This paper reports new results in adopting information theoretic learning concepts in the training of neural networks to perform wind power forecasts. The forecast “goodness” is discussed under two paradigms: one is only concerned in measuring the deviation between the forecasted and realized values, the other is related with the value of the forecast in the electricity market for different agents. The results and conclusions are supported by a real case example.

This paper describes development and experiences from the Nordic region and the current status and trend toward an integrated and open electricity market comprising most of Europe. The paper describes practical experiences as well as theoretical investigations and modeling studies. We focus on the following subjects: Congestion management: There are a variety of arrangements for transfer across national borders and for congestion management in Europe. A common future system based on an improved version of the Nordic market splitting system can be a good alternative. Management of ancillary services: We see certain trends concerning ancillary services in the Nordic market: 1) more focus on cost effectiveness and a move toward market arrangements including cross border trade in ancillary services; 2) increased use of the demand side in the provision of ancillary services; and 3) increased flexibility in defining the demand for ancillary services. Investment incentives: Experience as well theoretical investigations indicate that investment in generating capacity is a problem in an open electricity market, where investors are exposed to high risk and uncertainty. One important conclusion from our studies is that end user response (elasticity) to electricity prices is important in an open market. We also discuss how additional incentive mechanisms can be used as a measure to achieve capacity adequacy, when the market fails to provide sufficient signals for new investments.