Forecasting overhead distribution line failures using weather data and gradient-boosted location, scale, and shape models
Antoni M. Sieminski, Carl R. Donovan
备注：
25 pages, 7 figures, based on the MSc dissertation of the primary author submitted for the MSc degree in Applied Statistics and Datamining at the University of St Andrews in 2021 -- under the supervision of the co-author
Overhead distribution lines play a vital role in distributing electricity, however, their freestanding nature makes them vulnerable to extreme weather conditions and resultant disruption of supply. The current UK regulation of power networks means preemptive mitigation of disruptions avoids financial penalties for distribution companies, making accurate fault predictions of direct financial importance. Here we present predictive models developed for a UK network based on gradient-boosted location, scale, and shape models, providing spatio-temporal predictions of faults based on forecast weather conditions. The models presented are based on (a) tree base learners or (b) penalised smooth and linear base learners -- leading to a Generalised Additive Model (GAM) structure, with the latter category of models providing best performance in terms of out-of-sample log-likelihood. The models are fitted to fifteen years of fault and weather data and are shown to provide good accuracy over multi-day forecast windows, giving tangible support to power restoration.
The reliable power system operation is a major goal for electric utilities, which requires the accurate reliability forecasting to minimize the duration of power interruptions. Since weather conditions are usually the leading causes for power interruptions in the smart grid, especially for its distribution networks, this paper comprehensively investigates the combined effect of various weather parameters on the reliability performance of distribution networks. Specially, a multilayer perceptron (MLP) based framework is proposed to forecast the daily numbers of sustained and momentary power int…
Texas Tech University（德克萨斯理工大学）；Kinetica db Inc.（Kinetica数据库公司）
A robust model for time series forecasting is highly important in many domains, including but not limited to financial forecast, air temperature and electricity consumption. To improve forecasting performance, traditional approaches usually require additional feature sets. However, adding more feature sets from different sources of data is not always feasible due to its accessibility limitation. In this paper, we propose a novel self-boosted mechanism in which the original time series is decomposed into multiple time series. These time series played the role of additional features in which the…
PALO ALTO NETWORKS（帕洛阿尔托网络公司）；ADVANCED APPLIED AI RESEARCH（高级应用人工智能研究院）
Time series forecasting is a fundamental task emerging from diverse data-driven applications. Many advanced autoregressive methods such as ARIMA were used to develop forecasting models. Recently, deep learning based methods such as DeepAr, NeuralProphet, Seq2Seq have been explored for time series forecasting problem. In this paper, we propose a novel time series forecast model, DeepGB. We formulate and implement a variant of Gradient boosting wherein the weak learners are DNNs whose weights are incrementally found in a greedy manner over iterations. In particular, we develop a new embedding ar…
Ryerson University（瑞尔森大学）；University of Toronto（多伦多大学）；Bogazici University（博阿齐奇大学）
Time series forecasting involves collecting and analyzing past observations to develop a model to extrapolate such observations into the future. Forecasting of future events is important in many fields to support decision making as it contributes to reducing the future uncertainty. We propose explainable boosted linear regression (EBLR) algorithm for time series forecasting, which is an iterative method that starts with a base model, and explains the model's errors through regression trees. At each iteration, the path leading to highest error is added as a new variable to the base model. In th…
Weather-Informed Probabilistic Forecasting and Scenario Generation in Power Systems
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（工业与系统工程系，佐治亚理工学院）；AI Institute for Advances in Optimization（优化前沿人工智能研究所）
Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong SAR China（香港科技大学计算机科学与工程系）；Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China（南方科技大学计算机科学与工程系）；School of Computer and Information Sciences, University of Newcastle, Newcastle, Australia（新castle大学计算机与信息科学学院）；Hangzhou Innovation Institute of Beihang University, Hangzhou, China（北京航空航天大学杭州创新研究院）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）
Long Short-Term Memory (LSTM) is a well-known method used widely on sequence learning and time series prediction. In this paper we deployed stacked LSTM model in an application of weather forecasting. We propose a 2-layer spatio-temporal stacked LSTM model which consists of independent LSTM models per location in the first LSTM layer. Subsequently, the input of the second LSTM layer is formed based on the combination of the hidden states of the first layer LSTM models. The experiments show that by utilizing the spatial information the prediction performance of the stacked LSTM model improves i…
This paper describes the practical application of causal extrapolation of sequences for the purpose of forecasting. The methods and proofs have been applied to simulations to measure the range which data can be accurately extrapolated. Real world data from the Australian Stock exchange and the Australian Bureau of Meteorology have been tested and compared with simple linear extrapolation of the same data. In a majority of the tested scenarios casual extrapolation has been proved to be the more effective forecaster.
