A Flow-Based Model for Conditional and Probabilistic Electricity Consumption Profile Generation and Prediction
This addresses the need for accurate load forecasting in distribution networks as low-carbon technologies proliferate, representing a novel method for a known bottleneck.
The paper tackles the problem of generating and predicting residential electricity consumption profiles by introducing a flow-based generative model called FCPFlow, which achieves superior scalability and better modeling of complex correlations compared to existing methods.
Residential Load Profile (RLP) generation and prediction are critical for the operation and planning of distribution networks, especially as diverse low-carbon technologies (e.g., photovoltaic and electric vehicles) are increasingly adopted. This paper introduces a novel flow-based generative model, termed Full Convolutional Profile Flow (FCPFlow), which is uniquely designed for both conditional and unconditional RLP generation, and for probabilistic load forecasting. By introducing two new layers--the invertible linear layer and the invertible normalization layer--the proposed FCPFlow architecture shows three main advantages compared to traditional statistical and contemporary deep generative models: 1) it is well-suited for RLP generation under continuous conditions, such as varying weather and annual electricity consumption, 2) it demonstrates superior scalability in different datasets compared to traditional statistical models, and 3) it also demonstrates better modeling capabilities in capturing the complex correlation of RLPs compared with deep generative models.