Sharif Digital Repository

Response surfaces express the behavior of responses and can be used for both single and multi-response problems. A common approach to estimate a response surface using experimental results is the ordinary least squares (OLS) method. Since OLS is very sensitive to outliers, some robust approaches have been discussed in the literature. Although there are many methods available in the literature for multiple response optimizations, there are a few studies in model building especially robust models. Assuming correlated responses, in this paper, a robust coefficient estimation method is proposed for multi response problem based on M-estimators. In order to illustrate the performance of the... 

Learning an appropriate distance measure under supervision of side information has become a topic of significant interest within machine learning community. In this paper, we address the problem of metric learning for constrained clustering by considering three important issues: (1) considering importance degree for constraints, (2) preserving the topological structure of data, and (3) preserving some natural distribution properties in the data. This work provides a unified way to handle different issues in constrained clustering by learning an appropriate distance measure. It has modeled the first issue by injecting the importance degree of constraints directly into an objective function.... 

We consider the problem of learning a density function from observations of an unknown underlying model in a distributed setting, where the observations are partitioned into different sites. Applying commonly used density estimation methods such as Gaussian Mixture Model (GMM) or Kernel Density Estimation (KDE) to distributed data leads to an extensive amount of communication. A familiar approach to address this issue is to sample a small subset of data and collect them into a central node to run the density estimation algorithms on them. In this paper, we follow an alternative to the sub-sampling approach by proposing the nested Log-Poly model. This model provides an accurate density... 

With the capacity increase of large-scale DC renewable energy and DC loads, the reliability issues of hybrid AC/DC networks become increasingly prominent. On the other hand, a modern distribution network should also deliver power to individual customers based on their priority levels and the traditional reliability indices are not suitable for modern networks. Flexible reliability (FR) is a new concept that considers the loads' importance in the reliability evaluation of distribution grids. In this study, a novel comprehensive FR index is introduced for hybrid AC/DC networks. To determine the proposed index, power networks are modelled as a topological combination of edges and nodes. An... 

Extreme weather events such as earthquake and hurricane have disastrous consequences on power systems. Due to the inherent nature of these events, as high-impact low-probability (HILP) events, selection of an appropriate method that can provide the effects of weather conditions on the power system behavior still remains a significant challenge. Resilience is a new concept that focuses on mitigating the destructive effects of such disastrous events on power systems. This article provides a fundamental framework for quantifying and modeling of power systems resilience, with focus on high wind incidence. The algorithm composes of four steps. In the first step, the prerequisites of the analysis... 

Purpose: This paper aims to propose a novel matrix-based systematic approach for vulnerability assessment. Design/methodology/approach: The proposed method consists of two major steps. First, the power network is modeled as a topological combination of edges (transmission lines, transformers, etc.) and nodes (buses, substations, etc.). The second step is to use an axiomatic design-based index for topology analysis. This index is based on the systematic counting of possible routes from the start (generators) to destination (loads), considering load importance, before and after a disruption. Findings: The effectiveness of the proposed method is demonstrated through an illustrative example and... 

Electric power systems try to maximize resilience by various enhancement strategies as preventive and corrective actions against extreme weather events. This paper presents an operational network reconfiguration strategy during a high wind event to strengthen the resiliency of distribution networks. In the proposed resilience enhancement strategy, a bi-level optimization problem is formulated with two conflicting objectives (i) maximizing grid resilience and (ii) realize the primary objective by a minimum number of out-of-service lines (OSLs) switching operations. Furthermore, the algorithm considers the priority of loads, which is an important characteristic of modern distribution grids.... 

Purpose: This paper aims to propose a novel matrix-based systematic approach for vulnerability assessment. Design/methodology/approach: The proposed method consists of two major steps. First, the power network is modeled as a topological combination of edges (transmission lines, transformers, etc.) and nodes (buses, substations, etc.). The second step is to use an axiomatic design-based index for topology analysis. This index is based on the systematic counting of possible routes from the start (generators) to destination (loads), considering load importance, before and after a disruption. Findings: The effectiveness of the proposed method is demonstrated through an illustrative example and...