We discuss an approach to probabilistic forecasting based on two chained machine-learning steps: a dimensional reduction step that learns a reduction map of predictor information to a low-dimensional space in a manner designed to preserve information about forecast quantities; and a density estimation step that uses the probabilistic machine learning technique of normalizing flows to compute the joint probability density of reduced predictors and forecast quantities. This joint density is then renormalized to produce the conditional forecast distribution. In this method, probabilistic calibrat…
In order to enable the transition towards renewable energy sources, probabilistic energy forecasting is of critical importance for incorporating volatile power sources such as solar energy into the electrical grid. Solar energy forecasting methods often aim to provide probabilistic predictions of solar irradiance. In particular, many hybrid approaches combine physical information from numerical weather prediction models with statistical methods. Even though the physical models can provide useful information at intra-day and day-ahead forecast horizons, ensemble weather forecasts from multiple …
Prediction of various weather quantities is mostly based on deterministic numerical weather forecasting models. Multiple runs of these models with different initial conditions result ensembles of forecasts which are applied for estimating the distribution of future weather quantities. However, the ensembles are usually under-dispersive and uncalibrated, so post-processing is required. In the present work Bayesian Model Averaging (BMA) is applied for calibrating ensembles of wind speed forecasts produced by the operational Limited Area Model Ensemble Prediction System of the Hungarian Meteorolo…
University of Corsica（科西嘉大学）；Hospital of Castelluccio（卡斯泰卢乔医院）；Galatasaray University（加拉塔萨雷大学）；University HouaryBoumédiène（胡阿里·布迈丁大学）
Numerous methods exist and were developed for global radiation forecasting. The two most popular types are the numerical weather predictions (NWP) and the predictions using stochastic approaches. We propose to compute a parameter noted constructed in part from the mutual information which is a quantity that measures the mutual dependence of two variables. Both of these are calculated with the objective to establish the more relevant method between NWP and stochastic models concerning the current problem.
Traditionally, weather predictions are performed with the help of large complex models of physics, which utilize different atmospheric conditions over a long period of time. These conditions are often unstable because of perturbations of the weather system, causing the models to provide inaccurate forecasts. The models are generally run on hundreds of nodes in a large High Performance Computing (HPC) environment which consumes a large amount of energy. In this paper, we present a weather prediction technique that utilizes historical data from multiple weather stations to train simple machine l…
Exploring the impact of weather on Metro demand forecasting using machine learning method
Qiushi Honors College, Tianjin University（天津大学求是学部）；School of Traffic and Transportation, Beijing Jiaotong University（北京交通大学交通运输学院）；Maynooth International Engineering College, Fuzhou University（福州大学梅努斯国际工程学院）；Harbin Institute of Technology（哈尔滨工业大学）；Beijing Forestry University（北京林业大学）
In this article, we propose a novel ensemble technique with a multi-scheme weighting based on a technique called coopetitive soft gating. This technique combines both, ensemble member competition and cooperation, in order to maximize the overall forecasting accuracy of the ensemble. The proposed algorithm combines the ideas of multiple ensemble paradigms (power forecasting model ensemble, weather forecasting model ensemble, and lagged ensemble) in a hierarchical structure. The technique is designed to be used in a flexible manner on single and multiple weather forecasting models, and for a var…
