An efficient multi-unit production planning strategy based on continuous variables

A metaheuristic-based efficient strategy for multi-unit production planning with unique process constraints

The extraordinary fluctuations in China's hog prices, particularly since the outbreaks of the African swine fever in 2018, have brought tremendous risks to hog producers' production planning. This study proposes a decision framework for hog price prediction and production planning. Specifically, we use six forecast combination strategies to integrate multi‐step‐ahead forecasts of the hog price generated by 11 econometric and machine learning methods. Furthermore, we design a practical production plan based on the obtained hog price forecasts to determine the number of piglets purchased and fattened pigs sent to slaughter every month. Our results show that the forecast combinations consistently generate more accurate forecasts across six prediction horizons and three accuracy measures than individual forecasting methods. No model consistently performs best among the 11 individual forecasting models. The least absolute deviation strategy is particularly well‐suited for predicting hog prices. Concerning economic performance, the cumulative returns of hog producers who use the proposed production plan are consistently higher than those who use a naïve production plan. Experimental results indicate that our decision framework is a promising and practical tool for price forecasting and production planning in the hog industry.

Evolution of heterogeneous ensembles through dynamic particle swarm optimization for video-based face recognition

In This Issue

<title>Abstract</title> Cloud computing has become an influential paradigm for facilitating effective storage, access, and sharing of medical information. In spite of its merits, issues related to data security and privacy have remained central limitations to its large-scale adaptation in the healthcare industry. In a bid to overcome such challenges, this article suggests a privacy-preserving framework to improve the privacy of healthcare data as well as for securing data sanitization and restoration based on a new hybrid algorithm called Memetic-Enhanced Glowworm Swarm Optimization with Adaptive Particle Refinement (ME-GSO-APR). The algorithm proposed combines Glowworm Swarm Optimization (GSO) for global exploration, Dynamic Particle Swarm Optimization (DPSO) for faster convergence, Memetic Algorithms (MA) for optimized local utilization, and Simulated Annealing (SA) to break free from optima. Altogether the algorithms are used to secure peak performance in data hiding as well as recovery operations. ME-GSO-APR has adaptive neighborhood scaling and improved key extraction methods that maintain data integrity without losing too much information. The performance of the proposed model is compared with benchmark optimization techniques like Artificial Bee Colony (ABC), Firefly Algorithm (FF), Glowworm Swarm Optimization (GSO), and Genetically Modified Glowworm Swarm Optimization (GMGW). Comparative study validates the superior efficiency of ME-GSO-APR in terms of statistical robustness, sanitization accuracy, restoration fidelity, convergence rate, and robustness to significant sensitivity variations between 10% to 70% as well as in the radar chart showing multi-metric performance. Made to address the rigorous demands of privacy maintenance in cloud environments of healthcare, the superiority of the developed model is established.

Biometric models are typically designed a priori using limited number of samples acquired from complex environments that change in time during operations. Therefore, these models are often poor representatives of the biometric trait to be recognized. To circumvent this problem, ensemble of classifiers can be used to integrate solutions obtained from multiple diverse classifiers. In this paper, two dynamic particle swarm optimization (DPSO) algorithms are compared for the evolution of classifier ensembles during supervised incremental learning of newly-acquired data samples in video-based face recognition. Using the properties of these population-based optimization algorithms, an incremental DPSO learning strategy for adaptive classification systems (ACSs) is employed to evolve a pool of fuzzy ARTMAP classifiers while an heterogeneous ensemble is selected through a greedy search process that seeks to maximize both performance and diversity. The performance of dynamic niching PSO (DNPSO) and speciation PSO (SPSO) algorithms is assessed in terms of classification rate, resource requirements and diversity for different incremental learning scenarios of new data blocks extracted from real-world video streams. Simulation results indicate that both DPSO algorithms can efficiently create accurate ensembles while reducing computational complexity. In addition, directly selecting representative subswarm particles to form diversified classifier ensembles significantly reduces the computational complexity.

The Artificial Bee Colony (ABC) algorithm is a swarm intelligence approach which has initially been proposed to solve optimization of mathematical test functions with a unique neighbourhood search mechanism. However, this neighbourhood search mechanism could not be directly applied to combinatorial discrete optimization problems. The employed and onlooker bees need to be equipped with problem-specific perturbative heuristics in order to tackle combinatorial discrete optimization problems. However, there is a large variety of available problem-specific heuristics. In this paper, a hyper-heuristic method, namely a Modified Choice Function (MCF), is applied such that it can regulate the selection of the neighbourhood search heuristics adopted by the employed and onlooker bees automatically. The proposed MCF-based ABC model is implemented using the Hyper-heuristic Flexible Framework (HyFlex). To demonstrate the effectiveness of the proposed model, ten Traveling Salesman Problem (TSP) instances available in HyFlex have been evaluated. The empirical results show that the proposed model is able to statistically outperform four out of five ABC variants throughout the optimization process.

