Non-technical electricity losses due to anomalies or frauds are accountable for important revenue losses in power utilities. Recent advances have been made in this area, fostered by the roll-out of smart meters. In this paper, we propose a methodology for non-technical loss detection using supervised learning. The methodology has been developed and tested on real smart meter data of all the industrial and commercial customers of Endesa. This methodology uses all the information the smart meters record (energy consumption, alarms and electrical magnitudes) to obtain an in-depth analysis of the customer’s consumption behavior. It also uses auxiliary databases to provide additional information regarding the geographical location and technological characteristics of each smart meter. The model has been trained, validated and tested on the results of approximately 57000 on-field inspections. It is currently in use in a non-technical loss detection campaign for big customers. Several state-of-the-art classifiers have been tested. The results show that extreme gradient boosted trees outperform the rest of the classifiers.

Non-technical losses in electricity utilities are responsible for major revenue losses. In this paper, we propose a novel end-to-end solution to self-learn the features for detecting anomalies and frauds in smart meters using a hybrid deep neural network. The network is fed with simple raw data, removing the need of handcrafted feature engineering. The proposed architecture consists of a long short-term memory network and a multi-layer perceptrons network. The first network analyses the raw daily energy consumption history whilst the second one integrates non-sequential data such as its contracted power or geographical information. The results show that the hybrid neural network significantly outperforms state-of-the-art classifiers as well as previous deep learning models used in non-technical losses detection. The model has been trained and tested with real smart meter data of Endesa, the largest electricity utility in Spain.

With the continuous increase in the number and relevance of electric transmission lines and distribution networks, there is a higher exposure to the magnetic fields generated by them, leading to more cases of human electrosensitivity, which greatly necessitates the design and development of magnetic field mitigation procedures and, at the same time, the need to minimize both performance degradation and deterioration in the efficiency as well. During the last four decades, fruitful results have been reported about extremely low frequency magnetic field mitigation, giving a wide variety of solutions. This survey paper aims to give a comprehensive overview of cost-effective optimization techniques destined to magnetic field mitigation in power systems, with particular attention to the results reported in the last decade.

This paper analyzes the thermal effects derived from the use of different screen shapes when shielding the magnetic field generated by underground power cables. A parametric analysis is developed to show the influence of the geometrical and the electrical parameters of the shield on the maximum temperature achieved by the power cables in order to analyze the impact of this technique on the ampacity of the line. A 2-D finite element approach is employed in this study to verify the performance of different types of screens (horizontal plate, reverse-U, and H-layout) in terms of shielding efficiency, overheating of the power cables, and operational costs.

This paper analyzes different ways to electromagnetically simulate three-core armored cables in 3D by means of the finite element method. Full periodic models, as lengthy as 36 m, are developed to evaluate the accuracy when simulating only a small portion of the cable, as commonly employed in the literature. The adequate length and boundary conditions for having the same accuracy of full periodic models are also studied. To achieve this aim, five medium voltage and high voltage armored cables are analyzed, obtaining the minimum length of the cable that may be simulated for having accurate results in shorter time and with less computational burden. This also results in the proposal of a new method comprising the advantages of short geometries and the applicability of periodic boundary conditions. Its accuracy is compared with experimental measurements and the International Electrotechnical Commission (IEC) standard for 145 kV and 245 kV cables. The results show a very good agreement between simulations and measurements (errors below 4%), obtaining a reduction in the computation time of about 90%. This new method brings a more effective tool for saving time and computational resources in cable design and the development of new analytical expressions for improving the IEC standard.