A Hybrid Prediction Model for Damage Warning of Power Transmission Line Under Typhoon Disaster

Abstract

To bolster the resilience of power systems against typhoon disasters, this paper develops a holistic framework of wind disaster warning for transmission lines. This paper proposes a hybrid prediction model to quantify the transmission line damage probability under typhoon disaster based on extreme value type I probability distribution, Monte Carlo method, and Random Forest. Specifically, this paper uses the extreme value type I probability distribution and the Monte Carlo method to simulate the random wind field, and predict the damage probability of transmission lines under each wind field using the Random Forest method. This paper takes typhoon ''Mangkhut'' in 2018 as a case study, and compare the performance of the hybrid model based on random wind field with the Random Forest method under predicted and measured wind field. The results demonstrate that the hybrid model can effectively utilize wind speed data to obtain a more reliable prediction and achieves the best synthetic similarity to the actual damage situations. INDEX TERMS Typhoon, power system resilience, transmission line, extreme value type I probability distribution, Monte Carlo, Random Forest, random wind field.

A review of power system resilience assessment and enhancement approaches by focusing on wind farms and wind turbines

“…Therefore, wind storm is a spatiotemporal model that to get better results, its dynamic must be considered. In [44], the data of wind is obtained from ArcGIS10.4.1, which is provided by (ESRI). In [45], the difference in pressure between the centre and the periphery of the storm is the base of calculations and the speed of wind is calculated according to the pressure and the distance from the centre of storm.…”

“…Uncertainty non-sequential Monte-Carlo (MC) simulation to determine the system state under wind storms [57] finite element modelling of components, especially of transmission towers to model the outage of power [19] model the contingency of the wind power based on the Markov-switching model [55] unscented transform [58,59] to model the output of RES and the load demand Gaussian mixture to determine the WT output power and using probability density function (PDF) curve [16] Taguchi's orthogonal array testing (TOAT) to model the uncertainty of wind [56] the spatiotemporal impact of wind storm on transmission lines by using MC [60] the impact of extreme weather on transmission lines by using MC [61] Proposed a zonal wind-speed-specific uncertainty set [13] Wind storm Batt [45] Yan Meng [19] patio-temporal [46] Rankine vortex field [48] hybrid method contains MC and extreme value type I probability distribution [44] Weibull and Von Mises distributions [25] Load ZIP [23,24,51,52] normal distribution [25] abilistic methods [47]. In addition, in [19,21,45,46,48], the utilized model is based on the dynamic of wind in which the pressure, wind speed, and distance from the centre of the wind storm are key parameters.…”

“…To model the resiliency of the power transmission towers, the wind speed [44], age of the towers [45,49], and their adjacency [45] are important.…”

Resilience assessment and improvement for electric power transmission systems against typhoon disasters: A data-model hybrid driven approach

“…In Ref. [18]- [20], the authors established a data-model-driven failure model of transmission corridors against typhoon disasters. However, the paper lacked the analysis of system resilience and corresponding improvement strategies.…”

Topological Modeling Research on the Functional Vulnerability of Power Grid under Extreme Weather

“…In terms of frequently concerning typhoon weather, Nguyen H. T. et al [35] utilized a stochastic optimization model based on resilience improvement, and Zhou J. et al [36] proposed a coordinated optimization method based on the regional integrated energy system to realize resilience improvement. The mathematical programming model is an important optimization method to study the resilience of power grid; Hou H. et al [37] used machine learning methods to analyze the impact of wind disasters on transmission lines, and Karangelos E. et al [38] combined the failure rate of grid units sensitive to weather with an optimization model based on vulnerability identification through the Monte Carlo method. Under extreme weather, the power grid capabilities related to resilience include physical hardiness and operational capability, and each capability enhancement strategy improves the overall power grid system resilience [39].…”