Reliability analysis of smart grid communication network by simulation

Luo, Ping; Sansavini, Giovanni; Zio, Enrico

doi:10.3233/ica-140469

Cited by 3 publications

(2 citation statements)

References 34 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth mentioning that machine learning has been applied to solve other problems within the field of smart grid such as biding in electricity markets [31] and energy efficient routing [21]. 7 This is the same assumption we present in this paper.…”

Section: Other Machine Learning Techniquessupporting

confidence: 61%

A pattern recognition approach for peak prediction of electrical consumption

Goodwin

Yazidi

2016

ICA

View full text Add to dashboard Cite

Abstract.Demand peaks in electrical power consumptions pose serious challenges for energy companies as these are typically unforeseen and require the net to support abnormally high consumption levels. Such peaks can be regulated in smart energy grids with the introduction of relatively simple techniques such as load balancing and smart pricing strategies. This is, however, difficult in practice because it requires prediction of peaks prior to their actual occurrence.While most studies formulate the problem as an estimation problem, we take a radically different approach and formulate it as a classical pattern recognition problem. Further, the paper applies classification methods to solve the problem and applies these with real-life data from a Norwegian smart grid pilot project. Some of the key findings are that the algorithms can accurately detect 80% of energy consumption peaks up to one week ahead of time. Furthermore, we introduce a novel Learning Automata based approaches for selecting the optimal prediction model from a pool of models in an online fashion.

show abstract

Section: Other Machine Learning Techniquessupporting

confidence: 61%

A pattern recognition approach for peak prediction of electrical consumption

Goodwin

Yazidi

2016

ICA

View full text Add to dashboard Cite

show abstract

“…The communication network also poses important challenges from the point of view of the delay in transmitting messages containing all that information. The work in [34] proposes a model for evaluating such aspects and providing, at the same time, a quantification of the network reliability. Moreover, the management of the vast amount of grid events has been addressed by means of Complex Event Processing (CEP) techniques [32].…”

Section: Introductionmentioning

confidence: 99%

A comprehensive common-sense-based architecture for understanding voltage-sag events in electrical grids

Santofimia

García

Villanueva

et al. 2018

ICA

View full text Add to dashboard Cite

This research is intended to evaluate the suitability of a common-sense-based approach for providing causal explanations to power quality disturbances and, more specifically, to voltage-sage events, with the aim of improving the security and reliability of the electrical grid. Since voltage sags are one of the most common power-quality disturbance and may have a severe impact on sensitive loads and users, the case study presented is dedicated to find their causes as a prerequisite to prevent them. The main contribution presented in this work is in the knowledge management domain. However, the proposed architecture adopts a multi-layer approach that comprehensively faces all the necessary stages, comprising: measurement and data collection, filtering, distribution, homogenization, and integration up to the process of inference of the possible cause of the event. The architecture of the proposed system comprises three layers, namely: the information gathering, the information modeling and the information understanding layers. The proposed system has been evaluated using a synthetic dataset of simulated voltages sags. Information about weather conditions and different location features and environmental circumstances is aggregated to the electrical features of the voltage sag, in order to improve the inference of the external cause of the event. Even though a real-world dataset would be required to fully validate the proposed system and assess the benefits in a real scenario, the results obtained with the synthetic dataset are satisfactory and an overall accuracy above 90% of the cause identification is achieved.

show abstract