Combining Unsupervised and Supervised Learning for Asset Class Failure Prediction in Power Systems

In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities towards developing cost-effective asset management strategies. Previously, physical age based Weibull distribution has been widely used to failure prediction. However, this mathematical model cannot incorporate asset condition data such as inspection or testing results. As a result, the prediction cannot be very specific and accurate for individual assets. To solve this important problem, this paper proposes a novel and comprehensive data-driven approach based on asset condition data: K-means clustering as an unsupervised learning method is used to analyze the inner structure of historical asset condition data and produce the asset conditional ages; logistic regression as a supervised learning method takes in both asset physical ages and conditional ages to classify and predict asset statuses. Furthermore, an index called average aging rate is defined to quantify, track and estimate the relationship between asset physical age and conditional age. This approach was applied to an urban distribution system in West Canada to predict medium-voltage cable failures. Case studies and comparison with standard Weibull distribution are provided. The proposed approach demonstrates superior performance and practicality for predicting asset class failures in power systems.

A Hybrid Long-Term Load Forecasting Model for Distribution Feeder Peak Demand using LSTM Neural Network

Long Short-Term Memory (LSTM) neural network is an enhanced Recurrent Neural Network (RNN) that has gained significant attention in recent years. It solved the vanishing and exploding gradient problems that a standard RNN has and was successfully applied to a variety of time-series forecasting problems. In power systems, distribution feeder long-term load forecast is a critical task many electric utility companies perform on an annual basis. The goal of this task is to forecast the load change on existing distribution feeders for the next few years. The forecasted results will be used as input in long-term system planning studies to determine necessary system upgrades so that the distribution system can continue to operate reliably during normal operation and contingences. This research proposed a comprehensive hybrid model based on LSTM neural network for this classic and important forecasting task. It is not only able to combine the advantages of top-down and bottom-up forecasting models but also able to leverage the time-series characteristics of multi-year data. This paper firstly explains the concept of LSTM neural network and then discusses the steps of feature selection, feature engineering and model establishment in detail. In the end, a real-world application example for a large urban grid in West Canada is provided. The results are compared to other models such as bottom-up, ARIMA and ANN. The proposed model demonstrates superior performance and great practicality for forecasting long-term peak demand for distribution feeders.