Application of machine learning methods for the analysis of thermal energy consumption in Astana

Scientists of Astana IT University published another article in the journal indexed in the Scopus database (CiteScore- 1.8. Percentile – 55, Q2) as part of the Smart City project.

The ecological situation in the capital is always in the center of attention of the municipal authorities of the city and is one of the most important factors influencing the decisions made. Astana, the capital of Kazakhstan, consumes thermal energy generated from fossil fuels. As a result, greenhouse gas emissions and particulate matter from coal-fired CHP plants have a significant impact on the environment in the form of smog, especially during the heating season.

The paper analyzes high-resolution spatial Big Data collected from metering points of 385 houses and 62 heat transfer circuits in the city during the heating season. The time resolution was 10 minutes, i.e. 8754 lines for 5 months (January-May).

Over the past eight years, the volume of heat energy consumption through centralized heat and steam pipelines has grown by 40.4% and amounted to 8.48 million Gcal in 2021 (Figure 1). The increase in the level of heat consumption is due to high population growth rates and intensive housing construction.

The article presents the results of the analysis of correlation indicators between the consumption of thermal energy in the zones of the city of Astana and the ambient temperature. Mixed modeling and machine learning approaches such as Linear Regression, Kneighbours Regressor and Random Forest Regressor models have been used to develop smart city heat consumption forecasting tools.

Data sources: Bureau of National Statistics of the Republic of Kazakhstan www.stat.gov.kz and municipal authorities: www.a-tranzit.kz. *Data for 2021 is not yet categorized.

Figure 1. The level of consumption of thermal energy, thousand Gcal

The study was financially supported by the Committee of Science of the Ministry of Education and Science of the Republic of Kazakhstan (grant No. BR10965311 “Development of intelligent information and telecommunication systems for municipal infrastructure: transport, ecology, energy and data analytics in the concept of a smart city”).

You can read more in the open access article:

Omirgaliyev, R., Zhakiyev, N., Aitbayeva, N., Akhmetbekov, Y. (2022). Application of machine learning methods for the analysis of heat energy consumption by zones with a change in outdoor temperature: Case study for Astana city. International Journal of Sustainable Development and Planning, Vol. 17, no. 4, pp. 1247-1257.https://doi.org/10.18280/ijsdp.170423

Leave a Reply