantification using MCMC is computationally expensive. In the current study, a new ensemble variational Bayesian approximation method is developed to estimate the posterior probability density using an ensemble of realizations regarded as a trial sample distribution. The objective is to optimize the trial sample distribution such that the evidence lower bound is maximized indicating that the distance between the trial and true posterior distribution is minimized. A subspace is built using principle component analysis based on finite samples to obtain a diagonal positive-definite covariance matrix, and ensemble-based data assimilation is used to optimize the trial distribution efficiently. Heterogeneous 2D and 3D test cases of transient single- and two-phase Darcy flows are presented for validation.

An Integer Linear Programming Model to Optimize Coding DNA Sequences By Joint Control of Transcript Indicators.

A Coding DNA Sequence (CDS) is a fraction of DNA whose nucleotides are grouped into consecutive triplets called codons, each one encoding an amino acid. Because most amino acids can be encoded by more than one codon, the same amino acid chain can be obtained by a very large number of different CDSs. These synonymous CDSs show different features that, also depending on the organism the transcript is expressed in, could affect translational efficiency and yield. The identification of optimal CDSs with respect to given transcript indicators is in general a challenging task, but it has been observed in recent literature that integer linear programming (ILP) can be a very flexible and efficient way to achieve it. In this article, we add evidence to this observation by proposing a new ILP model that simultaneously optimizes different well-grounded indicators. With this model, we efficiently find solutions that dominate those returned by six existing codon optimization heuristics.

Operation optimization and performance evaluation of a ventilated heating floor in a nearly-zero-energy building with mixed power

With the proportion of renewable energy in the construction sector increasing and the structure of energy systems becoming increasingly complex, it is crucial to optimize the operation strategy of building energy systems with thermal energy storage for improving multi-performance. However, conventional heuristic optimization algorithm exhibits low searching speed and converges slowly, which is hard for operation optimization of such systems. In this study, with a binary particle swarm optimization (BPSO) algorithm coupled with experience-based searching guiding strategy, the operation of a ventilated floor heating system in a nearly-zero-energy building was optimized . System performance under different optimization objectives and combinations, including reducing operation cost and carbon emission fee, meanwhile increasing wind power consumption and thermal comfort time, was investigated. Results show that with the experience-based accelerating strategy, the BPSO algorithm converged fast and found more reasonable solutions. In contrast, multi-objective optimization yielded better and diverse feasible solutions were found than single-objective optimization. By optimizing operating costs, wind power consumption, and environmental costs, the best comprehensive solution was obtained. The cost range of energy consumption and carbon emissions within 10 days is 19.24–22.17 yuan and 17.45–20.11 yuan, respectively. The proportion of thermal comfort time is 95.39–95.82%. However, due to high thermal insulation level, thermal comfort time under different optimization objectives showed little difference.

Vehicle vibration test platform structure design and control strategy optimization

AbstractFor the needs of vehicle vibration test platform with high precision, large load capacity and fast response, the three‐dimensional model design and analysis of vehicle vibration test platform are carried out; in order to improve the motion performance of the platform, a vibration test plat‐form control strategy combining hybrid heuristic algorithm and PID control is proposed. Based on the designed 3D model parameters, the single‐channel mathematical model of the servo‐electric cylinder is derived and a hybrid heuristic algorithm PID optimization model is established to compare and analyze the control performance of the platform with the Ziegler‐Nichols method PID. The results show that the step system overshoot is 3.80% and the dynamic performance of the system is significantly improved when the hybrid heuristic algorithm PID control is used. The simulation system model of vehicle vibration test platform control is established, and the operation results show that the platform is closer to the input signal in the spatial position change curve when the hybrid heuristic algorithm PID control is used. Its maximum displacement error is 0.09 mm, and the motion accuracy of the system is improved by 61% compared with the Ziegler‐Nichols method PID control.

Research on Flexible workshop Scheduling Based on harmony search Algorithm

The purpose of this paper is to use the harmony search algorithm to solve the scheduling problem of flexible job shop, with the goal of minimizing the maximum completion time. The issue of flexible workshop scheduling is an important research content in the field of production operation management. It involves how to rationally arrange the processing sequence of different jobs on different machines to optimize production efficiency. As a heuristic optimization algorithm, the harmony search algorithm performs well in solving complex optimization problems with its good global search ability and robustness. This paper first establishes a mathematical model of the scheduling problem of flexible job shop, and expounds in detail the basic principle and process of the harmonic search algorithm. Subsequently, we designed a scheduling strategy based on the harmony search algorithm, and by adjusting the algorithm parameters and strategies, we realized the effective optimization of the maximum completion time. The experimental results show that the algorithm can significantly reduce the maximum completion time and improve production efficiency when solving the scheduling problem of flexible work workshops. The research in this paper not only provides a new solution method for the scheduling problem of flexible job shop, but also provides a useful reference for the application of harmonic search algorithm in similar problems.

