Stochastic Optimization Research Articles

A deep learning-based quantitative prediction model for the processing potentials of soybeans as soymilk raw materials

Current technologies as correlation analysis, regression analysis and classification model, exhibited various limitations in the evaluation of soybean possessing potentials, including single, vague evaluation and failure of quantitative prediction, and thereby hindering more efficient and profitable soymilk industry. To solve this problem, 54 soybean cultivars and their corresponding soymilks were subjected to chemical, textural, and sensory analyses to obtain the soybean physicochemical nature (PN) and the soymilk profit and quality attribute (PQA) datasets. A deep-learning based model was established to quantitatively predict PQA data using PN data. Through 45 rounds of training with the stochastic gradient descent optimization, 9 remaining pairs of PN and PQA data were used for model validation. Results suggested that the overall prediction performance of the model showed significant improvements through iterative training, and the trained model eventually reached satisfying predictions (|relative error| ≤ 20%, standard deviation of relative error ≤ 40%) on 78% key soymilk PQAs. Future model training using big data may facilitate better prediction on soymilk odor qualities.

Improve robustness of machine learning via efficient optimization and conformal prediction

AbstractThe advance of machine learning (ML) systems in real‐world scenarios usually expects safe deployment in high‐stake applications (e.g., medical diagnosis) for critical decision‐making process. To this end, provable robustness of ML is usually required to measure and understand how reliable the deployed ML system is and how trustworthy their predictions can be. Many studies have been done to enhance the robustness in recent years from different angles, such as variance‐regularized robust objective functions and conformal prediction (CP) for uncertainty quantification on testing data. Although these tools provably improve the robustness of ML model, there is still an inevitable gap to integrate them into an end‐to‐end deployment. For example, robust objectives usually require carefully designed optimization algorithms, while CP treats ML models as black boxes. This paper is a brief introduction to our recent research focusing on filling this gap. Specifically, for learning robust objectives, we designed sample‐efficient stochastic optimization algorithms that achieves the optimal (or faster compared to existing algorithms) convergence rates. Moreover, for CP‐based uncertainty quantification, we established a framework to analyze the expected prediction set size (smaller size means more efficiency) of CP methods in both standard and adversarial settings. This paper elaborates the key challenges and our exploration towards efficient algorithms with details of background methods, notions for robustness measure, concepts of algorithmic efficiency, our proposed algorithms and results. All of them further motivate our future research on risk‐aware ML that can be critical for AI–human collaborative systems. The future work mainly targets designing conformal robust objectives and their efficient optimization algorithms.

Simultaneous stochastic optimisation of mining complexes: Integrating progressive reclamation and waste management with contextual bandits

ABSTRACT Managing environmental performance of waste dump facilities in mining complexes is an integral part of long-term production planning. Sustainable long-term production scheduling solutions are desired to mitigate risk and return the environment to a productive post-mining state. A simultaneous stochastic optimisation framework for long-term production scheduling in mining complexes is developed that integrates waste management and progressive reclamation. The waste dump placement schedule is jointly optimised with the extraction sequence, destination policy, and stockpiling decisions in a single stochastic mathematical programming framework. This includes the timing of progressive reclamation activities in parallel with production to enhance waste dump rehabilitation. Uncertainty related to the production of acid rock drainage is quantified by simulating geochemical properties of waste and managing the blending of uncertain waste properties within the optimisation framework. With respect to the framework for simultaneous stochastic optimisation, contextual bandits are explored to improve the metaheuristic solution approach and solve the corresponding large-scale optimisation model. The framework is tested in a multi-mine copper-gold mining complex leading to improved environmental performance. Risk of acid rock drainage is decreased by 52.5% in the waste dump facilities. Reclamation planning activities for meeting environmental requirements are scheduled prior to closure. The solution approach more effectively improves the objective function with contextual bandits leading to a 24% improvement in the study presented.

