Cloud computing is a dynamic and rapidly evolving field,where the demand for resources fluctuates *** paper delves into the imperative need for adaptability in the allocation of resources to applications and services ...
详细信息
Cloud computing is a dynamic and rapidly evolving field,where the demand for resources fluctuates *** paper delves into the imperative need for adaptability in the allocation of resources to applications and services within cloud computing *** motivation stems from the pressing issue of accommodating fluctuating levels of user demand *** adhering to the proposed resource allocation method,we aim to achieve a substantial reduction in energy *** reduction hinges on the precise and efficient allocation of resources to the tasks that require those most,aligning with the broader goal of sustainable and eco-friendly cloud computing *** enhance the resource allocation process,we introduce a novel knowledge-based optimization *** this study,we rigorously evaluate its efficacy by comparing it to existing algorithms,including the Flower Pollination algorithm(FPA),Spark Lion Whale optimization(SLWO),and Firefly *** findings reveal that our proposed algorithm,Knowledge Based Flower Pollination algorithm(KB-FPA),consistently outperforms these conventional methods in both resource allocation efficiency and energy consumption *** paper underscores the profound significance of resource allocation in the realm of cloud *** addressing the critical issue of adaptability and energy efficiency,it lays the groundwork for a more sustainable future in cloud computing *** contribution to the field lies in the introduction of a new resource allocation strategy,offering the potential for significantly improved efficiency and sustainability within cloud computing infrastructures.
Over-the-air computation (AirComp) has attracted vast attention due to its fast aggregation capacity for large scale distributed data. In order to further improve the computation performance of AirComp, we consider a ...
详细信息
Over-the-air computation (AirComp) has attracted vast attention due to its fast aggregation capacity for large scale distributed data. In order to further improve the computation performance of AirComp, we consider a multi-relay assisted AirComp network over a multi-carrier broadband channel, which can benefit from the multi-carrier diversity. Moreover, we take into account a more practical scenario with bounded channel uncertainties, and the worst-case computational mean square error (CMSE) is minimized by jointly designing the transmit and receiving scaling factors, as well as the amplification coefficient of each relay under the transmit power constraints. To handle the intractable non-convex robust optimization problem, we develop an efficient alternating optimization algorithm based on the cutting-set method (CSM). Numerical results are provided to validate the effectiveness of our proposed schemes.
This paper presents the application of a data-driven method for turbulence modeling. The main aim is to enhance the prediction capabilities of an existing Reynolds-averaged Navier-Stokes (RANS) model for laminar separ...
详细信息
This paper presents the application of a data-driven method for turbulence modeling. The main aim is to enhance the prediction capabilities of an existing Reynolds-averaged Navier-Stokes (RANS) model for laminar separation bubbles. The recently developed field inversion method has been chosen to infer corrections to the shear stress transport kappa-omega-gamma turbulence model. An innovative approach has been proposed to reduce the computational cost of the modeling procedure. The objective function makes use of the friction coefficient to compare data coming from the RANS model with reference large-eddy simulation data available in the literature. The performed test cases responded well to the optimization procedure which provided a correction field that boosts the turbulent kinetic energy within the bubble. The proposed procedure is the necessary building block to define a new turbulence model able to overcome the present limitations in simulating laminar separation bubbles.
Currently, the detection of anomalous machine operations and the identification of faulty machine components are essential for maintaining the stability of manufacturing processes and ensuring product quality. In engi...
详细信息
Currently, the detection of anomalous machine operations and the identification of faulty machine components are essential for maintaining the stability of manufacturing processes and ensuring product quality. In engineering applications, variations in environmental and operating conditions significantly influence the performance and efficiency of fault monitoring models. A bearing fault diagnosis method based on unsupervised domain adaptation with popular embeddings is proposed to address the dual challenges of unsupervised data environments and diverse engineering requirements while meeting demands for model costs, speed, and accuracy. Initially, an optimal convolutional neural network architecture is selected to extract significant feature data. Subsequently, an unsupervised manifold learning approach is utilized for dimensionality reduction, and a heuristic optimization algorithm is employed for hyperparameter optimization, thereby enhancing the model's performance and generalization capability. Furthermore, a robust classifier developed from source domain data and an accuracy calculation method based on decision fusion are designed to significantly improve the model's robustness. Finally, experiments on datasets with varying noise levels demonstrate that the proposed model achieves up to 20% higher accuracy in bearing fault diagnosis compared to other monitoring methods, showcasing its excellent practical utility in bearing anomaly detection and fault diagnosis.