Particle Swarm Optimization (PSO) And Evolutionary Programming (EP) Technique for Optimal Placement and Sizing DG for Minimizing Loss in IEEE-30 Bus System

In recent years, most growing nations worldwide have experienced an unavoidably rising demand for electricity, which may result in a dropping of the voltage profile and a reduction in system stability, both of which have the potential to overload the power generation system significantly. One of the ways to reduce loss system network in this study is by distributed generation (DG) allocation, which the DG optimal location and sizing are the two most significant considerations for integration of DG. Improper placement and DG sizing in the power system not only result in increased total power losses but also affect the electrical system’s capability to be function properly. This paper provides a comparative analysis of two meta- heuristic optimization techniques, that is, Particle Swarm Optimization (PSO) and Evolutionary Programming (EP), to examine the optimal placement and sizing of distributed-generation (DG) for photovoltaic systems with the aim of minimizing the losses in interconnected distributed generation, IEEE-30 bus system. The objective function of this study is minimization the power loss with considered some constraints which are voltage limits and DG sizing limits are being covers in this study. The optimization issue has been solved by working with MATLAB/m-files software. The outcomes derived from the simulation results in this study demonstrated that PSO performance of two units of DG is better compared to EP algorithm. The voltage profile was improved drastically, and the power loss was reduced as lowest as 17.4486MW in the first case, 17.4368MW in the second case, and 17.4179MW in the third case.

An adaptive differential evolution algorithm with multi-strategy for solving complex optimization problem

In this paper, an adaptive differential evolution algorithm with multi-strategy, namely ESADE is proposed to solve the premature convergence and high time complexity for complex optimization problem. In the ESADE, the population is divided into several sub-populations after the fitness value of each individual is sorted. Then different mutation strategies are proposed for different populations to balance the global exploration and local optimization. Next, a new self-adaptive strategy is designed adjust parameters to avoid falling into local optimum while the convergence accuracy has reached its maximum value. And a complex airport gate allocation multi-objective optimization model with the maximum flight allocation rate, the maximum near gate allocation rate, and the maximum passenger rate at near gate is constructed, which is divided into several single-objective optimization model. Finally, the ESADE is applied solve airport gate allocation optimization model. The experiment results show that the proposed ESADE algorithm can effectively solve the complex airport gate allocation problem and achieve ideal airport gate allocation results by comparing with the current common heuristic optimization algorithms.

Strength and behavior of axially and eccentrically loaded built-up closed sections using four cold-formed steel open sections

Innovation in cold-formed steel framing systems is needed for opening flexibility and application in mid-rise buildings. Hence, this study proposes a closed built-up section using four cold-formed steel (CFS) open sections with a high load bearing capacity that potentially enables the development of high-performance cold-formed steel framing systems for these. The closed section by combining four open CFS sections using fasteners can effectively enhance the load capacity of the sections under axial loading. With a specially designed intersections gusset plate this built-up section offers more potential configurations of beam-column moment connections for CFS structures. First, a heuristic optimization was performed to identify a high-performance section based on the local and distortional buckling strengths using the finite strip method. Second, a test program was developed to investigate the load bearing capacity and failure behaviors of the optimized built-up closed section under axial and eccentric loading. Third, their load bearing capacities were compared with several other closed sections such as the rectangular hollow tube (RHS) of equal cross-sectional area or equal moment of inertia to highlight the high material efficiency. This study paved the groundwork for exploring high-performance cold-formed steel framing systems with this unique closed built-up section.

Adaptive Gradient-based Word Saliency for adversarial text attacks

Natural Language Processing (NLP) models are known vulnerable to adversarial text attacks. Various word-level attacks have been proposed to modify input words by a pre-calculated word saliency order or the heuristic optimization algorithm. However, the predefined fixed order usually leads to a low attack success ratio, and the heuristic algorithm is often inefficient due to many model queries. In this paper, an Adaptive Gradient-based Word Saliency (AGWS) is proposed to improve the query-efficiency and simultaneously preserve a high attack success ratio for the word-level adversarial text attack. Firstly, the AGWS calculates the word saliency with a one-time gradient to all words instead of iterative queries, so the query-efficiency is enhanced. Secondly, the AGWS adaptively updates the word saliency via the variable neighborhood search algorithm to avoid the fixed modification order, which is significant in improving the attack success ratio. Additionally, the AGWS collect substitutes with a hybrid sememe and synonym strategy to enlarge adversary options. Extensive experiments and ablation studies manifest that the AGWS achieves the highest or second highest attack success ratio with lowest word perturbation percentage and improves the query-efficiency compared with baselines. Besides, the AGWS also shows superiorities in adversarial training and transferability.

