Power distribution networks are increasingly challenged by ageing plant, environmental extremes and previously unforeseen operational factors. The combination of high loading and weather conditions is responsible for large numbers of recurring faults in legacy plants which have an impact on service quality. Owing to their scale and dispersed nature, it is prohibitively expensive to intensively monitor distribution networks to capture the electrical context these disruptions occur in, making it difficult to forestall recurring faults. In this paper, localised weather data are shown to support fault prediction on distribution networks. Operational data are temporally aligned with meteorological observations to identify recurring fault causes with the potentially complex relation between them learned from historical fault records. Five years of data from a UK Distribution Network Operator is used to demonstrate the approach at both HV and LV distribution network levels with results showing the ability to predict the occurrence of a weather related fault at a given substation considering only meteorological observations. Unifying a diverse range of previously identified fault relations in a single ensemble model and accompanying the predicted network conditions with an uncertainty measure would allow a network operator to manage their network more effectively in the long term and take evasive action for imminent events over shorter timescales.

The operation of distribution networks has become more challenging in recent years with increasing levels of embedded generation and other low carbon technologies pushing these towards their design limits. To identify the nature and extent of these challenges, network operators are deploying monitoring equipment on low voltage feeders, leading to new insights into fault behaviour and usage characterisation. With this heightened level of observability comes the additional challenge of finding models that translate raw data streams into outputs on which operational decisions can be based or supported. In this paper, operational low voltage substation and feeder monitoring data from a UK distribution network is used to identify fault occurrence relations to localised meteorological data, characterise the localised network sensitivities of demand dynamics and infer the effects of embedded generation not visible to the network operator. These case studies are then used to show how additional operational context can be provided to the network operator through the application of analytics.