Optimal Cost Research Articles

ASSESSMENT OF THE DOMESTIC WORKWEAR MARKET

The research paper examines the development of the market for tailoring work clothes in Ukraine. The European and domestic classification of types of work clothes and the corresponding segmentation of the market are given. Special purpose clothing guarantees protection to employees from the adverse effects of the working environment, reduces the risk of industrial injuries and shows their individuality. Under modern conditions, the market of overalls is developing rapidly, taking into account the growing need for it among enterprises in the construction industry, manufacturing industry, distribution of electricity, gas and water, wholesale and retail trade, tourism, medicine, the service sector and other industries. Therefore, the analysis of the development of the overalls market requires in-depth research and is an important and urgent issue. The article provides an assessment of the current state of the workwear market in terms of changes in the number of enterprises, volumes of merchandise and sales of special purpose products. The domestic market of work clothes and personal protective equipment maintains a stable growth trend. In particular, new business entities dealing with their tailoring and implementation are being opened. They expand the range of special purpose products; improve their quality and aesthetic appearance. The article outlines the trends in the development of the workwear market in Ukraine: cost optimization for the purchase of better quality workwear; the emergence of new technologies in the production of work clothes increase the requirements for the innovative component of the clothing market; orientation of manufacturers of work clothes mainly on consumers of low and medium price segments; growth in the amount of tailoring of uniforms for the Armed Forces, the State Emergency Service, and medical workers based on military needs; increase in the number of competing companies. Based on this, the ways of further improvement of the scope of sales regarding the tailoring of work clothes are planned: to make comfortable multi-functional overalls for active life and work; to revitalize the digitization of the market for the sale of workwear; to involve nanotechnology in the production of overalls (fabrics: a generator, a cooler, which changes color under the influence of water, heat and light, which is not subject to damage when using a knife). As a result of taking these measures, companies producing special purpose clothing will increase their competitiveness both on the domestic and European markets.

Modeling Approach of Cloud 4D Printing Service Composition Optimization Based on Non-Dominated Sorting Genetic Algorithm III

The manufacturing industry is currently experiencing a paradigm shift from traditional centralized systems to distributed, personalized, and cloud-based intelligent manufacturing ecosystems. The advent of 4-dimensional (4D) printing technology introduces dynamic characteristics to manufacturing design and functionality, necessitating the effective management of these emergent 4D printing services. This study aims to bridge the gap between the static nature of existing cloud manufacturing services and the dynamic requirements imposed by 4D printing technology. We propose a comprehensive multiobjective optimization model for cloud-based 4D printing service portfolios, incorporating the intricate complexities of 4D printing services and assessing the efficacy of the Non-Dominated Sorting Genetic Algorithm III (NSGA III) in optimizing these service portfolios to meet dynamic demands. In this research, the NSGA III algorithm is employed to develop a multiobjective optimization framework for 4D printing service portfolios, addressing critical issues such as service cost, time, quality, adaptability, and overall service optimization amidst fluctuating demand and service availability. The findings indicate that the NSGA III algorithm demonstrates superior performance in terms of generational distance (GD) and inverted generational distance (IGD), particularly excelling in convergence and diversity for high-dimensional optimization problems when compared to the comparison algorithms. The study concludes that the NSGA III algorithm exhibits significant potential in optimizing the orchestration of cloud-based 4D printing service portfolios, underscoring its effectiveness in managing the complexities associated with these services. This research provides valuable insights for the advancement of intelligent cloud-based 4D printing systems, paving the way for future developments in this field.

Optimal control strategy for building HVAC systems: Satisfying flexible demand response with different value-based selection

Growing renewable energy integration leads to significant fluctuations in electricity generation. To address this challenge, market-based mechanisms for dynamic carbon emission factors and electricity prices are emerging, particularly in regions like China pursuing carbon neutrality. Buildings, with HVAC systems as the largest consumers, require flexible Demand Response (DR) strategies to balance these fluctuations while maintaining occupant comfort. This paper proposes a hierarchical control framework for building HVAC systems. It optimizes operation for various objectives (minimizing energy consumption, reducing electricity costs, and lowering carbon emissions), while ensuring thermal comfort. The framework involves three modules. First is the time-based demand allocation, which uses genetic algorithms to optimize energy use based on future cooling demands, indoor temperature, and fluctuating electricity and carbon prices. It provides building-level temperature setpoints and electricity consumption plans. Second is the spatial indoor demand adjustment, which balances overall cooling load and temperature satisfaction across individual spaces, taking into account room-specific costs and difficulty confidents for temperature adjustments. This module assigns future temperature setpoints to each space. Third is HVAC system follow-up control, which Implements the optimized setpoints for real-time control of the HVAC system. The framework’s effectiveness is verified through application to a real commercial building project. Compared to a baseline scenario, the optimal electricity cost strategy achieved a 6.5% cost reduction, and the optimal carbon emission reduction strategy achieved an 8.2% reduction. Real-world control based on carbon emission optimization resulted in an actual year-on-year carbon emission reduction of 8.7%.

