Failure rate prediction under adverse weather conditions in an electric Distribution System using Negative Binomial Regression

Fanucchi, Rodrigo Z.; Bessani, Michel; Camillo, Marcos H. M.; London, João Bosco Augusto; Maciel, Carlos Dias

doi:10.1109/ichqp.2016.7783464

Cited by 12 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The components of an electrical distribution system, as transformers and conductors, can be considered as a two‐state system, with transition between a working state to a failure state, and this can be modelled by an exponential reliability function (

R false(t false)

) with a constant failure rate (

λ

) as shown in (1) [31]

R false(t false) = P false(T > t false) = e^{- λ t},

where

R false(t false)

is the probability of a proper function after a specified time interval T . From (1), the cumulative distribution function

P false(t false)

can be defined as

P false(t false) = P false(T \leq t false) = 1 - R false(t false) .

Thus, using the inverse transform method [29, 32] for the exponential distribution

U = P false(t false) = 1 - e^{- λ t},

where U is a uniform distribution between 0 and 1, a failure time t can be sampled from a uniform distributed random number by using (4)

t = - \frac{1}{λ} \ln (1 - U) = - \frac{1}{λ} \ln false(U false) .

In previous research [14], a failure rate prediction model was developed using historical data of failures in the Brazilian medium‐voltage distribution system also used in this study. This model is a count data regression using the negative binomial for the expected daily failure rate per kilometre with covariates for atmospheric discharges ( ad ) and wind gust speed ( w ).…”

Section: Power Distribution System Analysis With Smcsmentioning

confidence: 99%

“…In the case of electric power systems, disruption in any of its subsystems (generation, transmission, and distribution) can directly affect consumers and other infrastructures [12]. Among the high‐impact events that can cause such disruptions [13], severe weather events have great destructive potential [14]. A procedure to investigate the effects of disruptive events is the evaluation of power distribution systems resilience [13, 15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic indexes for power distribution systems resilience analysis

Fanucchi¹,

Bessani

Camillo³

et al. 2019

IET Generation, Transmission & Distribution

Self Cite

View full text Add to dashboard Cite

R false(t false)

) with a constant failure rate (

λ

) as shown in (1) [31]

R false(t false) = P false(T > t false) = e^{- λ t},

where

R false(t false)

is the probability of a proper function after a specified time interval T . From (1), the cumulative distribution function

P false(t false)

can be defined as

P false(t false) = P false(T \leq t false) = 1 - R false(t false) .

Thus, using the inverse transform method [29, 32] for the exponential distribution

U = P false(t false) = 1 - e^{- λ t},

where U is a uniform distribution between 0 and 1, a failure time t can be sampled from a uniform distributed random number by using (4)

t = - \frac{1}{λ} \ln (1 - U) = - \frac{1}{λ} \ln false(U false) .

Section: Power Distribution System Analysis With Smcsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Stochastic indexes for power distribution systems resilience analysis

Fanucchi¹,

Bessani

Camillo³

et al. 2019

IET Generation, Transmission & Distribution

Self Cite

View full text Add to dashboard Cite

“…MCPSs are comprised of four layers, which need to be considered and secured. (1) The data acquisition layer has a body area network (BAN), which are wearable sensors which facilitate the collection of patient medical information. (2) The data concentration/aggregation layer, consisting of transmitting the gathered information to a gateway server through short range wireless, such as Bluetooth, due to the low computational power of sensors with a BAN.…”

Section: Structurementioning

confidence: 99%

“…Hospital infrastructures are classified as mission-critical infrastructures [1]. These information infrastructures have become increasingly dependent on information and communication technologies (ICT) to facilitate communication and automate services [2].…”

Section: Introductionmentioning

confidence: 99%

An Investigation into Healthcare-Data Patterns

et al. 2019

View full text Add to dashboard Cite

Visualising complex data facilitates a more comprehensive stage for conveying knowledge. Within the medical data domain, there is an increasing requirement for valuable and accurate information. Patients need to be confident that their data is being stored safely and securely. As such, it is now becoming necessary to visualise data patterns and trends in real-time to identify erratic and anomalous network access behaviours. In this paper, an investigation into modelling data flow within healthcare infrastructures is presented; where a dataset from a Liverpool-based (UK) hospital is employed for the case study. Specifically, a visualisation of transmission control protocol (TCP) socket connections is put forward, as an investigation into the data complexity and user interaction events within healthcare networks. In addition, a filtering algorithm is proposed for noise reduction in the TCP dataset. Positive results from using this algorithm are apparent on visual inspection, where noise is reduced by up to 89.84%.

show abstract

“…Survival analysis is another approach applicable to regression methods, that usually uses time as the primary variable, and provides survival and hazard functions that are interesting to be analyzed. Both ways can be applied in DSs failure data associated with climatic events as covariates, as in Fanucchi et al (2016) with a Negative Binomial Regression for failure rate and Bessani et al (2016) with Survival Analysis using mainly non-parametric techniques.…”

Section: Introductionmentioning

confidence: 99%

Survival analysis of Electrical Power Distribution systems using Weibull Regression

Fogliatto

Santos

Bessani

et al. 2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

Self Cite

View full text Add to dashboard Cite

Critical infrastructures are systems present in our society, which interfere in several ways when they do not operate in their normal conditions. Electric Power Distribution systems are an example of critical infrastructure, and therefore, the study of the common factors that affect their performance has great relevance. The concept of time to event (Lifetime Data Analysis) makes it possible to use survival analyses to estimate the influence of different dangers on the reliability of systems. A Weibull distribution was used to implement a Weibull regression, using climate data and information about failures of a Brazilian Electrical Power Distribution System, allowing verification of how climatic events impact this type of critical infrastructure. The results presented describes the failure chance given certain climatic conditions, indicating the effect of such exogenous covariates. With greater awareness of potential threats, the reliability of the system can be incresead by better planning and for threats mitigation.

show abstract

Failure rate prediction under adverse weather conditions in an electric Distribution System using Negative Binomial Regression

Cited by 12 publications

References 19 publications

Stochastic indexes for power distribution systems resilience analysis

Stochastic indexes for power distribution systems resilience analysis

An Investigation into Healthcare-Data Patterns

Survival analysis of Electrical Power Distribution systems using Weibull Regression

Contact Info

Product

Resources

About