Multi-objective dynamic VAR planning against fault-induced delayed voltage recovery using heuristic optimization

Multi-objective dynamic VAR planning against fault-induced delayed voltage recovery using heuristic optimization

Harnessing solar power in industry: Heuristic optimisation design and transient thermal modelling of parabolic trough solar collector networks

This study presents the development of a transient model for designing and optimising parabolic trough solar thermal plants for industrial processes. The model is validated against published experimental data and other models from the literature. A heuristic optimization methodology based on Particle Swarm Optimization (PSO) to maximise the Present Value of the Life Cycle Energy Savings (PVLCES) is employed. This methodology is applied to three case studies. The results highlight the versatility of PTC (parabolic trough collector) technology in handling a wide range of temperatures. Additionally, the study reveals the optimal PTC aperture width dimensions that maximise the capture of solar thermal energy while increasing the solar fraction. Specifically: For low-temperature processes, the optimum aperture width is 5.0 m; in medium-temperature processes, the optimum aperture width increases to 5.5 m; for high-temperature applications, the optimal value is 5.8 m. Finally, the optimised networks achieve the following heat load-to-area ratios: Low-temperature applications: 0.57 kW/m²; medium-temperature applications: 0.58 kW/m²; high-temperature applications: 0.6 kW/m².

A heuristic‐based hybrid sampling method using a combination of SMOTE and ENN for imbalanced health data

AbstractHealth datasets often exhibit class imbalance, with healthy individuals being the majority class and patients being the minority class. As in many applications, machine learning methods are frequently used in the prediction and detection of diseases. The class imbalance presents a significant challenge for machine learning classifiers, particularly in their ability to accurately and effectively classify data from minority and majority classes. Therefore, data preprocessing is crucial before classifying the imbalanced data. In this study, we present GASMOTEPSO_ENN method that combines the synthetic minority oversampling technique (SMOTE) and edited nearest neighbour (ENN) algorithms using genetic algorithm (GA) and particle swarm optimization (PSO) heuristics as a preprocessing method to classify the imbalanced health datasets. In the experiments, chronic kidney disease (CKD), cerebral stroke prediction (CSP), and PIMA Indian diabetes (PID) datasets were utilized to assess the performance of the proposed method with metrics derived from the confusion matrix. The GASMOTEPSO_ENN method can classify the various diseases into different two classes of patients and healthy individuals with acceptable Matthews correlation coefficient (MCC) metric using the machine learning algorithms (Logistic regression (LR) 1.00 for CKD dataset, extreme gradient boosting (XGBoost) 0.94 for CSP dataset, and support vector machine (SVM) 0.87 for PID dataset). Moreover, the proposed method also performed well with other metrics in all datasets, and the analysis of the model results in relation to existing literature reveals that the proposed model demonstrably produces superior results.

Weighted Visibility Graph Based WiFi Indoor Positioning Method Using Heuristic Optimization

With the widespread use of wireless communication technologies and IoT applications, researchers are developing approaches that utilize WiFi signals for indoor location determination. In this study, indoor positioning process based on heuristic optimization-based methods was performed by creating weighted visibility matrices of access points based on WiFi signal strength (RSSI) values. In the proposed method, the PSO and GA approaches determine the position of the mobile user using a common fitness function based on the visibility weight matrices. The proposed method has been tested on a virtual scenario where position ranges based on RSSI ranges are determined. Both heuristic optimization methods are compared according to different criteria and the positioning process is performed with a maximum error of 3m for the GA based method and a maximum of 1.5m for the PSO based method.

