Search

Non-technical losses (NTL) 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 NTL detection. The model has been trained and tested with real smart meter data of Endesa, the largest electricity utility in Spain. [ABSTRACT FROM AUTHOR]

This paper describes and analyzes the Spanish AGC system. The differences with respect to a standard hierarchical structure are explained. A simple model useful for simulation is proposed. Using this model, the performance of the system and the influence of several parameters in system response is evaluated. The paper also suggests some changes in the configuration and parameter settings of the system to improve its performance. [ABSTRACT FROM AUTHOR]

This paper describes the application of sliced inverse regression to model the electrochemical process of aluminum smelter plants. Real data measurements obtained during several years in a Spanish industrial environment are used to illustrate the main dependencies between parameters. Nonlinear relations between the output variables and relevant linear combinations of input variables are deduced. An exploratory statistical analysis is also presented, checking for correlations and possible linear dependencies. [ABSTRACT FROM AUTHOR]

A novel hybrid approach, combining wavelet transform, particle swarm optimization, and adaptive-network-based fuzzy inference system, is proposed in this paper for short-term electricity prices forecasting in a competitive market. Results from a case study based on the electricity market of mainland Spain are presented. A thorough comparison is carried out, taking into account the results of previous publications. Finally, conclusions are duly drawn. [ABSTRACT FROM AUTHOR]

The solution of power system constraints is an important issue that has to be addressed to achieve a fair operation of a competitive electricity market. In the Spanish electricity market, the System Operator (SO) is in charge of determining the technical feasibility of the generation dispatch provided by the Market Operator (MO). An optimal solution method of power system constraints in the Spanish market must take into account the connection of off-line units to solve both branch overloads and voltage constraints, the adjustment of voltage control resources, the solution of the postulated n-I and n-2 contingencies with a preventive criteria and the coupling of the solution in the 24 hourly scenarios due to the start-up cost of nonconnected units. This paper details the management of power system constraints in the Spanish market, and contains a comprehensive review of solution methods of power system constraints. In addition, the paper proposes a novel approach to solve Spanish power system constraints that overcomes the limitations of existing methods, by decoupling the solution of branch overloads and voltage constraints. [ABSTRACT FROM AUTHOR]