The Internet of Things (IoT) integrates a large number of heterogeneous terminals and systems, possessing ubiquitous sensing and computing capabilities. Satellite networks are the crucial supplement to terrestrial net...
详细信息
The Internet of Things (IoT) integrates a large number of heterogeneous terminals and systems, possessing ubiquitous sensing and computing capabilities. Satellite networks are the crucial supplement to terrestrial networks, particularly in remote areas where network infrastructures are sparingly distributed or unavailable. Combining edge computing with satellite networks provides on-orbit computing capabilities for IoT applications, reducing service delay and enhancing service quality. Due to the resource constraints of satellites, achieving collaborative services through task offloading among multiple satellites becomes essential. Both the privacy leakage risk arising from frequent data interactions and the load imbalance resulting from offloading preferences cannot be overlooked. The key challenge of task offloading is to safeguard the privacy of offloaded data and ensure the system's load balance while minimizing the delay and energy consumption. In this paper, the task offloading problem is formulated as a Partially Observable Markov Decision Process (POMDP), and a task offloading algorithm based on multi-objective joint optimization using multi-agent deep reinforcement learning in a distributed architecture is proposed. The simulation results validate the efficacy of our model and algorithm, demonstrating that our proposed algorithm achieves better performance in minimizing comprehensive offloading costs.
PERT (Program Evaluation and Review Technique) is suitable for evaluating schedule optimization of DBB (Design-Bid-Build) projects based on serial execution of design and construction. However, it is not suitable for ...
详细信息
PERT (Program Evaluation and Review Technique) is suitable for evaluating schedule optimization of DBB (Design-Bid-Build) projects based on serial execution of design and construction. However, it is not suitable for evaluating the multi-objective joint optimization of DB (Design-Build) projects based on concurrent execution of design and construction. Therefore, focusing on the unique construction method and construction objective under DB mode, this study adopts the multi-parameter grey GERT (Graphical Evaluation and Review Technique) based on z-tag to construct a multi-objective joint optimization model of concurrent execution of designconstruction tasks. The research methods adopted are as follows: Firstly, based on the modeling idea of PERT, a multi-parameter grey GERT was constructed, which was composed of sub-GERTs representing the execution flow of design-construction tasks. Second, based on discussing the functional relationship between time, cost and quality in normal execution and rework execution, a method of constructing a moment generating function for concurrent execution time, cost and quality to characterize the uncertainty of input and output parameters is proposed. Thirdly, on the basis of analyzing the solving methods of each parameter of the multi-parameter GERT, the solving methods for starting execution time, information transmission duration, and total execution duration of the critical time nodes are given. Finally, according to the requirements of DB projects, the multi-objective joint optimization models based on progress oriented and quality oriented are constructed respectively, and the gamultiobj algorithm is used to solve the models. The proposed approach provides a scientific quantitative analysis method for evaluating the progress, cost and quality objectives of the concurrent execution of designconstruction tasks, and also lays theoretical guidance for further efficiency popularization of DB mode.
To solve the capacity vehicle routing problem (CVRP) more effectively and save related resources, this paper proposes a multi-objective joint optimization problem of loading problem and CVRP (LCVRP), and builds the ap...
详细信息
ISBN:
(纸本)9781467363433
To solve the capacity vehicle routing problem (CVRP) more effectively and save related resources, this paper proposes a multi-objective joint optimization problem of loading problem and CVRP (LCVRP), and builds the appropriate mathematical model. We design a multistage algorithm to solve it. In the first stage of the algorithm, we give a novel loading algorithm to work out the minimum number of transport vehicles. Numerical experiments manifest that we can get the minimum vehicles in LCVRP, and the satisfactory solutions of LCVRP are better than those of CVRP in some instances of VRPLIB. The experiment part of this paper shows the testing for E022 instance in detail.
Developing prefabricated buildings is an effective means to reduce carbon emissions in the construction industry. Currently, research on project management of prefabricated buildings mainly focuses on multi-objective ...
详细信息
Developing prefabricated buildings is an effective means to reduce carbon emissions in the construction industry. Currently, research on project management of prefabricated buildings mainly focuses on multi-objectiveoptimization of construction period cost quality issues, with little consideration given to the important environmental factor of carbon emissions. In this article, we propose a comprehensive optimizationobjective involving the carbon emissions, duration, cost and quality level of projects. Then, an interval grey GERT network is used to establish a multi-objective joint optimization model for the green construction of assembled buildings, and the modelling problem is solved with the modified NSGA-III algorithm based on a local search approach with sparsity. Taking the affordable housing project on the north side of Shangfang in Nanjing as an example, compared with the original contract, it is shown that the improved NSGA-III algorithm can shorten the total construction period by 17.52%, reduce the total cost by 15.24%, increase the total quality level by 8.89%, and reduce carbon emissions by 33.64%. The establishment of a multi-objective joint optimization model and its solving algorithm for green construction in prefabricated building projects provides more specific guidance for green construction in uncertain environments.