Evaluation of dropwise condensation from a vertical condenser tube impregnated with semisolid lubricant

AbstractThe quest for augmenting dropwise condensation heat transfer performance has been the driving force behind the exploration of innovative techniques and approaches to fulfill the desired objective. Mostly, earlier research on dropwise condensation was devoted to study condensation from horizontal tubes and plates but, rarely, addressed dropwise condensation from vertical tubes. An interesting topic of current research in dropwise condensation is to explore the application of Slippery Liquid Infused Porous Surfaces (SLIPSs) to improve the condensation performance. The aforesaid facts are the motivation behind the topics of interest in the present study. In this study, we explore the applicability of semisolid lubricant‐impregnated porous surfaces in enhancing dropwise condensation performance of a vertical condenser tube. The experiments conducted over a wide range of subcooling (5°C ≤ ΔT ≤ 65°C) in saturated steam environment showed significant improvement in condensation heat transfer coefficient of a vertical condenser tube impregnated with semisolid lubricants when compared to bare vertical condenser tube. The highest enhancement is found to be 280% at a subcooling of 40°C. Furthermore, these surfaces proficiently sustain dropwise condensation over a period of 72 hours without compromising heat transfer performance. The devised fabrication method is simpler, more cost‐effective, and less time‐consuming than earlier techniques used for creating SLIPSs. Additionally, an approach based on numerical optimization by a stochastic global optimization technique, namely, Genetic Algorithm, is proposed to retrieve the coefficients and the exponent in the mathematical expression of overall resistance, that is being used to compute the tube‐side dropwise convection heat transfer coefficient.

Co-evolutionary traffic signal control using reinforcement learning for road networks under stochastic capacity

A co-evolutionary traffic signal control using reinforcement learning approach (CORLA) is proposed for time-varying road networks under stochastic capacity. Classic reinforcement learning based traffic signal control cannot effectively reduce traffic congestion for large-scale road networks while standard evolutionary metaheuristics often suffer from significantly high computational cost. A co-evolutionary decomposition algorithm (CODA) is proposed to improve traffic mobility for urban road networks with time-varying traffic flow. To capture time-varying spatial evolution of traffic flow inside road links, a stochastic traffic model is presented. To fully consider road users’ response, a stochastic bi-level optimization problem (SBOP) is given where road users’ route choice can be fully taken into account. To efficiently implement CORLA in a large-scale road network against high-consequence realization for stochastic capacity, a coordinated co-evolutionary two phase control (CCTPC) is proposed. Numerical experiments are performed at a real-data city road network and various sizable traffic grids. As compared to state-of-the-art traffic signal control for various traffic conditions, obtained results showed that CCTPC exhibits sufficient gain of achieving road network performance and suffers from the least computational cost in all cases.

A REVIEW ON OPTIMAL PLACEMENT AND SIZING METHODS OF DISTRIBUTION GENERATION SOURCES

This manuscript outlines various work carried out in the field of Distributed Generation (DG). Increase in power consumption and shortage in transmission capabilities are addressed by DGs. In order to maximize the potential benefits, it is imperative to place the DGs at optimal locations and the DGs should have optimal size pertaining to that location. There are several research works that are carried out on the placement and sizing of DGs. Nonetheless, the methodical principle for this issue is still unsettled. Various optimization strategies can be used to obtain the appropriate placement and sizing of distributed generation (DG) in grids. This study provides a comprehensive overview of several DG placement approaches, including stochastic fractal search algorithms, particle swarm optimization, symbiotic search algorithms, opposition-based tuneable chaotic differential evaluation, and more. The benefits and potential uses of each method are briefly covered in this study. The study sheds light on the efforts made to determine the best location and size of DGs.

Multistage Stochastic optimization for mid-term integrated generation and maintenance scheduling of cascaded hydroelectric system with renewable energy uncertainty

The uncertainties resulting from the escalating penetration of renewable energy resources pose severe challenges to the efficient operation of modern power systems. Hydroelectricity is characterized by its flexibility, controllability, and reliability, and thus becomes one of the most ideal energy resources to hedge against such uncertainties. This paper studies the mid-term integrated generation and maintenance scheduling of a cascaded hydroelectric system (CHS) consisting of multiple cascaded reservoirs and hydroelectric units. To precisely describe the mid-term water regulation policies, the hydraulic coupling relationship and water-energy nexus of CHS are incorporated into the proposed optimization model. The uncertainties of natural water inflow and the power outputs of wind/solar energy generation are taken into consideration and captured via a stochastic process modeled by a scenario tree. A multistage stochastic optimization (MSO) approach is developed to coordinate the complementary operations of multiple energy resources, by optimizing the mid-term water resource management, generation scheduling, and maintenance scheduling of CHS. The proposed MSO model is formulated as a large-scale mixed-integer linear program that presents significant computational intractability. To address this issue, a tailored Benders decomposition algorithm is developed. Two real-world case studies are conducted to demonstrate the capability and characteristics of the proposed model and algorithm. The computational results show that the proposed MSO model can exploit the flexibility of hydroelectricity to efficiently respond to variable wind and solar power, and reserve water resources for the generation in peak months to reduce the consumption of fossil fuel. The proposed solution approach also exhibits promising computational efficiency when handling large-scale models.

