Search results

A cross-domain intelligent software-defined network (SDN) routing method based on a proposed multiagent deep reinforcement learning (MDRL) method is developed.

First, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between the root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to acquire global network state information in real time. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a network traffic state prediction mechanism is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time.

Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and open shortest path first (OSPF) routing methods.

Message transmission and message synchronization for multicontroller interdomain routing in SDN have long adaptation times and slow convergence speeds, coupled with the shortcomings of traditional interdomain routing methods, such as cumbersome configuration and inflexible acquisition of network state information. These drawbacks make it difficult to obtain global state information about the network, and the optimal routing decision cannot be made in real time, affecting network performance. This paper proposes a cross-domain intelligent SDN routing method based on a proposed MDRL method. First, the network is divided into multiple subdomains managed by multiple local controllers, and the state information of each subdomain is flexibly obtained by the designed SDN multithreaded network measurement mechanism. Then, a cooperative communication module is designed to realize message transmission and message synchronization between root and local controllers, and socket technology is used to ensure the reliability and stability of message transmission between multiple controllers to realize the real-time acquisition of global network state information. Finally, after the optimal intradomain and interdomain routing paths are adaptively generated by the agents in the root and local controllers, a prediction mechanism for the network traffic state is designed to improve awareness of the cross-domain intelligent routing method and enable the generation of the optimal routing paths in the global network in real time. Experimental results show that the proposed cross-domain intelligent routing method can significantly improve the network throughput and reduce the network delay and packet loss rate compared to those of the Dijkstra and OSPF routing methods.

This study aims to enhance an enterprise’s private cloud services by optimally determining the ownership of cloud computing resources and responsibility for maintenance and operations. The core objective is to identify the most cost-effective private cloud deployment model at the intersection of technology and business considerations.

This study evaluates three ownership and responsibility models, each encompassing decisions related to candidate data center locations, resource provisioning, and demand placements. Drawing from the cloud computing literature, these models are referred to as deployment models. The research formulates a private cloud deployment model selection problem and introduces an established Lagrangian-relaxation-based optimization approach, combined with a novel greedy relieving-pooling heuristic, to facilitate model selection.

This study identifies the optimal deployment model for a representative instance using real test-bed data from the US, demonstrating the private cloud deployment model selection problem. Various numerical examples are analyzed to explore the influence of environmental parameters. Generally, the virtual PC model is optimal for low demand arrival rates and resource requirements, while the on-premises PC model is preferable for higher values of these parameters. Additionally, the virtual PC model is found to be optimal when enroute latency coefficients are large.

This study contributes to the literature by formulating an optimization problem that integrates performance, financial, and assurance metrics for enterprises. The introduction of a solution approach enables enterprises to make informed decisions regarding ownership and responsibility design. The study effectively bridges the gap between academic research and industry demands from a business perspective.

This paper aims to propose an incremental graph indexing method based on probabilistic inferences in Bayesian network (BN) for approximate nearest neighbor search (ANNS) that adds unindexed queries into the graph index incrementally.

This paper first uses the attention mechanism based graph convolutional network to embed a social network into the low-dimensional vector space, which could improve the efficiency of graph index construction. To add the unindexed queries into the graph index incrementally, this study proposes to learn the rule-based BN from social interactions. Thus, the dependency relations of unindexed queries and their neighbors are represented, and the probabilistic inferences in BN are then performed.

Experimental results demonstrate that the proposed method improves the search precision by at least 5% and search efficiency by 10% compared to the state-of-the-art methods.

This paper proposes a novel method to construct the incremental graph index based on probabilistic inferences in BN, such that both indexed and unindexed queries in ANNS could be addressed efficiently.

This study aims to minimize the transportation-related cost in distribution while utilizing a heterogeneous fixed fleet to deliver distinct demand at different geographical locations with a proper workload balancing approach. An increased cost in distribution is a major problem for many companies due to the absence of efficient planning methods to overcome operational challenges in distinct distribution networks. The problem addressed in this study is to minimize the transportation-related cost in distribution while using a heterogeneous fixed fleet to deliver distinct demand at different geographical locations with a proper workload balancing approach which has not gained the adequate attention in the literature.

This study formulated the transportation problem as a vehicle routing problem with a heterogeneous fixed fleet and workload balancing, which is a combinatorial optimization problem of the NP-hard category. The model was solved using both the simulated annealing and a genetic algorithm (GA) adopting distinct local search operators. A greedy approach has been used in generating an initial solution for both algorithms. The paired t-test has been used in selecting the best algorithm. Through a number of scenarios, the baseline conditions of the problem were further tested investigating the alternative fleet compositions of the heterogeneous fleet. Results were analyzed using analysis of variance (ANOVA) and Hsu’s MCB methods to identify the best scenario.

