Learning customer behavior for effective load forecasting
RIS ID
128760
Abstract
Load forecasting has been deeply studied because of its critical role in Smart Grid. In current Smart Grid, there have been various types of customers with different energy consumption patterns. A customer's energy consumption pattern is referred as customer behavior. It would significantly benefit load forecasting in a grid if customer behavior could be taken into account. This paper proposes an innovative method that aggregates different types of customers by their identified behaviors, and then predicts the load of each customer cluster, so as to improve load forecasting accuracy of the whole grid. Sparse Continuous Conditional Random Fields (sCCRF) is proposed to effectively identify different customer behaviors through learning. A hierarchical clustering process is then introduced to aggregate customers according to the identified behaviors. Within each customer cluster, a representative sCCRF is fine-tuned to predict the load of its cluster. The final load of the whole grid is obtained by summing the loads of each cluster. Experiments conducted from different perspectives demonstrate the advantages of the proposed load forecasting method. A further discussion is provided, indicating that the approach of learning customer behavior can be extended as a general framework to facilitate decision making in other market domain
Publication Details
Wang, X., Zhang, M. & Ren, F. (2019). Learning customer behavior for effective load forecasting. IEEE Transactions on Knowledge and Data Engineering, 31 (5), 938-951.