No abstract

Occupant behavior (OB) has a significant impact on household air-conditioner (AC) energy use. In recent years, bottom-up simulation coupled with stochastic OB modeling has been intensively developed for estimating residential AC consumption. However, a comprehensive analysis of the diverse behavioral preference patterns of occupants regarding AC use is hampered by the limited availability of large-scale residential energy demand data. Therefore, this study aimed to develop a prediction model for the residential household’s AC usage considering various OB-related diversity patterns based on monitoring data of appliance-level electricity use in a residential community of 586 households in Osaka, Japan. First, individual operation schedules and thermal preferences were identified and quantitatively extracted as the two main factors for the diverse behaviors across the whole community. Then, a clustering analysis classified the target households, finding four typical patterns for schedule preferences and three typical patterns for thermal preferences. These results were used, with time and meteorological data in the summer seasons of 2013 and 2014, as inputs for the proposed prediction model using Extreme Gradient Boosting (XGBoost). The optimized XGBoost model showed a satisfactory prediction performance for the on/off state in the testing dataset, with an F1 score of 0.80 and an Area under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.845.

The diverse occupant's behaviour (OB) has been identified as a significant impact on household air-conditioner (AC) energy use. However, the stochastic feature of occupant's individual preference in AC use is seldom studied due to the limitation of appliance-level energy data. This study aims to analyze the inter-occupant OB diversity based on the monitoring bigdata of AC load in a residential community of 586 households in Osaka, Japan. First, household's thermal preference was quantitatively identified from AC load profiles. Clustering analysis is then employed for labeling and classification of the target households with different thermal preference types. Results show 4 typical behavioral patterns, namely sensitive & active users, sensitive but inactive users, insensitive but active users, insensitive & inactive users, with a share of dwellings in the community of 36%, 31%, 19%, and 14%, respectively. Such household-level benchmarking could provide an informative reference for the modeling and simulation of residential AC usage.

The residential air-conditioning load (ACL) has been identified as a key contributor to demand peaks, especially in the summer season. Occurrence of such intensive electricity loads has been a challenge for generation and transmission networks to ensure the necessary supply capacity. However, the comprehensive analysis of the characteristics of residential AC use in the real community has been hampered by the limited availability of appliance level interval consumption data. This study used appliance level data measured by smart meters in a residential community of 586 households in Osaka, Japan, to evaluate the contribution of the ACL to the total demand peak in the summer season. The target households were classified into several groups based on their cooling usage preferences and introduced into two different demand response (DR) scenarios. The DR potentials for each group of households were compared to assess the peak reduction effectiveness in not only the whole community but also different groups of customers.