Evolutionary Search for Stochastic Optimization with Binary Choice Relations Under Fuzzy Modeling

Evolutionary Search for Stochastic Optimization with Binary Choice Relations Under Fuzzy Modeling

Modelling the developmental path in the acquisition of /l/-final irregular plurals by Portuguese children

ABSTRACT Previous empirical research has shown that Portuguese children aged 4;0 to 6;0 are sensitive to the quality of stem-final vowels when acquiring the irregular plural forms of /l/-final words (acquisition order: plurals of /al, ɛl, ɔl, ul/ > plurals of /il/). This study presents a formal account of this emergent pattern. We first construct an initial-state grammar that arguably instantiates Portuguese children’s grammatical knowledge at the onset of morpho-phonological acquisition. We then simulate morpho-phonological learning using two constraint-based models (Stochastic Optimality Theory and Noisy Harmonic Grammar) and their associated Gradual Learning Algorithm. The results of our learning simulations corroborate the experimental data, showing that the plural form of /il/-final words takes longer to master than that of other /l/-final words. In addition to replicating the empirical results, the learning simulation reveals two important implications. First, the raw frequency of individual forms cannot account for the attested patterns, suggesting that the input frequency is mediated by some principles of grammatical learning. Second, Harmonic Grammar outperforms Optimality Theory in simulating real acquisition data. Through the additive constraint interaction, Harmonic-Grammar learning is more restrictive, avoiding the generation of unobserved data in the course of morpho-phonological acquisition.

Data-driven Wasserstein distributionally robust dual-sourcing inventory model under uncertain demand

Dual-sourcing inventory management, which is aimed at replenishing inventory through two supply sources, has been extensively incorporated across various industries as it can mitigate supply chain related operational risks. Given the practical relevance of this framework, many dual-sourcing inventory models based on stochastic and robust optimization approaches have been developed. However, these approaches encounter challenges such as the curse of dimensionality or solution conservativeness. In this study, we developed a data-driven distributionally robust optimization model for dual-sourcing inventory management under uncertain demand conditions, in which partial information regarding the distribution of the uncertain demand is available. A tractable model was constructed to solve the problem, and an optimal solution was derived in a closed-form expression. Numerical experiments were conducted to evaluate the performance of the proposed model in comparison with benchmark models in terms of the order-, stock-, and rolling-horizon-related parameters and demand distributions. The results demonstrated the benefit of adopting the dual-sourcing strategy in inventory management based on the distributionally robust optimization approach. In addition, the proposed model outperformed the benchmark models in terms of mitigating the bullwhip effect.

Multi-time-scale voltage control of the distribution network with energy storage equipped soft open points

The integration of distributed generation (DG) units into distribution networks (DNs) has brought about several operational challenges, including voltage issues and increased power loss. Energy storage equipped soft open points (E-SOPs) can accurately and flexibly control active and reactive power flows to address these problems. Additionally, the photovoltaic (PV) inverter and the network reconfiguration (NR) play a significant role in voltage control by adjusting the reactive power and the topology of the DN, respectively. However, due to differences in response times, there is a lack of systematic coordination between NR and the inverters of the E-SOP and PV. This paper proposes a multi-time-scale voltage control model that includes day-ahead NR scheduling, inter-day droop control optimization of the PV and E-SOP, and real-time local droop control. Considering the uncertainties of renewable DG outputs and loads, a robust optimization method is used in the day-ahead stage to obtain a reliable network structure. Then, with more accurate intra-day predictions, a stochastic optimization method is used to obtain the optimal state-of-charge interval, aiming to provide a flexible regulation range for battery energy storage to cope with the power fluctuations during the real-time stage. In addition, to address the intra-day voltage control model with bilinear constraints of the droop control function, a particle swarm optimization method is used. The results are verified on a 33-bus DN system through comparative analyses, showing effective performance.