Tensorial Evolutionary Optimization for Natural Image Matting

Natural image matting has garnered increasing attention in various computer vision applications. The matting problem aims to find the optimal foreground/background (F/B) color pair for each unknown pixel and thus obtain an alpha matte indicating the opacity of the foreground object. This problem is typically modeled as a large-scale pixel pair combinatorial optimization (PPCO) problem. Heuristic optimization is widely employed to tackle the PPCO problem owing to its gradient-free property and promising search ability. However, traditional heuristic methods often encode F/B solutions to a one-dimensional (1D) representation and then evolve the solutions in a 1D manner. This 1D representation destroys the intrinsic two-dimensional (2D) structure of images, where the significant spatial correlations among pixels are ignored. Moreover, the 1D representation also brings operation inefficiency. To address the above issues, this article develops a spatial-aware tensorial evolutionary image matting (TEIM) method. Specifically, the matting problem is modeled as a 2D Spatial-PPCO (S-PPCO) problem, and a global tensorial evolutionary optimizer is proposed to tackle the S-PPCO problem. The entire population is represented as a whole by a third-order tensor, in which individuals are classified into two types: F and B individuals for denoting the 2D F/B solutions, respectively. The evolution process, consisting of three tensorial evolutionary operators, is implemented based on pure tensor computation for efficiently seeking F/B solutions. The local spatial smoothness of images is also integrated into the evaluation process for obtaining a high-quality alpha matte. Experimental results compared with state-of-the-art methods validate the effectiveness of TEIM.

An Adjustable Wireless Backhaul Link Selection Algorithm for LEO-UAV-Sensor-Based Internet of Remote Things Network.

Internet of Remote Things (IoRT) networks utilize the backhaul links between unmanned aerial vehicles (UAVs) and low-earth-orbit (LEO) satellites to transfer the massive data collected by sensors. However, the backhaul links change rapidly due to the fast movement of both the UAVs and the satellites, which is different from conventional wireless networks. Additionally, due to the various requirements of IoRT multiservices, the system performance should be comprehensively considered. Thus, an adjustable wireless backhaul link selection algorithm for a LEO-UAV-sensor-based IoRT network is proposed. Firstly, an optimization model for backhaul link selection is proposed. This model uses Q, which integrates the remaining service time and capacity as the objective function. Then, based on the snapshot method, the dynamic topology is converted into the static topology and a heuristic optimization algorithm is proposed to solve the backhaul link selection problem. Finally, the proposed algorithm is compared with two traditional algorithms, i.e., maximum service time and maximum capacity algorithms. Numerical simulation results show that the proposed model can achieve better system performance, and the overload of the satellites is more balanced. The algorithm can obtain a trade-off between remaining service time and capacity by dynamically adjusting model parameters. Thus, the adjustable backhaul link selection algorithm can apply to multiservice IoRT scenarios.

Navigating legal pathways for accelerating urban energy transition: A comprehensive deep analysis of photovoltaic power prediction and policy instruments

This research proposes a navigation method that explores how to accelerate urban energy transformation through legal means from the perspective of energy law, in order to improve the accuracy of photovoltaic output power prediction in sustainable energy transformation. Firstly, a deep learning model based on adversarial autoencoder (AAE) architecture was introduced to predict photovoltaic output power according to clean environment policies. Secondly, in order to effectively fine tune the parameters of AAE, a heuristic optimization method based on the Imperial Competition Algorithm was proposed to optimize the AAE configuration to adapt to the unique characteristics of photovoltaic systems, thereby improving prediction accuracy. In addition, the study analyzed the challenges and opportunities faced by current urban energy transformation, and then proposed sustainable ways to accelerate urban energy transformation from the aspects of formulating transformation plans, promoting technological innovation, promoting green transportation, promoting building energy conservation, and developing circular economy. The synergistic effect of deep learning and heuristic optimization, combined with strict stability and sensitivity assessment, puts this research at the forefront of advancing photovoltaic output power prediction methods, which is of great significance for optimizing renewable energy utilization and grid integration.

Atomic physics-inspired atom search optimization heuristics integrated with chaotic maps for identification of electro-hydraulic actuator systems

Electro-hydraulic actuator system (EHAS) has imposed a challenge in the research community for accurate mathematical modeling and identification due to non-linearities. In this paper, autoregressive exogenous (ARX) structure is used for EHAS modeling and identification is performed by exploiting the competency of atomic physics-based chaotic atom search optimization (CASO) that adapts ten chaotic maps (Chebyshev, Circle, Gauss, Iterative, Logistic, Piecewise, Sine, Singer, Sinusoidal and Tent) in position update of atom search optimization (ASO). The fitness/merit function of the EHAS model is developed in mean-square error (MSE) sense between desired and approximated values. Simulations and analysis show that ASO with a chaotic logistic map (CASO5) performs better than the ASO and its other chaotic variants, as well as other recently introduced metaheuristics for diverse variations in the system model. Statistics based on MSE, learning plots, results of autonomous trials and average fitness analyses verify the consistency and reliability of the CASO5 for the identification of the EHAS model.