Artificial intelligence in smart grids

• Thesis title in Czech: Artificial intelligence in smart grids
• Thesis title in English: Artificial intelligence in smart grids
• Academic year of topic announcement: 2016/2017
• Thesis type: dissertation
• Department: Department of Theoretical Computer Science and Mathematical Logic (32-KTIML)
• Supervisor: RNDr. Jiří Fink, Ph.D.
• Author: hidden - assigned and confirmed by the Study Dept.
• Date of registration: 22.09.2017
• Date of assignment: 22.09.2017
• Confirmed by Study dept. on: 03.10.2017

Guidelines

One of the problems Smart Grid faces is forecasting energy consumption of a household. Reliable forecasts can be used by specialized algorithms to anticipate peak consumptions and prevent penalties imposed by electricity companies on exceeding the limit previously agreed in energy supply contract. A common approach to all of the aforementioned problems in Smart Grid is time series analysis. There is a number of techniques frequently used in time series analysis. The student should focus on a selection of state-space models and machine learning methods, and their advantages and disadvantages.

References

James Douglas Hamilton.Time series analysis, volume 2. Princeton university press, 1994
Ryszard S Michalski, Jaime G Carbonell, and Tom M Mitchell. Machine learning: An artificial intelligence approach. Springer Science & Business Media, 2013.
A Sfetsos and AH Coonick. Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques. Solar Energy, 68(2):169--178, 2000.
Amir-Hamed Mohsenian-Rad, Vincent WS Wong, Juri Jatskevich, Robert Schober, and Alberto Leon-Garcia. Autonomous demand-side management based on game-theoretic energy consumption scheduling for the future smart grid. IEEE transactions on Smart Grid, 1(3):320--331, 2010.

Recent papers published in impacted journals, e.g.
Data Mining and Knowledge Discovery, IEEE Transactions on Knowledge and Data Engineering, Machine Learning, IEEE transactions on smart grid