K-hyperparameter optimization in high-dimensional genomics remains a critical challenge, impacting the quality of clustering. Improved quality of clustering can enhance models for predicting patient outcomes and ident...
详细信息
K-hyperparameter optimization in high-dimensional genomics remains a critical challenge, impacting the quality of clustering. Improved quality of clustering can enhance models for predicting patient outcomes and identifying personalized treatment plans. Subsequently, these enhanced models can facilitate the discovery of biomarkers, which can be essential for early diagnosis, prognosis, and treatment response in cancer research. Our paper addresses this challenge through a four-fold approach. Firstly, we empirically evaluate the k-hyperparameter optimization algorithms in genomics analysis using a correlation based feature selection method and a stratified k-fold cross-validation strategy. Secondly, we evaluate the performance of the best optimization algorithm in the first step using a variety of the dimensionality reduction methods applied for reducing the hyperparameter search spaces in genomics. Building on the two, we propose a novel algorithm for this optimization problem in the third step, employing a jointoptimization of Deep-Differential-Evolutionary Algorithm and Unsupervised Transfer Learning from Intelligent GenoUMAP (Uniform Manifold Approximation and Projection). Finally, we compare it with the existing algorithms and validate its effectiveness. Our approach leverages UMAP pre-trained special autoencoder and integrates a deep-differential-evolutionary algorithm in tuning k. These choices are based on empirical analysis results. The novel algorithm balances population size for exploration and exploitation, helping to find diverse solutions and the global optimum. The learning rate balances iterations and convergence speed, leading to stable convergence towards the global optimum. UMAP’s superior performance, demonstrated by short whiskers and higher median values in the comparative analysis, informs its choice for training the special autoencoder in the new algorithm. The algorithm enhances clustering by balancing reconstruction accuracy, local structur
Based on the novel proton exchange membrane fuel cells (PEMFC) stack integrated with highly thermal conductive micro heat pipe arrays (MHPA), a method that combines mathematical modeling, experiment, and multi-objecti...
详细信息
Based on the novel proton exchange membrane fuel cells (PEMFC) stack integrated with highly thermal conductive micro heat pipe arrays (MHPA), a method that combines mathematical modeling, experiment, and multi-objectiveoptimization is designed in this paper. The mathematical model adopts lumped parameter coupled with water, thermal, electricity, and other sub-models, which is used to investigate the performance of the MHPA-PEMFC stack, and is further combined with the response surface method to develop a multi-objective joint optimization strategy and predictive models for the structure of the stack. Results show that the performance of the stack at low ambient temperature is better when the stack is under high currents. The maximum loading currents and maximum power density improvement effects of increasing the number of MHPA are much less than the disadvantages brought by increasing the weight. The optimization results suggest that for each 1 kW of the stack, the optimum configuration is as follows: The numbers of MHPAs and fin groups are 30 and 10, respectively, and the length of MHPA condensation is 75.7 mm. The maximum net power under typical load (30 A) can be increased by 17.7 %, and the stack weight can be reduced by 1083.5 g after optimization.
An unheard of growth in mobile data traffic has drawn attention from academia and industry. Mobile cloud computing is an emerging computing paradigm combining cloud computing and mobile networks to alleviate resource-...
详细信息
An unheard of growth in mobile data traffic has drawn attention from academia and industry. Mobile cloud computing is an emerging computing paradigm combining cloud computing and mobile networks to alleviate resource-constrained limitations of mobile devices, which can greatly improve network quality of service and efficiency to make good use of available network resource. Mobile cloud computing not only inherits the advantages of strong computing capacity and massive storage of cloud computing, but also overcomes the time and geographical restrictions, bringing benefits for mobile users to offload complex computation to powerful cloud servers for execution anytime and anywhere. To this end, an optimal task workflow scheduling scheme is proposed for the mobile devices, based on the dynamic voltage and frequency scaling technique and the whale optimization algorithm. Through considering three factors: task execution position, task execution sequence, and operating voltage and frequency of mobile devices, this study makes a tradeoff between performance and energy consumption by solving the jointoptimization for task completion time and energy consumption simultaneously. Finally, a series of extensive simulation results has demonstrated and verified the scheme has distinguished performance in terms of efficiency and operational cost, providing feasible solutions to similar optimization problems of mobile cloud computing. (C) 2019 Elsevier B.V. All rights reserved.
暂无评论