Application of neural networks and evolutionary algorithms to solve energy optimization and unit commitment for a smart city

Title:

Application of neural networks and evolutionary algorithms to solve energy optimization and unit commitment for a smart city

Creator:

Garlík, Bohumír

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:f402f918-ac7d-49ee-87a9-b9ab73a5e579
uuid:f402f918-ac7d-49ee-87a9-b9ab73a5e579
doi:10.14311/NNW.2018.28.022

Subject:

simulated annealing, unit commitment, micro grid, smart area, fuzzy number, and optimization

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

The optimization problem of two or more special-purpose functions of the energy system is subjected to an analysis. Based on experience of our research and general knowledge of partial solutions of energy system optimization at the level of control of production and power energy supply by energy companies in the Czech Republic, a special-purpose (cost) function has been defined. By analysing the special-purpose function, penalty and limitations have been defined. Using the fuzzy logic, a set of suitable solutions for the special-purpose function is accepted. An optimum of the special-purpose function is looked for using the simulated annealing method. The history of electricity consumption is sorted by day and by hour, representing the multidimensional data. When using the cluster analysis, type daytime diagrams of consumption are defined. Type daytime diagrams form prototypes of identified clusters. The so-called self-organizing neural network with Kohonen map attached is used to perform the cluster analysis. The result of our research is presented by an experiment.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2018 Volume:28 | Number:4

Harvested from:

CDK

Metadata only:

false