Energy consumption is an important cost driven by growth of computing power, thereby energy conservation has become one of the major problems faced by cloud system. How to maximize the utilization of physical machines...
详细信息
Energy consumption is an important cost driven by growth of computing power, thereby energy conservation has become one of the major problems faced by cloud system. How to maximize the utilization of physical machines, reduce the number of virtual machine migrations, and maintain load balance under the constraints of physical machine resource thresholds that is the effective way to implement energy saving in data center. In the paper, we propose a multi-objective physical model for virtual machine deployment. Then the improved multi-objective particleswarmoptimization (TPSO) is applied to virtual machine deployment. Compared to other algorithms, the algorithm has better ergodicity into the initial stage, improves the optimization precision and optimization efficiency of the particleswarm. The experimental results based on CloudSim simulation platform show that the algorithm is effective at improving physical machine resource utilization, reducing resource waste, and improving system load balance.
Bearings are the core components of ship propulsion shafting, and effective prediction of their working condition is crucial for reliable operation of the shaft system. Shafting vibration signals can accurately repres...
详细信息
Bearings are the core components of ship propulsion shafting, and effective prediction of their working condition is crucial for reliable operation of the shaft system. Shafting vibration signals can accurately represent the running condition of bearings. Therefore, in this article, we propose a new model that can reliably predict the vibration signal of bearings. The proposed method is a combination of a fuzzy-modified Markov model with gray error based on particleswarmoptimization (PGFM (1,1)). First, particleswarmoptimization was used to optimize and analyze the three related parameters in the gray model (GM (1,1)) that affect the data fitting accuracy, to improve the data fitting ability of GM (1,1) and form a GM (1,1) based on particleswarmoptimization, which is called PGM (1,1). Second, considering that the influence of historical relative errors generated by data fitting on subsequent data prediction cannot be expressed quantitatively, the fuzzy mathematical theory was introduced to make fuzzy corrections to the historical errors. Finally, a Markov model is combined to predict the next development state of bearing vibration signals and form the PGFM (1,1). In this study, the traditional predictions of GM (1,1), PGM (1,1), and newly proposed PGFM (1,1) are carried out on the same set of bearing vibration data, to make up for the defects of the original model layer by layer and form a set of perfect forecast system models. The results show that the predictions of PGM (1,1) and PGFM (1,1) are more accurate and reliable than the original GM (1,1). Hence, they can be helpful in the design of practical engineering equipment.
The aim of logistics distribution center location is to improve the logistics service quality and reduce the transportation cost of goods. The problems are related to both the classical location problem and the vehicl...
详细信息
ISBN:
(纸本)9781467344975
The aim of logistics distribution center location is to improve the logistics service quality and reduce the transportation cost of goods. The problems are related to both the classical location problem and the vehicle routing problem. This paper proposes logistics distribution center location based on particle swarm optimization algorithm. It models the logistics distribution center location problem considering the user demand and operating cost, then it uses modified particle swarm optimization algorithm to give solution. Experimental result shows that the proposed model and algorithm is effective.
Device-to-device (D2D) and caching can effectively solve the problem of repeated transmission of plentiful short videos in wireless networks. This paper considers a downlink video transmission process among cellular u...
详细信息
ISBN:
(纸本)9781728107325
Device-to-device (D2D) and caching can effectively solve the problem of repeated transmission of plentiful short videos in wireless networks. This paper considers a downlink video transmission process among cellular users and D2D users with interference between co-channel users. Caching with user preferences in D2D users is also taken into consideration to improve the system capacity. Joint channel and power allocation is optimized to maximize the sum rate of all users. The problem is a mixed integer nonlinear programming (MINLP) and is hard to solve. Firstly, the concept of cache similarity distance based on user preferences and video popularity is introduced to divide users into different groups. Then, the optimization problem is decoupled into two sub-problems. And a joint channel and power allocation algorithm based on caching with user preferences is proposed. Besides, a penalty function is introduced to handle constraints and a speed update function is modified to optimize binary variables and continuous variables simultaneously. Finally, an improved particle swarm optimization algorithm (PSO) is proposed to solve the problem. Simulation results show that the proposed algorithm can effectively improve the system capacity of the network.
The current temperature field model of plate rolling process is generally based on CPU programming, due to the influence of computer performance, the accuracy and speed of the model can not be improved at the same tim...
详细信息
The current temperature field model of plate rolling process is generally based on CPU programming, due to the influence of computer performance, the accuracy and speed of the model can not be improved at the same time. To solve this problem, this paper studies the temperature field model with particleswarmoptimization to modify the heat transfer coefficients, and the parallel program of this model is written under CUDA architecture, on premise of ensuring the accuracy of the model, the computation speed of the model is improved. To get the best acceleration, this paper analyzes the factors affecting GPU performance, the accuracy and speed of the temperature field model before and after modification are compared under the best acceleration configuration. Final temperature field model calculation error reduced to an average of 15.57., better than the model based on the empirical formula, the computing speed is also improved, which is 1.78 times that of CPU.
