Designing an Expert Climate Improvement System with Pattern Finding of Cold Climate Residential Buildings based on Learning Models

Purpose: With the increasing growth of energy consumption in the modern world and the position of the construction industry as one of the important factors in creating and exacerbating this crisis, the emergence and emergence of a complex issue called "energy supply and consumption management" is occurring, which, in addition to affecting the sustainable development of societies, is of particular importance in terms of its tremendous impact on the healthy lives of humans. The present study aims to design a decision-making system for maximum utilization of solar energy (passive) in supplying the energy needed by the residents of a residential building (information entity), taking into account the minimum amount of energy loss, based on the appropriate design of the outer shell without the need to install additional electrical equipment.

Method: The research method in the present study is a combination of descriptive, experimental, analytical, and comparative research, and has characteristics such as being indigenous, relying on Iranian data and laws, and being able to be developed based on climatic data. The integrated approach of the research is influenced by the concepts of knowledge management, decision-making systems, expert system rule construction, and the use of learning models in the specialized field of residential building architecture, with the approach of addressing a real problem. With the aim of building the desired knowledge set, the characteristics related to the site of the desired plan, with an emphasis on geographical coordinates, the characteristics related to the building shell, including: building dimensions and openings, etc., as well as the characteristics related to energy waste, were examined as criteria and sub-criteria for information production. In line with the aforementioned goal and considering the environmental comfort of residents in a climate with high heating needs (Zanjan city located in a cold climate), a technical study of the issue was conducted by modeling the condition of residential buildings in ten areas of Zanjan city, including 100 buildings, using a simple random sampling method. Next, the potential for climate improvement of the outer shell was assessed from the perspective of three methods: direct absorption, Trombe wall, and solar space. For the desired modeling, a dataset of over 3,500 information fields was used using statistics and as a sample of the statistical population. To collect information, a combination of field data collection methods, review of descriptive information layer information in the detailed plan, and information from aerial maps for selected residential lots were used. The validity criterion for the output status of the models was calculated based on the climate energy label criterion with the aim of calculating the ability of the residential building form to receive solar energy. The complexity of the problem was managed in a multi-part process based on examining the climate in terms of temperature and solar radiation changes, examining fixed urban development characteristics centered on the site plan, and utilizing the relevant decision matrix. Then, achieving the lowest amount of energy loss (thermal transfer and heat dissipation) along with the highest absorption from the perspective of the implementation status of passive solar systems was made the criterion for action by presenting a new concept called the climate energy label (production of training and test data). Next, using three learning models: decision tree, association rules, and Bayes theory, it was analyzed and implemented with the aim of producing the rules required to design the knowledge base required for a decision-making expert system.

Findings: An analysis of the feasibility of implementing passive solar energy methods revealed that among the ten areas studied in the city of Zanjan (cold climate), the implementation of the solar greenhouse method was prioritized, followed by the implementation of direct absorption and Trombe wall methods. In addition to prioritizing features in the structured resolution of the problem space and having a positive impact on the forward inference chains used in the inference engine of the proposed expert system, the research findings produced appropriate performance (with a confidence factor of over 85 percent), which, considering the high complexity of the problem, indicates the acceptable accuracy of the prediction models and also implicitly guarantees the accuracy of the rules derived from them in forming the inference database.

Conclusion: The results can be useful as an auxiliary knowledge system in the improvement of existing residential buildings for decision-making and decision-making organizations, as well as in generating design recommendations in the complex problem of existing energy imbalance.