Enhanced steelmaking cost optimization and real-time alloying element yield prediction: a ferroalloy model based on machine learning and linear programming

Enhanced steelmaking cost optimization and real-time alloying element yield prediction: a ferroalloy model based on machine learning and linear programming

Production-oriented approach for optimal mass-customisation of floor panel layouts in cross-laminated timber (CLT) buildings

PurposeThis study aims to develop a production-oriented approach for optimal mass-customisation of floor panel layouts in cross-laminated timber (CLT) buildings. The study enables meeting building clients’ unique floor plan requirements at an optimal cost and simultaneously enhances manufacturers’ profit by minimising material and manufacturing process waste.Design/methodology/approachThe present research uses a hybrid approach consisting of field data collection, mathematical modelling, development of a Genetic Algorithm (GA) and scenario analysis. Field data includes engineered timber production information, design data and building code requirements. The study adopts the Flexible Demand Assignment (FDA) technique to formulate a mathematical model for optimising the design of mass timber buildings and employs GA to identify optimal production solutions. Scenario analysis is performed to validate model outputs.FindingsThe proposed model successfully determines the load-bearing wall placement and building spans and specifications of floor panels that result in optimal production efficiency and the desired architectural layout. The results indicate that buildings made of a single category of thickness of panels but customised in various lengths to suit building layout are the most profitable scenario for CLT manufacturers and are a cost-effective option for clients.Originality/valueThe originality of the present study lies in its mathematical and model-driven approach towards implementing mass customisation in multi-storey buildings. The proposed model has been developed and validated based on a comprehensive set of real-world data and constraints.

An Analysis of Managing the Cloud: Obstacles and Solutions for Efficient Administration and Protection

Cloud management offers possibilities and difficulties to enterprises looking for effective management and strong data security. This essay examines the challenges associated with cloud administration and suggests workarounds for these issues. Assuring data security, upholding legal compliance, cutting expenses, and overseeing intricate multi-cloud setups are important obstacles. The use of cloud-native monitoring and governance tools, the implementation of extensive data backup and recovery plans, the use of automation for resource provisioning and administration, and the implementation of strong security measures like encryption and access restrictions are all necessary for finding solutions. Organizations may improve the security of their important data assets and expedite their cloud administration procedures by tackling these challenges with suitable solutions. Ensuring data security is a major concern in cloud administration. Organizations are concerned about data breaches, illegal access, and industry regulatory compliance when they move critical data to the cloud. Organizations need to have strong security mechanisms like identity management, access restrictions, and encryption in place to lessen these risks. Furthermore, implementing a defense-in-depth strategy that incorporates several security tiers might improve cloud environments' overall resilience. Upholding legal requirements and industry norms is another challenge for cloud managers. To secure sensitive data and uphold client confidence, businesses in regulated sectors like healthcare and finance are subject to strict compliance regulations. Adherence to frameworks like HIPAA, GDPR, and PCI DSS, as well as thorough policies and frequent audits are necessary to achieve compliance in the cloud. Organizations may minimize the risk of non-compliance penalties and expedite compliance processes by putting governance tools and compliance automation systems into place. For enterprises using cloud resources, cost optimization is another major concern. Pay-as-you-go cloud services might result in overspending and financial restrictions due to improper resource utilization.