The error backpropagation algorithm is a representative learning method that has been used in most deep network models. However, the error backpropagation algorithm, despite its decent performance, clearly has limits ...
详细信息
ISBN:
(纸本)9781665456456
The error backpropagation algorithm is a representative learning method that has been used in most deep network models. However, the error backpropagation algorithm, despite its decent performance, clearly has limits to its biological plausibility. Unlike the learning mechanism of the actual brain, the error backpropagation algorithm must reuse the weights used in the forward calculation for the backward error propagation. In order to overcome these limitations, the feedback alignment method, which uses a fixed random weight for the backpropagation computation, was proposed. The feedback alignment algorithm showed performances comparable to the original error backpropagation on several benchmark data sets. However, it is still in the preliminary stage of analysis, and various analysis on its learning behavior and practical efficiency are needed. In this paper, we combine feedback alignment learning method with popular optimization techniques such as RMSprop and Adam, and investigate its effect on the learning performances through computational experiments on benchmark data sets.
作者：
Huang, HaoLiang, XiuyeGuan, FangZi, JianFudan Univ
Inst Nanoelect Devices & Quantum Comp State Key Lab Surface Phys Shanghai 200433 Peoples R China Fudan Univ
Dept Phys State Key Lab Surface Phys Shanghai Peoples R China Fudan Univ
Zhangjiang Fudan Int Innovat Ctr Shanghai Peoples R China
In this letter, we propose an end-to-end inverse modeling and optimization method for microwave filter designs based on the data-augmentation learning strategy. Because of the non-uniqueness of solutions, it is diffic...
详细信息
In this letter, we propose an end-to-end inverse modeling and optimization method for microwave filter designs based on the data-augmentation learning strategy. Because of the non-uniqueness of solutions, it is difficult to achieve good convergence with artificial neural networks for inverse designs when the parameter space is very large. We prove that the accuracy of inverse predictions can be significantly improved using the network's self-generated data and the optimization can be greatly accelerated with the help of the inverse network. The predicted structural parameters can be used as initial values for optimization, which reduces the number of iterations and avoids falling into local optima. This method is applied to designs of fourth-order interdigital cavity filters. The measurement and simulation agree well.
This paper studies an orbital inspection game, which involves two spacecraft competing for imaging conditions in an on-orbit inspection mission. First, the main factors affecting the imaging conditions, including the ...
详细信息
This paper studies an orbital inspection game, which involves two spacecraft competing for imaging conditions in an on-orbit inspection mission. First, the main factors affecting the imaging conditions, including the sun angle, sunangle changing rate, relative distance, and distance changing rate, are analyzed to formulate a realistic multiplefactor inspection game. An approximate switching-type payoff function is specially designed to incorporate all the boundary constraints of those factors into the game model. Then, the analytical necessary conditions for the Nash equilibrium are derived and converted as a two-point boundary value problem (TPBVP). But different from conventional routes to solve the challenging TPBVP, a lighter costate optimization method is proposed, which transforms the TPBVP to a direct optimization problem by employing the conclusion that the optimal thrust directions of both sides are the same and utilizing the theory of the epsilon-Nash equilibrium. The existence of the epsilon-Nash equilibrium is proven, and the necessary conditions for a small epsilon are derived to support the method. Finally, simulations of the GEO inspection missions demonstrated the superiority of the proposed game formulation and the high efficiency and accuracy of the proposed method.
Calibration of low-cost humidity sensors such as the HTS221TR is critical for accurate measurements, especially in smart devices. This study compares two calibration methods: machine learning (PyTorchNeural Network re...
