Short-Term Load Forecasting is a very relevant aspect in managing, operating or participating an electric system. From system operators to energy producers and retailers knowing the electric demand in advance with high accuracy is a key feature for their business. The load series of a given system presents highly repetitive daily, weekly and yearly patterns. However, other factors like temperature or social events cause abnormalities in this otherwise periodic behavior. In order to develop an effective load forecasting system, it is necessary to understand and model these abnormalities because, in many cases, the higher forecasting error typical of these special days is linked to the larger part of the losses related to load forecasting. This paper focuses on the effect that several types of special days have on the load curve and how important it is to model these behaviors in detail. The paper analyzes the Spanish national system and it uses linear regression to model the effect that social events like holidays or festive periods have on the load curve. The results presented in this paper show that a large classification of events is needed in order to accurately model all the events that may occur in a 7-year period.

Artificial Intelligence (AI) has been widely used in Short-Term Load Forecasting (STLF) in the last 20 years and it has partly displaced older time-series and statistical methods to a second row. However, the STLF problem is very particular and specific to each case and, while there are many papers about AI applications, there is little research determining which features of an STLF system is better suited for a specific data set. In many occasions both classical and modern methods coexist, providing combined forecasts that outperform the individual ones. This paper presents a thorough empirical comparison between Neural Networks (NN) and Autoregressive (AR) models as forecasting engines. The objective of this paper is to determine the circumstances under which each model shows a better performance. It analyzes one of the models currently in use at the National Transport System Operator in Spain, Red Eléctrica de España (REE), which combines both techniques. The parameters that are tested are the availability of historical data, the treatment of exogenous variables, the training frequency and the configuration of the model. The performance of each model is measured as RMSE over a one-year period and analyzed under several factors like special days or extreme temperatures. The AR model has 0.13% lower error than the NN under ideal conditions. However, the NN model performs more accurately under certain stress situations.

This paper proposes the use of two indicators of the predictability of the load series along with an accuracy value such as mean average percentage error as standard measures of load forecasting performance. Over the last 10 years, there has been a significant increase in load forecasting models proposed in engineering journals. Most of these models provide a description of the inner design of the model, the results from applying this model to a specific data base and the conclusions drawn from this application. However, a single accuracy value may not be sufficient to describe the performance of the model when applied to other data bases. The aim of this paper is to provide researchers with a tool that is able to assess the predictability of a load series and, therefore, contextualize the forecasting accuracy reported. Nine different data bases from the U.S. have been used; all of them include hourly load and temperature data.

En Psicolingüística y Lingüística computacional las pruebas de libre asociación de palabras han servido tradicionalmente como fuente de datos para desarrollar redes conceptuales que, de diferente forma, simulan el espacio semántico mental de los hablantes de una lengua. La modelación de las redes léxicas se articula habitualmente a través de valores como el número de asociados de cada palabra, la fuerza asociativa y otra serie de factores cuantitativos de diversa índole. Menos abundante es, sin embargo, el número de estudios que cuantifican el entorno de una palabra a través del tipo de relaciones asociativas. Este trabajo realiza un análisis exploratorio de las relaciones semántico-asociativas de 150 palabras en español partiendo de una prueba de libre asociación discreta, con el objetivo de proponer una clasificación de las palabras por medio de las técnicas de los mapas auto-organizados (SOM), con el objetivo de que tanto las variables resultantes basadas en los tipos de asociados como la clasificación de palabras propuesta puedan utilizarse como variables independientes en estudios de psicolingüística experimental, para observar si características semánticas de corte asociativo influyen de algún modo en tareas de procesamiento lingüístico.