Demand forecasting is essential for businesses, particularly in the fashion industry, because it predicts future demand for clothing and accessories, thereby aiding in informed production decisions. However, the continuous increase in inventory stock outages, inaccurate forecasting, and inefficient supply chain coordination in the Nigerian fashion industry offers a valid opportunity for empirical investigation. This study examines the effect of the weighted moving average (WMA) demand forecasting on production planning and resource optimization in the fashion industry. A cross-sectional survey of 105 fashion industry professionals was conducted. Data collected through the structured questionnaire were analyzed using partial least squares structural equation modeling (PLS-SEM). The study found that accurate demand forecasting using the WMA positively impacts resource optimization and production planning. Effective resource optimization measures significantly enhance production outcomes. Emphasizing adaptive forecasting methods and dynamic resource management capabilities strengthens the relationship between demand forecasting and production planning. The findings provide valuable insights for fashion industry operation managers to improve demand forecasting practices and resource management, leading to better production planning and enhanced operational efficiency.

A dynamic multiple populations particle swarm optimization algorithm based on decomposition and prediction

Optimizing the location of distributed generation units in electrical distribution networks is a well-established approach to improving grid performance, particularly for enhancing reliability and reducing operational losses. Recent large-scale blackouts in Spain and Portugal have underscored the vulnerability of power systems and the urgent need for more resilient, cost-effective, and efficient grid configurations. However, integrating distributed generation involves significant investment, operational, and maintenance costs, making optimal placement a critical challenge. Integrating optimally located distributed generation units into distribution networks using a modified artificial bee colony algorithm will substantially reduce power losses, voltage deviations, and total electricity costs compared to the conventional artificial bee colony and other state-of-the-art optimization methods. The main contributions of this work are: (1) the development of an enhanced artificial bee colony algorithm incorporating inverse population initialization and a bounded-round search strategy to improve diversity and avoid premature convergence; (2) the introduction of a chaotic cosine-based neighborhood search around the global best to accelerate convergence and enhance solution quality; and (3) the application and validation of the proposed method on IEEE 33-bus and 69-bus distribution systems, demonstrating its effectiveness in reducing power losses and improving voltage profiles. The proposed algorithm achieved reductions in total power loss of up to 82.33% for the IEEE 33-bus system and 86.6% for the IEEE 69-bus system, outperforming the basic artificial bee colony and other recent optimization techniques. The findings confirm that the modified artificial bee colony algorithm is a robust and efficient tool for distributed generation allocation, providing significant improvements in grid resilience, reliability, and operational efficiency in the face of increasing energy demands and instability risks.

Over the years, Metaheuristic algorithms have proven significant efficacy in handling None- Deterministic polynomial hard (NP-hard) combinatorial optimization problems, mainly the Traveling Salesman Problem (TSP) which has been used to evaluate and test many metaheuristics algorithms such as Ant Colony optimizations. This paper contributes a new optimization algorithm to the famous-family of swarm and evolutionary techniques named Scuba Diver Optimization Algorithm (SDOA) which is a novel population-based metaheuristic optimization algorithm inspired by the behavioural and physiological dynamics of scuba divers in the open water environments. SDOA simulates main diving factors including (depth, tank pressure/oxygen, bottom time, and ascent strategies) for keeping a balance between explorations and exploitations during the search process. SDOA novelty appears in its adaptive control of solution diversity using pressure and oxygen level thresholds, enabling robust avoidance of local optima and faster convergence. The SDOA algorithm was evaluated on a range of TSP instances from the TSPLIB library, which were categorized into three groups: Group 1, comprising instances with 1–99 cities; Group 2, including instances with 100–999 cities; and Group 3, consisting of large-scale instances with 1000 or more cities. And the results of SDOA is compared with established metaheuristics algorithms such as Ant Colony Optimization, Artificial Bee Colony, and Genetic Algorithm. The study results showing that SDOA consistently produces shorter (near optimal) tour lengths with significantly minimum computational time in larger problem sizes (Group 3). The proposed algorithm also demonstrates better scalability and stability in different initialization and population sizes. Future directions include adapting SDOA for solving other optimization problems including multi-objective or dynamic optimization contexts.

