Investigating factors affecting electricity energy consumption using association rules(Case study: Yazd city)

Extended Abstract:



1. Introduction



Electricity is an essential input for all production systems and a necessity for all modern families. Hence, relevant energy policies are needed to induce efficient electricity consumption in the residential sector in many countries due to the effects of global warming and security of energy supply. Forecasting electricity demand at a regional or national level is crucial for planning to ensure optimal energy management. Various factors influence household consumption patterns. Factors such as employment rate, residential area, distance from green space, etc. affect electricity consumption. The purpose of this study is to investigate the impact of various factors on electricity consumption in residential homes in Yazd city. The results of this study will be useful for making management decisions for planning to reduce electricity consumption.

2. Research Methodology



The present study was conducted in the city of Yazd, which has a hot and dry climate and is extremely hot in the summer. Data on electricity consumption of Yazd city subscribers was obtained from the provincial electricity distribution company for the years 2016 to 2019. Data related to the city's buildings, such as (current use, building height, area, building shape, and building age), as well as streets, existing street widths, and the location of parks and green spaces, were obtained from the municipality. Spatial configuration indices including: connectivity, depth, coherence and control were estimated. The urban physical parameters of the components of parcel area, building area, yard area, building height, building volume were calculated. Then, association rules were used to examine the existing relationships. Spatial Association Rules are a set of rules that describe the relationships between different features in spatial data. These rules are a capability to find unknown relationships in spatial data. Spatial association rules are rules that indicate the implication of a set of features on another set of features in a spatial database. These rules are introduced to discover the rules between products in large-scale transactional data.

3. Results and discussion



Residential electricity consumption data was analyzed using Moran's spatial autocorrelation index and based on Euclidean distance. The results of the study of hot and cold spots of residential electricity consumption data in the study area showed that the distribution of electricity consumption in residential homes is asymmetrical. That is, the number of homes with very high electricity consumption is greater than the number of homes with very low electricity consumption.In total, 3.2 percent of the number of parcels in the region is made up of Low_High outliers and 4.7 percent is High_Low. In the present study, the Apriori algorithm was used. The Apriori algorithm is known as one of the main methods in data mining for discovering association rules. The results of the rule review using Apriori showed that in rule one: buildings with a height of 5 to 8 meters that are located in a new urban context are most likely (93%) to have an annual electricity consumption of more than 3,500 units. Rule two: buildings that are located in a new urban context and their control is less than 1 are most likely (87%) to have an annual electricity consumption of more than 3,500 units. Rule three: buildings that are located in parcels with an area of 150 to 250 square meters and a local connectivity of 2-3 are most likely (74%) to have an annual electricity consumption of more than 3,500 units. Rule four: buildings that are located in parcels with an area of 150 to 250 square meters and in a new urban context and with a yard area of less than 75 square meters are most likely (61%) to have an annual electricity consumption of more than 3,500 units.



4. Conclusion



Association rules are able to extract patterns that cannot be easily identified by traditional methods and provide useful information for optimizing energy consumption.One of the major challenges in using association rules in big data is the need for time-consuming and resource-intensive processing, especially when the data is complex and contains a large number of features. Association rules are usually designed for discrete data, and for numerical data, complex preprocessing such as converting the data to categorical values may be required. Also, the appropriate selection of parameters such as minimum support and confidence can be difficult and have a significant impact on the quality and applicability of the extracted results. It is suggested that in future studies, hourly electricity consumption data should be used if possible so that the effects of more factors can be examined. -