Multi-fidelity multidisciplinary meta-model based optimization of a slender body with fins

Multidisciplinary design optimization (MDO) involving aero-elastic simulations still proves challenging for computational cost. This paper proposes a competitive cost-effective multi-fidelity MDO strategy based on two ideas. Firstly, a new multi-fidelity fluid-structure interaction model (MF-FSI) is proposed, allowing a considerable saving of the FSI simulation cost. Secondly, the optimization cost is further reduced using a meta-model approximation of the MF-FSI computations during optimization. Therefore, the MF-FSI model is validated on an experimental case of supersonic projectile fins. Then, it is combined with a meta-model-based optimization strategy (MBO) to improve the fins design. The constrained multi-objective problem aiming to maximize the lift-to-drag ratio and minimize the fin mass is solved using both high-fidelity (HFMDO) and multi-fidelity (MFMDO). The results showed that the proposed MFMDO strategy could produce the same optimal solutions as the HFMDO one with a 52% lower cost.

Exploring economic and environmental impacts of recycled aggregate concrete using particle swarm optimization algorithm

Recycled aggregate concrete (RAC) is a sustainable alternative that encounters challenges due to varying sources and processing methods. This study introduces a novel approach to optimize the mix proportions of RAC through machine learning and multi-objective optimization techniques. It identifies the key factors influencing the compressive strength of concrete, aiming to minimize costs and environmental impacts while meeting compressive strength requirements. Six machine learning models were developed based on a database of 522 samples to predict the cubic compressive strength of RAC. Among these, the XGBoost model demonstrated the highest accuracy, establishing a functional relationship between cubic compressive strength and mix proportions, achieving an R2 of 0.965 and a composite performance index of 0.081. Additionally, life cycle cost analysis and life cycle assessment were employed to evaluate both cost and environmental impacts. Using the particle swarm optimization algorithm, the optimization of strength, cost, and environmental impact was conducted, comparing RAC with conventional concrete. The significant factors affecting cubic compressive strength were identified as curing age, water-to-cement ratio, and sand content, contributing 28.6%, 20.6%, and 15.8% to the variation in strength, respectively. Cement content and the fly ash-to-cement ratio were found to significantly influence cost and environmental factors, respectively. Optimal reductions in cost and environmental impact were achieved with a recycled aggregate replacement ratio of 45%–60%, resulting in decreases of up to 18.94% and 41.72%, respectively.

RED-SEA Project: Towards a new-generation European interconnect

RED-SEA is a H2020 EuroHPC project, whose main objective is to prepare a new-generation European Interconnect, capable of powering the EU Exascale systems to come, through an economically viable and technologically efficient interconnect, leveraging European interconnect technology (BXI) associated with standard and mature technology (Ethernet), previous EU-funded initiatives, as well as open standards and compatible APIs.To achieve this objective, the RED-SEA project is being carried out around four key pillars: (i) network architecture and workload requirements-interconnects co-design – aiming at optimizing the fit with the other EuroHPC projects and with the EPI processors; (ii) development of a high-performance, low-latency, seamless bridge with Ethernet; (iii) efficient network resource management, including congestion and Quality-of-Service; and (iv) end-to-end functions implemented at the network edges.This paper presents key achievements and results at the midterm of the project for each key pillar in the way to reach the final project objective. In this regard we can highlight: (i) The definition of the network requirements and architecture as well as a list of benchmarks and applications; (ii) In addition to initially planned IPs progress, BXI3 architecture has evolved to support natively Ethernet at low level, resulting in reduced complexity, with advantages in terms of cost optimization, and power consumption; (iii) The congestion characterization of target applications and proposals to reduce this congestion by the optimization of collective communication primitives, injection throttling and adaptive routing; and (iv) the low-latency high-message rate endpoint functions and their connection with new open technologies.

Optimization and simulation of a novel multi-energy complementary heat pump system in cold regions

Solar-assisted ground source heat pump systems(SAGSHPSs) and solar- assisted air source heat pump systems (SAASHPSs) are recognized renewable energy technologies for clean and feasible heating and domestic hot water supply. However, in cold regions, the poor thermal comfort of SAASHPSs and the soil thermal imbalance of SAGSHPSs during heating periods must be resolved urgently. Therefore, to provide an efficient and stable heat source, a multi-energy complementary heat pump system(MECHPS) with seasonal heat storage was designed to meet the needs of building energy consumption. The system comprehensively utilizes solar energy and ambient air for seasonal heat storage during non-heating periods, and then directly provides heat coupled with the ground source heat pump during heating periods. The composition and control strategy of the system were introduced. The system was numerically modeled by the simulation software Transient System Simulation Program (TRNSYS), and the main MECHPS modules were experimentally verified. Additionally, to study the optimal capacity of MECHPS in terms of economy and energy savings, the Hooke-Jeeves algorithm was used for MECHPS capacity optimization with the objectives of minimising the annual cost and maximising the annual savings of standard coal. The results showed that compared with traditional SAASHPSs, the MECHPS exhibited better thermal comfort while maintaining the room temperature above 18 °C. Compared to SAGSHPSs, the MECHPS was able to achieve soil thermal balance, and its soil temperature remained largely constant after 15 years of operation. Finally, compared with the initial scheme, the annual cost reduction rate was 4.98 % under the annual cost optimization scheme and an additional 1310 kg of standard coal could be saved under the annual savings of standard coal optimization scheme. The proposed system provides a way to satisfy the building energy supply for widespread application in cold regions.