详细信息
Calibration of low-cost humidity sensors such as the HTS221TR is critical for accurate measurements, especially in smart devices. This study compares two calibration methods: machine learning (PyTorchNeural Network regression model) and optimization algorithm with Engineering Equation Solver. The critical role of temperature in humidity measurement emphasizes that it must be included for a valid calibration. The machine learning approach significantly reduced the average deviation of humidity, reaching +/- 2,5% compared to the original +/- 13,4%. Additionally, it aligned mean values along the identity line. However, the performance of the model varied across the different humidity ranges. Applying the model to real-world scenarios showed that the model underestimates humidity, likely due to the sensor's inherent tendency to overestimate humidity, especially at higher temperatures. Despite these challenges, both calibration methods offer simple and effective approaches for correcting lowcost sensor measurements, with machine learning enabling faster processing. This study not only improves the accuracy of the HTS221TR sensor, but also paves the way for more accurate and affordable humidity measurement technologies in general.
The mission requirements of crewed space vehicles flown by NASA drove the development of new techniques for burn targeting and guidance for ascent, rendezvous, lunar landing, and deorbit. The Saturn V Iterative Guidan...
详细信息
The mission requirements of crewed space vehicles flown by NASA drove the development of new techniques for burn targeting and guidance for ascent, rendezvous, lunar landing, and deorbit. The Saturn V Iterative Guidance Mode used an approximately optimal steering law that could adjust the trajectory to compensate for performance issues while meeting trajectory constraints at propulsion-system cutoff. Hypersurface targeting provided constraints for the Saturn V Trans-Lunar Injection burn. E Guidance, in quadratic- and linear-acceleration forms, provided closed-loop descent and ascent guidance for the Apollo Lunar Module. The Space Shuttle's Powered Explicit Guidance algorithm was more flexible than Apollo-era guidance algorithms, and it had better convergence characteristics, enabling it to support challenging abort profiles. The Space Launch System has built on the heritage of the Space Shuttle's guidance algorithm. The Orion spacecraft's Two-Level Targeter enables onboard, autonomous targeting of an entire mission profile subject to three-body dynamics in cislunar space. Orion uses Shuttle-derived guidance as the basis for an orbit-guidance package with more capability than guidance algorithms of previous vehicles.
With dynamic changes in the energy market and continuous advances in smart energy technology, regional integrated energy systems (RIESs) have emerged as a vital direction in the evolution of energy systems. They are i...
详细信息
With dynamic changes in the energy market and continuous advances in smart energy technology, regional integrated energy systems (RIESs) have emerged as a vital direction in the evolution of energy systems. They are increasingly gaining significance in the realm of energy supply (ES) and demand response initiatives. In this context, this article introduces a novel optimal operational model for an integrated energy system (IES) that incorporates energy price responsiveness. The paper commences by delivering a comprehensive overview of the typical structure of an IES, presenting detailed models for each system module, encompassing the electrical energy supplier, heating, and cooling components. The proposed system model comprises three distinct subsystems, each catering to specific energy requirements. The primary emphasis is on devising an efficient planning scheme tailored to the energy consumption patterns and operational aspects of the IES. Through the presented model, there is substantial potential for significantly reducing the overall system cost without inducing a noteworthy upsurge in environmental pollution. Moreover, the energy efficiency of the system can experience considerable enhancement. The desired optimization problem has been solved using the proposed multiobjective Horse Herd optimization algorithm (MOHHOA). Additionally, in this strategy, Pareto front and fuzzy selection are employed to make better decisions among all Pareto solutions. The optimization strategy devised in this research not only enables the integrated operation of the IES but also ensures its compatibility with ongoing energy development initiatives. The proposed method yields a diverse set of Pareto solutions across the objective space, providing various trade-offs between economic, environmental, and reliability considerations. Utilizing MOHHOA, the algorithm efficiently balances exploration and exploitation during optimization, resulting in informed decision-making. In optimal p
暂无评论