Virtual machine placement (VMP) is an important issue in selecting most suitable set of physical machines (PMs) for a set of virtual machines (VMs) in cloud computing environment. VMP problem consists of two sub problems: incremental placement (VMiP) problem and consolidated placement (VMcP) problem. The goal of VMcP is to consolidate the VMs to more suitable PMs. The challenge in VMcP problem is how to find optimal solution effectively and efficiently especially when VMcP is a kind of NP-hard problem. In this paper, we present a novel solution to the VMcP problem called VMPMBBO. The proposed VMPMBBO treats VMcP problem as a complex system and utilizes the biogeography-based optimization (BBO) technique to optimize the virtual machine placement that minimizes both the resource wastage and the power consumption at the same time. Extensive experiments have been conducted using synthetic data from related literature and data from two real datasets. First of all, the necessity of VMcP has been proved by experimental results obtained by applying VMPMBBO. Then, the proposed method is compared with two existing multi-objective VMcP optimization algorithms and it is shown that VMPMBBO has better convergence characteristics and is more computationally efficient as well as robust. And then, the issue of parameter setting of the proposed method has been discussed. Finally, adaptability and extensibility of VMPMBBO have also been proved through experimental results. To the best of our knowledge, this work is the first approach that applies biogeography-based optimization (BBO) to virtual machine placement.

No abstract

It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks. In this paper, we extend adversarial graphs to the problem of community detection which is much more difficult. We focus on black-box attack and aim to hide targeted individuals from the detection of deep graph community detection models, which has many applications in real-world scenarios, for example, protecting personal privacy in social networks and understanding camouflage patterns in transaction networks. We propose an iterative learning framework that takes turns to update two modules: one working as the constrained graph generator and the other as the surrogate community detection model. We also find that the adversarial graphs generated by our method can be transferred to other learning based community detection models.

A spintronic method of ultra-fast broadband microwave spectrum analysis is proposed. It uses a rapidly tuned spin torque nano-oscillator (STNO), and does not require injection locking. This method treats an STNO generating a microwave signal as an element with an oscillating resistance. When an external signal is applied to this "resistor" for analysis, it is mixed with the signal generated by the STNO. The resulting mixed voltage contains the "sum" and "difference" frequencies, and the latter produces a DC component when the external frequency matches the frequency generated by the STNO. The mixed voltage is processed using a low pass filter to exclude the "sum" frequency components, and a matched filter to exclude the dependence of the resultant DC voltage on the phase difference between the two signals. It is found analytically and by numerical simulation, that the proposed spectrum analyzer has a frequency resolution at a theoretical limit in a real-time scanning bandwidth of 10 GHz, and a frequency scanning rate above 1 GHz/ns, while remaining sensitive to signal power as low as the Johnson-Nyquist thermal noise floor.Spectrum analyzers are critically important instruments with applications in engineering, science, and medicine 1,2 . Historically, spectrum analyzers have been implemented with either swept-tuned or Fourier methods. More recently, real-time spectrum analyzers have started to use a combination of these methods and vector signal analysis. Despite substantial technological improvements, current real time spectrum analyzers for demanding applications, such as pulsed radar frequency determination or electronic signal intelligence, are exceedingly complex and/or computationally expensive 1 .We propose to use a rapidly tuned spin torque nanooscillator (STNO) 3-7 based on a magnetic tunnel junction (MTJ) to perform fast, broadband spectrum analysis with frequency scanning rates and bandwidths that exceed current state of the art, all while remaining sensitive to signals with power levels as low as the Johnson-Nyquist thermal noise floor. STNOs are nano-sized low power microwave auto-oscillators that can be tuned over a wide frequency range by adjusting a driving bias DC current. They have a number of interesting features, including low operating power, compatibility with CMOS technology, nonlinear synchronization behavior, operation from below 1 GHz to above 65 GHz, high modulation rates, and the possibility of a radiation-hard construction 7-19 . At low frequencies (f < 3 GHz), they have been constructed to operate in the absence of a bias magnetic field 20 . STNO oscillations occur in an MTJ when a DC electric current of sufficient amplia) slouis@oakland.edu tude excites the free layer magnetization to precess with a microwave frequency due to the spin-transfer torque effect 21,22 . These magnetization oscillations can be detected macroscopically through the effect of tunneling magnetoresistance (TMR). For the purposes of this paper, an STNO (a current-driven MTJ with an oscillating TMR) will be tre...

In scientific data analysis, clusters identified computationally often substantiate existing hypotheses or motivate new ones. Yet the combinatorial nature of the clustering result, which is a partition rather than a set of parameters or a function, blurs notions of mean, and variance. This intrinsic difficulty hinders the development of methods to improve clustering by aggregation or to assess the uncertainty of clusters generated. We overcome that barrier by aligning clusters via optimal transport. Equipped with this technique, we propose a new algorithm to enhance clustering by any baseline method using bootstrap samples. Cluster alignment enables us to quantify variation in the clustering result at the levels of both overall partitions and individual clusters. Set relationships between clusters such as one‐to‐one match, split, and merge can be revealed. A covering point set for each cluster, a concept kin to the confidence interval, is proposed. The tools we have developed here will help address the crucial question of whether any cluster is an intrinsic or spurious pattern. Experimental results on both simulated and real data sets are provided. The corresponding R package OTclust is available on CRAN.