Cost-based performance optimization of a single system under a hierarchical imperfect maintenance policy

Abstract Due to the influence from external factors such as repair sites and seasonal climate change, it is difficult to restore the system performance to any intermediate level between perfect maintenance and minimal maintenance through imperfect maintenance. This article first categorizes the states of the system just before repair into three classes based on its internal degradation level: failure, major defect, and minor defect, with three corresponding thresholds. Subsequently, the corresponding repairs are carried out to dwindle the system’s degradation to different levels. In detail, if the internal degradation level of the system just before repair is recognized as minor defect, an imperfect repair, termed as type I imperfect repair, is implemented to scale down the degradation level below the minor defect threshold. If the degradation level is identified as major defect, an upgraded imperfect repair, termed as type II imperfect repair, is executed to only lower the degradation to the level between the minor defect threshold and major defect threshold. Otherwise, if the degradation before repair is beyond the failure threshold, replacement will be carried out instead of these imperfect repairs. Thus, a novel hierarchical imperfect maintenance structure is introduced. Then, a multi-variable repair cost model is constructed when considering the related costs incurred from inspection, type I imperfect repair, type II imperfect repair, replacement, and even system downtime. Finally, with the aid of the stationary law of Markov chains and the semi-regenerative process, the cost-based performance optimization with three parameters, including the inspection interval, minor defect threshold, and major defect threshold, is explored through a numerical experiment, and the closed expression of the optimal cost rate is provided.

Ideal Arrival and Service Control Model Policy Based on Fuzzy Queuing System of Uncertainty Measure

In this work, we investigate how to optimize costs for a single-server queuing system operating in a fuzzy, unpredictable environment. Constructing the overall optimal cost and cost function of the queuing system under uncertainty in the fuzzy paradigm is the aim of the inquiry. The fuzzy analysis is carried out to offer a more practical answer to the issues at hand, as opposed to the model's usual crisp responses. The model's crisp and fuzzy systems have different theoretical advances that have been determined, and the estimated costs are easily verifiable and comparable. Lastly, sensitivity analysis has also been carried out utilising numerical analysis to evaluate the theoretical conclusions of the model that is being studied.

Dynamic Programming, Neuro-Dynamic Programming, Rollout Method and Model Predictive Control to Optimal Control of a Fermentation Process

This work presents the use of dynamic programming (DP), neuro-dynamic programming (NDP), rollout algorithm (RA) and model predictive control (MPC) for optimal control of batch cultivation of the yeast Kluyveromyces marxianus var. lactis MC5. DP is a widespread method for solving problems related to optimization and optimal process control. To reduce the “curse of dimensionality”, NDP has been implemented as an alternative. In NDP, a neural network is used to solve the dimensionality problem. A simpler NDP method, called RA, is used to approximate the optimal cost through the cost of a relatively good suboptimal policy, called the baseline policy. RA is a suboptimal method for deterministic and stochastic problems that can be solved by DP. In this paper we also present off-line MPC technique for tracking of constrained fermentation systems and it overcomes the problem by off-line optimizations prior to implementation. MPC is used to provide perturbation feedback and it is developed theoretical on base a controller as an illustration how we can avoid disturbances in the process optimisation. The developed control algorithm-combined NDP and MPC ensures maximum biomass production at the end of the process and feedback during disturbances and process stability and shows that robust stability can be ensured.

