Multi-Criteria Spatial Decision Making Supportsystem for Renewable Energy Development in Kazakhstan

IEEE Access

卷:7

Sophia Kiseleva¹  Viktor Gopejenko²  Kirill Yakunin³  Ravil I. Mukhamediev³  Renat Mustakayev⁴ 

[1]Department of Geography, Lomonosov Moscow State University, Moscow, Russia

[2]|Department of Natural Science and Information Technologies, ISMA University, Riga, Latvia

[3]|Institute of Cybernetics and Information Technology, Satbayev University, Almaty, Kazakhstan

[4]|Institute of Information and Computational Technologies, Almaty, Kazakhstan

关键词: Decision making support methods;    geo information systems;    intelligent information technologies;    heterogeneous data;    machine learning;    renewable energy;   

DOI  :  10.1109/ACCESS.2019.2937627

来源: DOAJ

【 摘 要 】

The Republic of Kazakhstan has significant deposits of fossil fuels and is one of the largest energy producers among the countries of Central Asia. At the same time, The Republic of Kazakhstan is one of the richest countries of the world in terms of renewable resources, evaluated to over 1000 billion kWh/year. The application of therenewable energy sources (RES), both on a large scale and at the level of a single household, ensures the transformation of the energy system to a “green state”. However, these initiatives should be substantiated by relevant supportive information to promote transformation of the country's economy to a qualitative ecological state.The paper covers developed multi-criteria decision-making system (MCDM) and software tools for processing of spatial heterogeneous data which could be applied for evaluation of the RES potential.The developed system serves to evaluate the potential of usable RES as it allows the assessment of a territory of the country in terms of installing photovoltaic and wind generators.A feature of the proposed MCDM is the use of an analytical hierarchical process (AHP) in combination with the Bayesian approach, which allows obtaining two complementary assessments of the territory areas. The method allows a rough estimate in an event of lack of data.The verification performed based on the available data on the installed solar and wind power stations shows that the system gives a relatively small root-mean-square error within 15%.

【 授权许可】

Unknown