The detection of network attacks on computer systems remains an attractive but challenging research scope. As network attackers keep changing their methods of attack execution to evade the deployed intrusion-detection...
详细信息
ISBN:
(纸本)9783030009793;9783030009786
The detection of network attacks on computer systems remains an attractive but challenging research scope. As network attackers keep changing their methods of attack execution to evade the deployed intrusion-detection systems (IDS), machine learning (ML) algorithms have been introduced to boost the performance of the IDS. The incorporation of a single parallel hidden layer feed-forward neural network to the Fast Learning Network (FLN) architecture gave rise to the improved Extreme Learning Machine (ELM). The input weights and hidden layer biases are randomly generated. In this paper, the particle swan optimizationalgorithm (PSO) was used to obtain an optimal set of initial parameters for Reduce Kernel FLN (RK-FLN), thus, creating an optimal RKFLN classifier named PSO-RKELM. The derived model was rigorously compared to four models, including basic ELM, basic FLN, Reduce Kernel ELM (RK-ELM), and RK-FLN. The approach was tested on the KDD Cup99 intrusion detection dataset and the results proved the proposed PSO-RKFLN as an accurate, reliable, and effective classification algorithm.
The emergence of Multichip Module(MCM) means that the development of component technology is greatly improved in number, speed and performance. Research on thermal layout optimization methods for MCM can promote its r...
详细信息
ISBN:
(纸本)9781728101057
The emergence of Multichip Module(MCM) means that the development of component technology is greatly improved in number, speed and performance. Research on thermal layout optimization methods for MCM can promote its reliability, this paper established a numerical relationship model between junction temperature and coordinates of each chip. and uses ANSYS to simulate and analyze the temperature profile of the optimization results. This paper compares several typical optimization schemes based on (W) and presents the improved particleswarmalgorithm. Experimental results show that improved particleswarmalgorithm can improve inertia weight and maximum speed effectively, and also can achieve lower chip junction temperature in chip layout.
In order to reduce the operating costs of car-sharing companies and improve the satisfaction of users, a one-way carsharing systems optimization model which considers the time windows requirements of users is construc...
详细信息
ISBN:
(纸本)9781728132686
In order to reduce the operating costs of car-sharing companies and improve the satisfaction of users, a one-way carsharing systems optimization model which considers the time windows requirements of users is constructed with minimum total costs including scheduling costs and penalty costs. Then, an improved particle swarm optimization algorithm with tabu search is proposed to solve the model. Numerous experiments are performed to obtain the optimal solution. Finally, based on experimental results, some practical proposals for one-way carsharing systems are provided for the carsharing companies.
With the development of the peak load regulation ancillary service market and the improvement of the rules, the role of thermal power unit changed from the passive participant in peak load regulation for duty to the a...
详细信息
ISBN:
(纸本)9781728115900
With the development of the peak load regulation ancillary service market and the improvement of the rules, the role of thermal power unit changed from the passive participant in peak load regulation for duty to the active bidder. The power grid dispatching agency called the depth peak load regulation (DPLR) resources on demand according to the price. In order to research the optimal bidding strategy of thermal power units in the depth peak load regulation ancillary service market, a bi-level model of multiple thermal power manufacturers and single market dispatching institution is established based on stackelberg game. The upper level is the bidding strategy of thermal power manufacturers, including the income and cost of thermal power manufacturers. The lower level is the optimal scheduling scheme of the market dispatching institution. The nonlinear bi-level model is solved by the particle swarm optimization algorithm. The cases show the importance and validity of the proposed model
In order to realize the real-time on-line detection on resolution ratio of cement kiln tail, by means of the advantages from soft sensor measurement technology in which process parameters cannot be directly measured a...
详细信息
ISBN:
(纸本)9781728140940
In order to realize the real-time on-line detection on resolution ratio of cement kiln tail, by means of the advantages from soft sensor measurement technology in which process parameters cannot be directly measured at present, a support vector regression (SVR) optimized by the improved particleswarmoptimization (IPSO) algorithm is proposed. Based on the idea of adaptive weight, this algorithm overcomes the shortcomings of PSO which is prone to show premature convergence and poor local search ability, and improves its global search ability and local improvement ability. The parameters of SVR machine are optimized, and then soft sensor measurement model of resolution ratio of cement kiln tail is established. The simulation is compared with those based on the cross validation method and PSO, the results show that the IPSO-SVR algorithm has better ability of modeling, prediction and generalization, and the average relative error of prediction is 0.75%, so it can be further applied to the product real-time on-line detection on large-scale industries such as cement production.
暂无评论