Coupled partition and configuration for cohesive and self-sufficient virtual microgrids

Active Distribution Network shows promise in operating and controlling distributed generations. Based on ADN structural and electrical differences, ADN could be partitioned to reveal innate heterogeneity for better control. Virtual Microgrid works as such a partition mode that each VM serves both as a part of ADN and as an individual operating agent. To identify VM boundaries, previous research utilized community detection methods and then configured ADN based on stationary partition. In this paper, VM partition and configuration are simultaneously determined in the proposed Coupled-Configuration-Partition of Active Planning. Also, a new definition of electrical edge betweenness is proposed to depict interaction among power system buses to improve the partition algorithm. Based on this proposal, ADN is planned to be cohesive in Net-ability, Flexibility Supply Index, and Capacity Fitness, in the meantime to minimize the cost in a multi-objective optimization, iteratively in Genetic Algorithm to reach Pareto Front. Case studies are designed to denote the benefits of the proposed Coupled-Configuration-Partition of Active Planning in modularity and system cohesion intensity.

ANALISIS PENGENDALIAN FOOD COST PADA HOTEL THE ST. REGIS BALI RESORT

This research examines food cost control at The St. Regis Bali Resort uses the Committee of Sponsoring Organizations (COSO) framework which includes five main components of internal control. The study revealed that although the resort implemented a comprehensive control system, there were some gaps between implementation and ideal food cost control practices. The main findings show the existence of food cost variances caused by ineffective and inefficient controls. Several important factors that contribute to this problem include: delays in sending market lists and purchase requisitions from the kitchen to the purchasing department, receiving invoices that do not match the purchase order, and receiving scribbled notes from suppliers. This research also identified non-compliance with standard procedures in the process of purchasing and receiving food ingredients. For example, the purchasing department sometimes makes purchases outside the specified suppliers, while the goods receiving department faces price inconsistencies from suppliers. These gaps hinder the achievement of optimal food cost control targets and have the potential to affect the company's financial stability. This study emphasizes the importance of implementing a tighter and more consistent internal control system to increase the effectiveness and efficiency of food cost control at The St. Regis Bali Resort

Modelling and optimization of ATM cash-loading under stochastic demand

A set of ATMs in commercial areas were considered for business transactions. Customer demand for money requires prompt cash supply; to harmonize optimality options for ATM cash loading to sustain customers. We formulated this tis decision as a multi-stage stochastic process with Markovian demand of ATM cash among customers. The loading and operations of the ATMs were governed by cash demand and supply; with unit (loading, operational, and shortage) costs. The study considered the ATM cash demand of ten ATMs in regions within commercial centres of Kampala city. The relevant data was collected every hour throughout four months. The task focused on optimizing cash-loading decisions that minimize the operational costs of managing ATMs. The optimality of cash loading decisions were determined using the Markov decision processes. The tested model revealed optimal state-dependent options and operational costs of managing ATMs cost-effectively. As a cost optimization strategy for managers in the banking industry, the productivity of ATMs towards improved efficiency and utilization of resources for cash provision to customers emerged; supporting a larger customer base for business transactions.

Efficient microservices offloading for cost optimization in diverse MEC cloud networks

In recent years, mobile applications have proliferated across domains such as E-banking, Augmented Reality, E-Transportation, and E-Healthcare. These applications are often built using microservices, an architectural style where the application is composed of independently deployable services focusing on specific functionalities. Mobile devices cannot process these microservices locally, so traditionally, cloud-based frameworks using cost-efficient Virtual Machines (VMs) and edge servers have been used to offload these tasks. However, cloud frameworks suffer from extended boot times and high transmission overhead, while edge servers have limited computational resources. To overcome these challenges, this study introduces a Microservices Container-Based Mobile Edge Cloud Computing (MCBMEC) environment and proposes an innovative framework, Optimization Task Scheduling and Computational Offloading with Cost Awareness (OTSCOCA). This framework addresses Resource Matching, Task Sequencing, and Task Scheduling to enhance server utilization, reduce service latency, and improve service bootup times. Empirical results validate the efficacy of MCBMEC and OTSCOCA, demonstrating significant improvements in server efficiency, reduced service latency, faster service bootup times, and notable cost savings. These outcomes underscore the pivotal role of these methodologies in advancing mobile edge computing applications amidst the challenges of edge server limitations and traditional cloud-based approaches.