BM-RCWTSG: An integrated matching framework for electric vehicle ride-hailing services under stochastic guidance

Electric vehicles (EVs) are playing an increasingly vital role in sustainable ride-hailing services, primarily due to their potential to reduce carbon emissions and enhance environmental well-being. A core service of ride-hailing platforms is to match riders with nearby drivers within a short time window. In this mandate, it is crucial to ensure a high matching rate and low rider waiting time since these are key indicators of customer satisfaction and the platform’s operational effectiveness. However, existing matching mechanisms in the literature failed to consider important aspects related to EVs, including the range limit, charging detour time, and charging waiting time. These factors can significantly affect the system matching rate, rider waiting time, and vehicle utilization rate. To address the new challenges of the increased adoption of EVs in ride-hailing services, we propose a data-driven stochastic optimization framework for EV ride-hailing matching. The proposed framework integrates two stochastic optimization models, namely the stochastic guidance (SG) model and the EV matching (EVM) model. The SG model optimizes EV relocation and improves the system matching rate by proactively guiding idle EVs to the designated regions based on probabilistic rider demand forecasting. The EVM model utilizes the relocated EVs and current rider demands to provide the optimal matching solution that minimizes the overall cost associated with rider waiting time, EV charging waiting time, and charging detours. We conduct experimental validation of this approach using two real-world data sets from New York City. Comparative results suggest that by utilizing the proposed framework, the matching rate can be increased up to 22.9%, and the rider and EV waiting times can be reduced up to 14.9% and 73.6%, respectively, compared to the benchmark models.

Multi-objective reinforcement learning-based approach for pressurized water reactor optimization

A novel method, the Pareto Envelope Augmented with Reinforcement Learning (PEARL), has been developed to address the challenges posed by multi-objective problems, particularly in the field of engineering where the evaluation of candidate solutions can be time-consuming. PEARL distinguishes itself from traditional policy-based multi-objective Reinforcement Learning methods by learning a single policy, eliminating the need for multiple neural networks to independently solve simpler sub-problems. Several versions inspired from deep learning and evolutionary techniques have been crafted, catering to both unconstrained and constrained problem domains. Curriculum Learning (CL) is harnessed to effectively manage constraints in these versions. PEARL’s performance is first evaluated on classical multi-objective benchmarks. Additionally, it is tested on two practical PWR core Loading Pattern (LP) optimization problems to showcase its real-world applicability. The first problem involves optimizing the Cycle length (LC) and the rod-integrated peaking factor (FΔh) as the primary objectives, while the second problem incorporates the mean average enrichment as an additional objective. Furthermore, PEARL addresses three types of constraints related to boron concentration (Cb), peak pin burnup (Bumax), and peak pin power (Fq). The results are systematically compared against conventional approaches from stochastic optimization. Notably, PEARL, specifically the PEAL-NdS ( ▪ ) variant, efficiently uncovers a Pareto front without necessitating additional efforts from the algorithm designer, as opposed to a single optimization with scaled objectives. It also outperforms the classical approach across multiple performance metrics, including the Hyper-volume. Future works will encompass a sensitivity analysis of hyper-parameters with statistical analysis to optimize the application of PEARL and extend it to more intricate problems.

Designing an optimal multi-energy system with fast charging and hydrogen refueling station under uncertainties

As the demand for battery-powered and hydrogen-based electric vehicles continues to rise, the need for integrated charging and refueling systems with energy systems becomes more critical. Therefore, it is crucial to consider the stations serving diverse vehicle users during the system design process. This paper presents an optimal sizing strategy for a multi-energy system that covers clean energy sources and two energy storage technologies under the presence of a fast-charging station and a hydrogen refueling station for various types of car users. For the considered system, the optimal sizing problem aims to minimize the loss of power supply probability (LPSP) and annualized total life cycle cost (TLCC) through a two-stage stochastic programming-based multi-objective optimization approach. Using a scenario-based approach, the study considers the uncertainties associated with renewables, homeowner’s vehicle demands, and energy demands from homes and stations. Different cases are produced to evaluate the impacts of the different stations with the availability of various electric vehicle profiles under different levels of reliability. The TLCC decreases if LPSP increases in each case. Also, the cost of installing a fast charging station is significantly lower than that of a hydrogen refueling station for all LPSP limits. Moreover, the overall cost of the system design is at its lowest when homeowners’ vehicles provide vehicle-to-grid services. It is worth noting that when the station loads which come from the customers’ vehicle increase by 10%, the TLCC increases by 1.19%. Additionally, the revenue from hydrogen refueling station is approximately 70% less than the fast charging station.

