Factors of very rapidly rising oil prices, the running out time limits on continued use of fossil fuels, as well as elements of the Kyoto Protocol, have greatly arouses the increasing emphasis on natural and renewable energy sources. 40 minutes of total solar radiation on earth could provide enough power to meet the energy needs of all human beings for approximately one year. The potential of solar energy is virtually limitedless. Moreover, by means of solar powered batteries, solar energy can be directly converted to electric power. Since it neither pollutes the environment or ecology, solar is an extremely clean source of energy. The life-span of solar cell is very long, possibly 20 years or more. The capability of solar batteries to provide energy is approximately proportional to the intensity of the sunlight. This thesis proposes the use of Artificial intelligence for "Sun Track Solar Energy System". This system employs Fuzzy Logic Control Theory, combined with Grey Relational Analysis, for tracking the angle of the sun, and further control the motor to adjust the angle for tracking, so direct sunlight could be acquired to increase power output. As a result of the experiment, comparing the electricity generated from the fix angle solar battery with the AI-based Sun Track Solar Energy System, the latter one has an efficiency increase up to 23% for the same amount of sunlight.

The global use of solar power is growing at an unprecedented rate, making the need toaccurately track the energy generation of decentralised solar energy systems (SES) more andmore relevant. The purpose of this thesis is to further develop a binary image classifier for thesimulation system framework known as Alfrödull, which will be used to detect and segment SESfrom aerial images to simulate the energy generation within a given Swedish municipality on anhourly basis. This project focuses on improving the Alfrödull classifier through four differentanalyses. the first focusing on examining how additional training data from publicly availabledatasets affects the model performance. The second on how the model can be improvedthrough the use of various image pre-processing techniques. The third on how the model canbe improved through balancing the training datasets to make up for the low amount of positiveimages as well as utilising model ensembles for joint classification. Finally, the fourth analysisemploys a sliding window approach to classify overlapping image tiles. The results show thathaving training data that is a good representation of the environment the model will be used in iscrucial, that the use of image augmentation policies can significantly improve modelperformance, that compensating for class imbalance as well as utilising ensemble methodspositively impacts model performance and that a sliding window approach to classifyingoverlapping images significantly decreases the amount of missed SES at the cost of clusters offalsely classified negative images (false positives). In conclusion, this thesis serves as animportant stepping stone in the practical implementation of the Alfrödull framework, showcasingthe key aspects in making a well performing binary image classifier of SES in Sweden.