This is a report about artificial intelligence in the field of computer science. The issue handled is prediction of energy usage in district heating systems. Prediction of energy usage in district heating systems is a tricky problem because of the social behaviors, weather and distribution time that has to be accounted for. One algorithm is offered and three different experiments are made to determine if the algorithm is helpful. The results from the experiments were decent. This report differs in approach to the problem then other reports found in this field. The difference is that this report tries to handle social behaviors and looks at a decentralized view of the problem…
Contents
1. Introduction
2. Background
2.1 District Heating Systems
2.2 Forecasting
2.3 Machine Learning
2.4 Weighted K-Nearest Neighbour
2.5 Genetic Algorithms
2.6 Neural Networks
3. Hypothesis
3.1 Research Questions
4. Goals
5. Delimitations
6. Heat Prediction in District Heating Systems
6.1 Problem description
6.2 The Simulator
6.3 Simulated Experiments
6.4 Experiment Results..
Source: Blekinge Institute of Technology