Development of a mathematical model for investigation of hollow-fiber membrane contactor for membrane distillation desalination

This research investigates the predictive modeling of a dataset containing parameters denoted by r(m), z(m), and T(K) which is temperature. The considered process is a membrane distillation (MD) for separation of compounds based on temperature gradient. A membrane contactor is used for the process, and the computations are performed in the context of computational fluid dynamics (CFD) and machine learning. The dataset, which is generated by CFD modeling and encompasses over 5,000 data points, is analyzed using three distinct regression models: Support Vector Machine (SVM), Deep Neural Network (DNN), and Kernel Ridge Regression (KRR). Hyperparameter tuning is performed employing the Stochastic Fractal Search (SFS) algorithm. Our findings unraveled the nuanced intricacies of each model's performance, gauged through a comprehensive set of metrics. The RMSE, MAPE, and R2 score collectively offer a robust evaluation framework. The Deep Neural Network (DNN) exhibits a compelling RMSE of 7.7001E-01, a remarkably low MAPE of 2.05131E-03, and an impressive R2 score of 0.97054. Meanwhile, the Support Vector Machine (SVM) showcases a notable RMSE of 1.7215E-01, a minimal MAPE of 2.90820E-04, and a remarkably high R2 score of 0.99839. On the other hand, the Kernel Ridge Regression (KRR) model presents an RMSE of 1.3588E + 00, a MAPE of 2.63550E-03, and an R2 score of 0.90042.

Distributed gradient-free and projection-free algorithm for stochastic constrained optimization

Distributed stochastic zeroth-order optimization (DSZO), in which the objective function is allocated over multiple agents and the derivative of cost functions is unavailable, arises frequently in large-scale machine learning and reinforcement learning. This paper introduces a distributed stochastic algorithm for DSZO in a projection-free and gradient-free manner via the Frank-Wolfe framework and the stochastic zeroth-order oracle (SZO). Such a scheme is particularly useful in large-scale constrained optimization problems where calculating gradients or projection operators is impractical, costly, or when the objective function is not differentiable everywhere. Specifically, the proposed algorithm, enhanced by recursive momentum and gradient tracking techniques, guarantees convergence with just a single batch per iteration. This significant improvement over existing algorithms substantially lowers the computational complexity. Under mild conditions, we prove that the complexity bounds on SZO of the proposed algorithm are O(n/ϵ2)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\mathcal{O}(n/\\epsilon ^{2})$\\end{document} and O(n(21ϵ))\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$\\mathcal{O}(n(2^{\\frac{1}{\\epsilon}}))$\\end{document} for convex and nonconvex cases, respectively. The efficacy of the algorithm is verified on black-box binary classification problems against several competing alternatives.

Multi time scale optimal dispatch of distribution network considering load demand response

Considering the uncertainty of wind power output and load as well as the differences in the operating characteristics of various adjustable resources over different time scales, a multitime scale optimal dispatching model based on stochastic optimization and distributed robust optimization is designed for the distribution network. Firstly, the demand response of the user load side is divided into price-based load and incentive-based load, and price elasticity coefficients are introduced to describe it. Then, with the minimum operation cost of the distribution network, the loss cost, and the penalty cost of abandoned wind as the objective function, various active and reactive regulation elements as well as the system power flow formulas are taken as constraints. In the day-ahead and real-time stages, a stochastic optimization method based on scenarios and opportunity constraints is introduced. In the intraday stage, a self-regressive sliding window prediction model is used to predict wind power and load processing, and a Wasserstein distance-based prediction error uncertainty set is established to establish an intraday distributed robust rolling optimization model. The improved IEEE 33-node case is used for simulation verification, and the results show that the model can effectively reduce system costs and improve system operation stability.

