Marginalized Maximum Likelihood for Parameters Estimation of the Three Parameter Weibull Distribution

The aims of this paper is to propose a new approach for fitting a three-parameter weibull distribution to data from an independent and identically distributed scheme of sampling. This approach use a likelihood function based on the n - 1 largest order statistics. Information loss by dropping the first order statistic is then retrieved via an MM-algorithm which will be used to estimate the model’s parameters. To examine the properties of the proposed estimators, the associated bias and mean squared error were calculated through Monte Carlo simulations. Subsequently, the performance of these estimators were compared with those of two concurrent methods.

Distributed Extremum-Seeking for Wind Farm Power Maximization Using Sliding Mode Control

This paper introduces a sliding-mode-based extremum-seeking algorithm aimed at generating optimal set-points of wind turbines in wind farms. A distributed extremum-seeking control is directed to fully utilize the captured wind energy by taking into consideration the wake and aerodynamic properties between wind turbines. The proposed approach is a model-free algorithm. Namely, it is independent of the model selection of the wake interaction between the wind turbines. The proposed distributed scheme consists of two parts. A dynamic consensus algorithm and an extremum-seeking controller based on sliding-mode theory. The distributed consensus algorithm is exploited to estimate the value of the total power produced by a wind farm. Subsequently, sliding-mode extremum-seeking controllers are intended to cooperatively produce optimal set-points for wind turbines within the farm. Scheme performance is tested via extensive simulations under both steady and varying wind speed and directions. The presented distributed scheme is compared with a centralized approach, in which the problem can be seen as a multivariable optimization. The results show that the employed scheme is able to successfully maximize power production in wind farms.

Information Bottleneck Classification in Extremely Distributed Systems

We present a new decentralized classification system based on a distributed architecture. This system consists of distributed nodes, each possessing their own datasets and computing modules, along with a centralized server, which provides probes to classification and aggregates the responses of nodes for a final decision. Each node, with access to its own training dataset of a given class, is trained based on an auto-encoder system consisting of a fixed data-independent encoder, a pre-trained quantizer and a class-dependent decoder. Hence, these auto-encoders are highly dependent on the class probability distribution for which the reconstruction distortion is minimized. Alternatively, when an encoding–quantizing–decoding node observes data from different distributions, unseen at training, there is a mismatch, and such a decoding is not optimal, leading to a significant increase of the reconstruction distortion. The final classification is performed at the centralized classifier that votes for the class with the minimum reconstruction distortion. In addition to the system applicability for applications facing big-data communication problems and or requiring private classification, the above distributed scheme creates a theoretical bridge to the information bottleneck principle. The proposed system demonstrates a very promising performance on basic datasets such as MNIST and FasionMNIST.