We are given a set of clients with budget constraints and a set of indivisible items. Each client is willing to buy one or more bundles of (at most) k items each (bundles can be seen as hyperedges in a k-hypergraph). If client i gets a bundle e, she pays bi,e and yields a net profit wi,e. The Hypermatching Assignment Problem (HAP) is to assign a set of pairwise disjoint bundles to clients so as to maximize the total profit while respecting the budgets. This problem has various applications in production planning and budget-constrained auctions and generalizes well-studied problems in combinatorial optimization: for example the weighted (unweighted) k-hypergraph matching problem is the special case of HAP with one client having unbounded budget and general (unit) profits; the Generalized Assignment Problem (GAP) is the special case of HAP with k = 1.Let e > 0 denote an arbitrarily small constant. In this paper we obtain the following main results:• We give a randomized (k + 1 + e) approximation algorithm for HAP, which is based on rounding the 1-round Lasserre strengthening of a novel LP. This is one of a few approximation results based on Lasserre hierarchies and our approach might be of independent interest. We remark that for weighted k-hypergraph matching no LP nor SDP relaxation is known to have integrality gap better than k − 1 + 1/k for general k [Chan and Lau, SODA'10].• For the relevant special case that one wants to maximize the total revenue (i.e., bi,e = wi,e), we present a local search based (k + O (√k))/2 approximation algorithm for k = O(1). This almost matches the best known (k + 1 + e)/2 approximation ratio by Berman [SWAT'00] for the (less general) weighted k-hypergraph matching problem.• For the unweighted k-hypergraph matching problem, we present a (k + 1 + e)/3 approximation in quasipolynomial time. This improves over the (k + 2)/3 approximation by Halldorsson [SODA'95] (also in quasipolynomial time). In particular this suggests that a 4/3 + e approximation for 3-dimensional matching might exist, whereas the currently best known polynomial-time approximation ratio is 3/2.

This paper introduces a newly developed symbiotic organism search algorithm for deal with ORPD problem. The reactive power optimization problem is essential for suitable operation and regulation in power system network. It helps operators to control the voltage limits, to curtail the real power loss in transmission lines, enhances the strength of the electrical power system to withstand and counteract voltage collapse during load variations in an electrical power system. The symbiotic organism search algorithm is one of the assuring, latest developments in the tract of Meta heuristic algorithms. The texture — animated philosophy of symbiotic organism search algorithm resembles the interactive nature among organisms in feature. Organisms in the real cosmos infrequently live in isolation due to their dependence on other organisms for livelihood and longevity. This ORPD problem is formulated by generator output voltages (continuous variable), regulating transformers and switchable VAR devices (discrete variables). The proposed symbiotic organism search algorithm is realized for IEEE-14 bus and 30-bus systems. The improved result values are compared with Evolutionary programming, Differential evolutionary algorithm, dynamic particle swarm optimization, self-adaptive real coded genetic algorithm and modified Gaussian bare bones teaching learning based optimization.

Memetic computation (MC) has emerged recently as a new paradigm of efficient algorithms for solving the hardest optimization problems. On the other hand, artificial bees colony (ABC) algorithms demonstrate good performances when solving continuous and combinatorial optimization problems. This study tries to use these technologies under the same roof. As a result, a memetic ABC (MABC) algorithm has been developed that is hybridized with two local search heuristics: the Nelder-Mead algorithm (NMA) and the random walk with direction exploitation (RWDE). The former is attended more towards exploration, while the latter more towards exploitation of the search space. The stochastic adaptation rule was employed in order to control the balancing between exploration and exploitation. This MABC algorithm was applied to a Special suite on Large Scale Continuous Global Optimization at the 2012 IEEE Congress on Evolutionary Computation. The obtained results the MABC are comparable with the results of DECC-G, DECC-G*, and MLCC.

A dynamic adaptive particle swarm optimization and genetic algorithm is presented to solve constrained engineering optimization problems. A dynamic adaptive inertia factor is introduced in the basic particle swarm optimization algorithm to balance the convergence rate and global optima search ability by adaptively adjusting searching velocity during search process. Genetic algorithm–related operators including a selection operator with time-varying selection probability, crossover operator, and n-point random mutation operator are incorporated in the particle swarm optimization algorithm to further exploit optimal solutions generated by the particle swarm optimization algorithm. These operators are used to diversify the swarm and prevent premature convergence. Tests on nine constrained mechanical engineering design optimization problems with different kinds of objective functions, constraints, and design variables in nature demonstrate the superiority of the dynamic adaptive particle swarm optimization and genetic algorithm against several other meta-heuristic algorithms in terms of solution quality, robustness, and convergence rate in most cases.