Stochastic optimization scheduling of wind-photovoltaic-storage-hydrogen-water system in independent island zero-carbon microgrid

A stochastic optimal scheduling strategy is being proposed for a wind-photovoltaic-storage-hydrogen-water system within a zero-carbon microgrid for independent islands. This strategy is aimed at addressing the challenge of sustainable energy resource supply prevalent in traditional islands, while also considering the demand response of seawater desalination. In order to harness the clean, low-carbon, and high-efficiency characteristics of hydrogen, an electrolytic water hydrogen production system is integrated into the power system to utilize wind power generation. The desalination equipment is regarded as a controllable load within the system. It is combined with a demand response strategy to maximize the full utilization of the desalination equipment for consuming wind power on the island. Furthermore, a two-stage stochastic optimization method is being employed to handle uncertainties related to wind and photovoltaic generation. The objective is to minimize the system’s operating cost. To solve this optimization problem, the commercial solver CPLEX is being utilized. Through comparative analysis across different scenarios, simulation results indicate that the proposed strategy effectively dissipates uncertainties in wind scenarios while concurrently reducing the overall system operation cost. This approach comprehensively considers the system’s economics, thus demonstrating its potential to efficiently promote wind power consumption.

Bayesian Estimation of Inverted Beta Mixture Models With Extended Stochastic Variational Inference for Positive Vector Classification.

The finite inverted beta mixture model (IBMM) has been proven to be efficient in modeling positive vectors. Under the traditional variational inference framework, the critical challenge in Bayesian estimation of the IBMM is that the computational cost of performing inference with large datasets is prohibitively expensive, which often limits the use of Bayesian approaches to small datasets. An efficient alternative provided by the recently proposed stochastic variational inference (SVI) framework allows for efficient inference on large datasets. Nevertheless, when using the SVI framework to address the non-Gaussian statistical models, the evidence lower bound (ELBO) cannot be explicitly calculated due to the intractable moment computation. Therefore, the algorithm under the SVI framework cannot directly use stochastic optimization to optimize the ELBO, and an analytically tractable solution cannot be derived. To address this problem, we propose an extended version of the SVI framework with more flexibility, namely, the extended SVI (ESVI) framework. This framework can be used in many non-Gaussian statistical models. First, some approximation strategies are applied to further lower the ELBO to avoid intractable moment calculations. Then, stochastic optimization with noisy natural gradients is used to optimize the lower bound. The excellent performance and effectiveness of the proposed method are verified in real data evaluation.

Predictive analysis of concrete slump using a stochastic search-consolidated neural network

Attaining a dependable measurement of concrete slump is crucial as it is a valuable indication of concrete workability. On the other hand, complexities associated with costly traditional approaches have driven engineers to use indirect efficient models such as metaheuristic-based machine learning for approximating the slump. While the literature shows promising application of some metaheuristic techniques for this purpose, the large variety of these algorithms calls for evaluating the most capable ones to keep the solution updated. Stochastic fractal search (SFS) is one of the most powerful optimization algorithms in the literature that has not received appropriate attention in analyzing concrete mechanical parameters. In the present research, a multi-layer perceptron neural network (NN-MLP), is enhanced using the SFS. The proposed SFS-NN-MLP model aims to predict the slump based on the amount of ingredients in the mixture, as well as the curing age of specimens. Accuracy assessment revealed that the proposed model can deal with the assigned task with excellent accuracy. It indicates that the SFS could properly tune the parameters required for training the NN-MLP, and consequently, the trained network could reliably calculate the slump of specimens that were not analyzed before. For comparative validation, the SFS was replaced with two similar optimizers, namely elephant herding optimization algorithm (EHO) and slime mould algorithm (SMA). Based on the calculated mean square errors of 5.6526, 6.1129, and 7.3561 along with mean absolute errors of 4.6657, 5.0078, and 6.3066, as well as the percentage-Pearson correlation coefficients of 78.06 %, 73.95 %, and 58.11 %, respectively for the SFS-NN-MLP, EHO–NN–MLP, and SMA–NN–MLP, it was shown that the SFS-NN-MLP is the most accurate predictor. Hereupon, the SFS-NN-MLP model is recommended to be effectively used for obtaining a cost-efficient approximation of concrete slump in real-world projects.