Juan Carlos Burguillo Rial

Self-Adapting Coalition Formation Among Electric Vehicles in Smart Grids

In the last years, the need for using multiple energy sources made the concept of smart grids emerge. A smart grid is a fully automated electricity network, which monitors and controls all its elements being able to supply energy in an efficient and reliable way. Within this context, the use of electric vehicles (EVs) and Vehicle-To-Grid (V2G) technologies have been advocated as an efficient way to reduce the intermittent supply associated with renewable energy sources. However, operating on V2G sessions in a cost effective way is not a trivial task for EVs. To address this problem, the formation of coalitions among EVs has been proposed as a mean to improve profitability on V2G sessions. Addressing these scenarios, in this paper we introduce the Self-Adapting Coalition Formation (SACF) method, which is a local and dynamic heuristic-based mechanism for coalition structure generation. In our approach, coalitions are formed observing constraints imposed by the grid to the EVs, which negotiate locally the formation of feasible coalitions among themselves. Based on experiments, we see that SACF is an efficient method, providing good solutions in a simple and low-cost way. SACF is faster than centralized methods and provides solutions with near optimal quality. In dynamic scenarios, SACF also shows very good results, being able to keep the agents gain relatively stable along time, even in quickly changing environments. Its main advantage is that the computational effort is very low, while classical centralized methods are limited to manage no more than a dozen agents in a reasonable amount of time.

Using semantics in INES, an Intelligent Educational System

INES (INtelligent Educational System) is a functional prototype of an online learning platform, which combines three essential capabilities related to e-learning activities. These capabilities are those related to Learning Management Systems, Learning Content Management Systems, and Intelligent Tutoring Systems. To carry out all these functionalities, our system, as a whole, comprises a set of different tools and technologies, as follows: an intelligent chatterbot which is able to communicate with students in natural language, an intelligent agent based on BDI (Believes, Desires, Intentions) technology which acts as the brain of the system, an inference engine based on JESS (a rule engine for the Java platform), and an ontology. At the present paper we will focus on this ontology, which is used in the platform to provide semantic support for system users (administrators, teachers, and students), their activities, and the learning contents. We will specifically address the architecture and performance of the ontology, and their contribution to INES.

NLAST: A natural language assistant for students

This paper presents a system that works as an assistant for students in their learning process. The assistant system has two main parts: an Android application and a server platform. The Android application is a chatterbot (i.e., an agent intended to conduct a conversation in natural language with a human being) based on AIML, one of the more successful languages for developing conversational agents. The chatterbot acts as an intermediation agent between a student and the server platform. The server platform contains four repositories and a recommender (which are part of a bigger professor assessment system). The final objective of the assistant system is to make a student able to carry out several actions related to his/her learning and assessment processes, such as: to consult exam questions from a repository, to receive recommendations about learning material, to ask questions about a course, and to check his/her own assessed exams. These actions are carried out through and Android application using a natural language interface (by voice or typing). The purpose of this development is to facilitate the access to this information through a friendly interface.

Modeling the Urban Context through the Theory of Roles

Urban environments are intelligent spaces where a wide set of heterogeneous variables that directly influence the behavior of the individual converge. In this paper we present UrbanContext, a new model for urban platforms that follows an individual centered approach and validates the use of the Theory of Roles to understand the behavior of the individual within a social environment. The roles defined in UrbanContext allow the interpretation of the states of the individual, facilitating his interaction with the environment and offering services without damaging his privacy. We describe the UrbanContext model and the fundamental principles that have been identified in this design; likewise we present a first validation scenario for UrbanContext.