Antithetic multilevel Monte Carlo method for approximations of SDEs with non-globally Lipschitz continuous coefficients

In the field of computational finance, one is commonly interested in the expected value of a financial derivative whose payoff depends on the solution of stochastic differential equations (SDEs). For multi-dimensional SDEs with non-commutative diffusion coefficients in the globally Lipschitz setting, a kind of one-half order truncated Milstein-type scheme without Lévy areas was recently introduced by Giles and Szpruch (2014), which combined with the antithetic multilevel Monte Carlo (MLMC) gives the optimal overall computational cost O(ϵ−2) for the required target accuracy ϵ. Nevertheless, many nonlinear SDEs in applications have non-globally Lipschitz continuous coefficients and the corresponding theoretical guarantees for antithetic MLMC are absent in the literature. In the present work, we aim to fill the gap and analyze antithetic MLMC in a non-globally Lipschitz setting. First, we propose a family of modified Milstein-type schemes without Lévy areas to approximate SDEs with non-globally Lipschitz continuous coefficients. The expected one-half order of strong convergence is recovered in a non-globally Lipschitz setting, where even the diffusion coefficients are allowed to grow superlinearly. This then helps us to analyze the relevant variance of the multilevel estimator and the optimal computational cost is finally achieved for the antithetic MLMC. Since getting rid of the Lévy areas destroys the martingale properties of the scheme, the analysis of both the convergence rate and the desired variance becomes highly non-trivial in the non-globally Lipschitz setting. By introducing an auxiliary approximation process, we develop non-standard arguments to overcome the essential difficulties. Numerical experiments are provided to confirm the theoretical findings.

Energy efficient design of rural prefabricated buildings based on ANN and NSGA-II

The growing concern about global climate change and the rapid development of rural areas highlight the need for energy efficient building design. This study aims to establish a multi-objective optimization model based on artificial neural network (ANN) and non-dominated sorting Genetic algorithm II (NSGA-II) to optimize the energy consumption of rural prefabricated buildings. Firstly, ANN and simulation technology are used to build building models and predict building energy consumption. Then, NSGA-II algorithm was used to optimize the energy consumption and material selection of the building, and the best prefabricated building scheme was obtained. The experimental results show that the optimization efficiency of the model is about 95%, which is better than the traditional method. Specifically, compared with the NSGA-II algorithm, the model reduces energy consumption by 16.7%, operating costs by 20.0%, and carbon emissions by 20.0%. When the cost optimization, energy consumption optimization and carbon emission optimization are difficult to balance, the average optimization efficiency of the research design method is about 90% when the cost optimization rate is low, and the other optimization rates are about 85% when the cost optimization rate rises to 50%. When the cost optimization reaches the maximum, the optimization rate remains at about 80%. These results show that the proposed model is robust and efficient. This study provides a comprehensive framework for designing sustainable and energy efficient rural prefabricated buildings that can help reduce energy consumption and environmental impact. It has positive significance in the sustainable development of rural economy and provides a new way of thinking for rural construction.

Artificial intelligence-implemented prediction and cost-effective optimization of micropollutant photodegradation using g-C3N4/Bi2O3 heterojunction

Micropollutants pose a formidable hazard to human health, however, conventional water treatment fails to efficiently and economically eliminate them. The imperative need for real-time concentration monitoring of these micropollutants, vital for effective elimination and cost optimization, has proven elusive without the intervention of artificial intelligence. To bridge these critical gaps, g-C3N4/Bi2O3 heterojunction was proposed as an efficient catalyst to eliminate recalcitrate micropollutants under visible light in this study, demonstrating a 1.8-fold increase in catalytic efficiency compared to g-C3N4, and furthermore, artificial intelligence models, i.e., the proposed Long short-term memory combined with Gated residual network (ALG) and Deep Deterministic Policy Gradient (DDPG), were employed for real-time concentration prediction of micropollutants (R2 = 0.9541) and their treatment processing optimization, respectively. The predominant active species for degrading micropollutants were identified as O2•− and 1O2. We proved that HOO• serves as an intermediate to transform HO• and H2O2 generated in-situ to O2•− and 1O2, further enhancing micropollutant elimination. Compared to other models, the ALG demonstrated significantly lower root mean square error (RMSE = 0.0432) and mean absolute percentage error (MAPE = 4.8273). Weight analysis revealed that Catalyst Type (31.80 %) is the most critical factor. Finally, the proposed DDPG model dynamically adjusted its treatment strategy, aiming to discover an optimal balance among cost, reaction time, and removal efficiency. This study provides mechanistic insights into the pivotal roles of artificial intelligence in prediction and cost-effective optimization of micropollutant elimination.