Abstract

Abstract
Preliminary filtering of a large decision set can be an important issue in multicriteria problems. Besides eliminating dominated solutions, it is usual to define aspiration levels in some or all the attributes, and then eliminate all the solutions that do not respect the imposed limits. This procedure may lead to the undesired elimination of possibly interesting solutions, due to the irrelevant violation of a specified limit. In this paper, a new method is presented that overcomes this problem by defining the concept of accepted solution as a fuzzy set and calculating a degree of acceptance for each solution that takes values in the interval [0, 1] instead of having only the crisp {0, 1} values. The method also deals with fuzzy attributes, and has an additional feature of advising the decision maker regarding the definition of the acceptance level that leads to selection or exclusion of an alternative. To illustrate the application of the fuzzy filtering method (FFM), a planning problem in the area of power distribution systems is used. The example shows how FFM can be used to reduce an initial set of 48 plans, according to the expressed aspiration levels.

Abstract
This paper provides a description of a new approach for steady-state security evaluation, using fuzzy nearest prototype classifiers. The basic method has an offline training phase, used to design the fast classifiers for online purposes, allowing more than the two traditional security classes. A battery of these fuzzy classifiers, valid for a specific configuration of the network, is adopted to produce a global evaluation for all relevant single contingencies. An important feature of this approach is that it selects automatically the most appropriate number of security clusters for each selected contingency. Natural language labeling is also used to produce standardized sentences about the security level of the system, improving in this way the communication process between the system and the operator. The paper is completed by an example on a realistic model of the Hellenic Interconnected power system, where seven contingencies were simulated.

Abstract
In this paper, CARE an advanced control system for the optimal operation and management of isolated power systems with increased wind power integration, is presented. This control system minimises the production costs through an on-line optimal scheduling of the power units, which takes into account the technical constraints of the thermal units, as well as short-term forecasts of the load and the renewable resources. The power system security is maximised through on-line security assessment modules, which predict the power system capacity to withstand pre-selected disturbances caused by power variations from both the renewable and thermal power sources or from faults.In this paper, CARE an advanced control system for the optimal operation and management of isolated power systems with increased wind power integration, is presented. This control system minimizes the production costs through an on-line optimal scheduling of the power units, which takes into account the technical constraints of the thermal units, as well as short-term forecasts of the load and the renewable resources. The power system security is maximized through on-line security assessment modules, which predict the power system capacity to withstand pre-selected disturbances caused by power variations from both the renewable and thermal power sources or from faults.

Abstract
The paper describes the on-line dynamic security assessment functions developed within the European Union, DGXII programme, CARE. These functions are based exclusively on the application of machine learning techniques. A description of the problem and the data set generation procedure for the Crete island power system are included. Comparative results regarding performances of Decision Trees, Kernel Regression Trees and Neural Networks are presented and discussed.The paper describes the on-line dynamic security assessment functions developed within the European Union, DGXII programme, CARE. These functions are based exclusively on the application of machine learning techniques. A description of the problem and the data set generation procedure for the Crete island power system are included. Comparative results regarding performances of Decision Trees, Kernel Regression Trees and Neural Networks are presented and discussed.

Abstract
This paper describes the main steps needed to apply neural networks in the domain of dynamic security assessment (DSA). The paper provides also an overview of the application of neural networks in DSA. Special emphasis is given to the application of this approach in a medium size real system where a large penetration of wind power is foreseen.