The solutions generated by both algorithms were subjected to the t-test, and the results revealed that the GA outperformed in solution quality in planning a heterogeneous fleet for distribution with load balancing. Through a number of scenarios, the baseline conditions of the problem were further tested investigating the alternative fleet utilization with different compositions of the heterogeneous fleet. Results were analyzed using ANOVA and Hsu’s MCB method and found that removing the lowest capacities trucks enhances the average vehicle utilization with reduced travel distance.

The developed model has considered both planning of heterogeneous fleet and the requirement of work load balancing which are very common industry needs, however, have not been addressed adequately either individually or collectively in the literature. The adopted solution methodologies to solve the NP-hard distribution problem consist of metaheuristics, statistical analysis and scenario analysis are another significant contribution. The planning of distribution operations not only addresses operational-level decision, through a scenario analysis, but also strategic-level decision has also been considered.

The planning of distribution operations not only addresses operational-level decisions, but also strategic-level decisions conducting a scenario analysis.

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.

Gillette’s historically successful “razor and blade” business model (RBM) has been a promising benchmark for multiple businesses across diverse industries worldwide in the past several decades. The extant literature deals with very few nuances of this business model notwithstanding the fact that there are several variants of this business model being put to practical use by firms in diverse industries in grossly metaphorically equivalent situations.

This study adopts the 2 × 2 truth table framework from the domains of mathematical logic and combinatorics in fleshing out all possible (four logical possibilities) variants of the razor and blade business model for further analysis. This application presents four mutually exclusive yet collectively exhaustive possibilities on any chosen dimension. Two major dimensions (viz., provision of subsidy and intra- or extra-firm involvement in the making of razors or blades or both) form part of the discussion in this paper. In addition, this study synthesizes and streamlines entrepreneurial wisdom from multiple intra-industry and inter-industry benchmarks in terms of real-time firms explicitly or implicitly adopting several variants of the RBM that suit their unique context and idiosyncratic trajectory of evolution in situations that are grossly reflective of the metaphorically equivalent scenario of razor and recurrent blades. Inductive method of research is carried out with real-time cases from diverse industries with a pivotally common pattern of razor and blade model in some form or the other.

Several new variants of the razor and blade model (much beyond what the extant literature explicitly projects) have been discovered from the multiple metaphorically equivalent cases of RBM across industries. All of these expand the portfolio of options that relevant entrepreneurial firms can explore and exploit the best possible option chosen from them, given their unique context and idiosyncratic trajectory of growth.

This study has enriched the literature by presenting and analyzing a more inclusive or perhaps comprehensive palette of explicit choices in the form of several variants of the RBM for the relevant entrepreneurial firms to choose from. Future research can undertake the task of comparing these variants of RBM with those of upcoming servitization business models such as guaranteed availability, subscription and performance-based contracting and exploring the prospects of diverse combinations.

Smart entrepreneurial firms identify and adopt inspiring benchmarks (like razor and blade model whenever appropriate) duly tweaked and blended into a gestalt benchmark for optimal profits and attractive market shares. They target diverse market segments for tied-goods with different variants or combinations of the relevant benchmarks in the form of variegated customer value propositions (CVPs) that have unique and enticing appeal to the respective market segments.

Value-sensitive customers on the rise globally choose the option that best suits them from among multiple alternatives offered by competing firms in the market. As long as the ratio of utility to price of such an offer is among the highest, even a no-frills CVP may be most appealing to one market segment while a plush CVP may be tempting to yet another market segment simultaneously. While professional business firms embrace resource leverage practices consciously, amateur customers do so subconsciously. Each party subliminally desires to have the maximum bang-to-buck ratio as the optimal return on investment, given their priorities ceteris paribus.

Prior studies on the RBM have explicitly captured only a few variants of the razor and blade model. This study is perhaps the first of its kind that ferrets out many other variants (more than ten) of the razor and blade model with due simplification and exemplification, justification and demystification.

Prefabricated building has been widely applied in the construction industry all over the world, which can significantly reduce labor consumption and improve construction efficiency compared with conventional approaches. During the construction of prefabricated buildings, the overall efficiency largely depends on the lifting sequence and path of each prefabricated component. To improve the efficiency and safety of the lifting process, this study proposes a framework for automatically optimizing the lifting path of prefabricated building components using building information modeling (BIM), improved 3D-A* and a physic-informed genetic algorithm (GA).

Firstly, the industry foundation class (IFC) schema for prefabricated buildings is established to enrich the semantic information of BIM. After extracting corresponding component attributes from BIM, the models of typical prefabricated components and their slings are simplified. Further, the slings and elements’ rotations are considered to build a safety bounding box. Secondly, an efficient 3D-A* is proposed for element path planning by integrating both safety factors and variable step size. Finally, an efficient GA is designed to obtain the optimal lifting sequence that satisfies physical constraints.

