Real-Time Energy Disaggregation at Substations With Behind-the-Meter Solar Generation

Energy Disaggregation at substations (EDS) is challenging because measurements are mostly aggregated over multiple types of loads, and the existence of some loads such as behind-the-meter solar is unknown to the operator. This paper for the first time addresses this so-called “partial labels” issue in energy disaggregation and develops a model-free EDS method to separate individual loads, including BTM solar, from the total energy consumption in real-time. Our approach learns the patterns of all loads offline from recorded historical datasets with partial labels. Compared with conventional model-free methods that require either pure measurements of each load for training or full labels of each training sample, our method can extract load patterns from partially labeled aggregated data and thus, is more applicable to practical scenarios and alleviates the annotation burden for the operator. Specifically, we propose to solve a new dictionary learning problem, where column-sparsity and incoherence regularization terms are added to identify unlabeled loads and learn distinctive patterns of each load. In real-time disaggregation, our approach solves an improved sparse decomposition problem where one decomposes the aggregated measurements as a linear combination of some representative recorded measurements with known disaggregation learned in the offline stage. Numerical experiments are reported to validate our method.

I. Introduction

Although modern meters are installed at some residential households, commercial buildings, and the output of solar farms and wind turbines, the coverage in distribution systems is still very sparse such that the visibility is not comparable to that of transmission systems. The power consumption measured at a substation is the net consumption of all the industrial loads, residential users, and renewable (like solar or wind) generations that are connected to this substation, and the operator does not have separate measurements for each type of load.¹

Both loads and renewable generations are referred to as “load” to simplify the presentation in this paper. Renewable generation is considered as a negative load.

The objective of energy disaggregation at the substation level (EDS) is to extract the energy consumption of each type of load from the aggregated net load measurements. EDS becomes increasingly challenging due to behind-the-meter (BTM) solar generations, which are not directly measured by the operator. Accurate real-time estimation of various loads, especially BTM solar, is necessary for distribution systems planning and operations such as hosting capacity analysis [1], distribution network reconfiguration [2], Volt Var control [3], load forecasting [4], and demand response [5].