The world is right now in a global transition from a fossil fuel dependency towards an electrified society based on green and renewable energy. Investments in power grid capacity are therefore needed to meet the increased future demand which this transition implicates. One part of this is the expansion of intermittent energy sources, such as wind and solar power. Even though these sources have benefits in form of cheap and green energy, they have other characteristics that need to be addressed. Per definition, intermittent power sources cannot produce energy on demand since they are dependent on weather conditions such as wind and sun. This induces a second problem which is that it can be hard to predict the production from intermittent power sources, especially wind, which increases the volatility in the power market. Because of these characteristics, the expansion of wind power has increased the volume traded on the intraday power market. The intermittent energy surge, emphasizes the need of a good trading strategy for balance responsible parties to handle the increased trading volume and volatility. The prupose of this report is to introduce the elements which affect intraday power trading, formulate the fundamentals of a power trading strategy and thereafter explore how predictive models can be used in such a strategy. This includes predicting regulating and intraday market prices using linear regression models, neural networks and LSTM-models. Furthermore, the report highlights underlying properties which affects the predictive power of a prediction model used to forecast wind power production. Regulating prices can be predicted well using both linear regression models and more complex deep learning models based on weather and market data. Both approaches are better than using a simple model based on the latest regulating and market price, since the simple model tends to fall short in a volatile market. Overall, the deep learning models performs the best.  The difference in result when predicting the volume weighted average price on the intraday market, using linear regression and machine learning, are not as substantial. In fact, the linear models tends to outperform the machine learning models in some instaces. The conclusion when analyzing how underlying properties affect wind power prediction models is that how far ahead the model predicts is not the key factor affecting predictive power. Instead, the production volume predicted has a larger effect.