The proposed optimization framework is validated in a physics engine with a pilot project, which enables better understanding. The results show that the framework can intuitively and automatically generate the optimal lifting path for each type of prefabricated building component. Compared with traditional algorithms, the improved path planning algorithm significantly reduces the number of nodes computed by 91.48%, resulting in a notable decrease in search time by 75.68%.

In this study, a prefabricated component path planning framework based on the improved A* algorithm and GA is proposed for the first time. In addition, this study proposes a safety-bounding box that considers the effects of torsion and slinging of components during lifting. The semantic information of IFC for component lifting is enriched by taking into account lifting data such as binding positions, lifting methods, lifting angles and lifting offsets.

The purpose of this study is to investigate and understand the performance of countries in individual Olympic Games, specifically focusing on the Tokyo 2020 Olympics. Employing cluster analysis and decision trees, the research aims to categorize countries based on their representation, participation and success.

This research employs a data-driven approach to comprehensively analyze and enhance understanding of countries' performances in individual Olympic Games. The methodology involves a two-stage clustering method and decision tree analysis to categorize countries and identify influential factors shaping their Olympic profiles.

The study, analyzing countries' performances in the Tokyo 2020 Olympics through cluster analysis and decision trees, identified five clusters with consistent profiles. Notably, China, Great Britain, Japan, Russian Olympic Committee and the United States formed a high-performing group, showcasing superior success, representation and participation. The analysis revealed a correlation between higher representation/participation and success in individual Olympic Games. Decision tree insights underscored the significance of population size, GDP per Capita and HALE index, indicating that countries with larger populations, better economic standing and higher health indices tended to perform better.

The study has several limitations that should be considered. Firstly, the findings are based on data exclusively from the Tokyo 2020 Olympics, which may limit the generalizability of the results to other editions.

The research offers practical implications for policymakers, governments and sports organizations seeking to enhance their country's performance in individual Olympic Games.

The research holds significant social implications by contributing insights that extend beyond the realm of sports.

The originality and value of this research lie in its holistic approach to analyzing countries' performances in individual Olympic Games, particularly using a two-stage clustering method and decision tree analysis.

The e-commerce boom presents new challenges for last-mile delivery (LMD), which may be mitigated by new delivery technologies. This paper evaluates the impact of mobile parcel lockers (MPL) on costs and CO₂ equivalent (CO₂e) emissions in existing LMD networks, which include home delivery and shipments to stationary parcel lockers.

To describe customers’ preferences, we design a multinomial logit model based on recipients’ travel distance to pick-up locations and availability at home. Based on route cost estimation, we define the operating costs for MPLs. We devise a mathematical model with binary decision variables to optimize the location of MPLs.

Our study demonstrates that integrating MPLs leads to additional cost savings of 8.7% and extra CO₂e emissions savings of up to 5.4%. Our analysis of several regional clusters suggests that MPLs yield benefits in highly populous cities but may result in additional emissions in more rural areas where recipients drive longer distances to pick-ups.

This paper designs a suitable operating model for MPLs and demonstrates environmental and economic savings. Moreover, it adds recipients’ availability at home to receive parcels improving the accuracy of stochastic demand. In addition, MPLs are evaluated in the context of several regional clusters ranging from large cities to rural areas. Thus, we provide managerial guidance to logistics service providers how and where to deploy MPLs.

This paper aims to propose a simulation-based performance evaluation model for the drone-based delivery of aid items to disaster-affected areas. The objective of the model is to perform analytical studies, evaluate the performance of drone delivery systems for humanitarian logistics and can support the decision-making on the operational design of the system – on where to locate drone take-off points and on assignment and scheduling of delivery tasks to drones.

This simulation model captures the dynamics and variabilities of the drone-based delivery system, including demand rates, location of demand points, time-dependent parameters and possible failures of drones’ operations. An optimization model integrated with the simulation system can update the optimality of drones’ schedules and delivery assignments.

An extensive set of experiments was performed to evaluate alternative strategies to demonstrate the effectiveness for the proposed optimization/simulation system. In the first set of experiments, the authors use the simulation-based evaluation tool for a case study for Central Florida. The goal of this set of experiments is to show how the proposed system can be used for decision-making and decision-support. The second set of experiments presents a series of numerical studies for a set of randomly generated instances.

The goal is to develop a simulation system that can allow one to evaluate performance of drone-based delivery systems, accounting for the uncertainties through simulations of real-life drone delivery flights. The proposed simulation model captures the variations in different system parameters, including interval of updating the system after receiving new information, demand parameters: the demand rate and their spatial distribution (i.e. their locations), service time parameters: travel times, setup and loading times, payload drop-off times and repair times and drone energy level: battery’s energy is impacted and requires battery change/recharging while flying.