Photovoltaic Output Power Estimation and Baseline Prediction Approach for a Residential Distribution Network with Behind-the-Meter Systems

Abstract

Considering that most of the photovoltaic (PV) data are behind-the-meter (BTM), there is a great challenge to implement effective demand response projects and make a precise customer baseline (CBL) prediction. To solve the problem, this paper proposes a data-driven PV output power estimation approach using only net load data, temperature data, and solar irradiation data. We first obtain the relationship between delta actual load and delta temperature by calculating the delta net load from matching the net load of irradiation for an approximate day with the least squares method. Then we match and make a difference of the net load with similar electricity consumption behavior to establish the relationship between delta PV output power and delta irradiation. Finally, we get the PV output power and implement PV-load decoupling by modifying the relationship between delta PV and delta irradiation. The case studies verify the effectiveness of the approach and it provides an important reference to perform PV-load decoupling and CBL prediction in a residential distribution network with BTM PV systems.

An LSTM-SAE-Based Behind-the-Meter Load Forecasting Method

“…A method for BTM PV-load decomposition and customer baseline prediction that considers the net load data, temperature, and solar irradiation was addressed for a residential distribution system. It relies on historical data rather than requiring specific information on individual PV outputs [32]. For the purpose of estimating the average temperature inside a building, Lin et al [33] suggested a hybrid approach for the short-term load forecasting method of the individual user to analyze a dynamic model based on the temperature.…”

A Review on Thermal Energy Modelling for Optimal Microgrids Management

“…The steady-state heating network also needs to meet Kirchhoff's first and second laws. The method in Figure 2 describes the heating network [62][63][64][65].…”

“…Usually, the secondary pipe network is short and the energy consumption is negligible. Therefore, this paper only models the primary pipe network [65]. The nodes where the cogeneration and electric boilers are located are regarded as heat source nodes, and the nodes where the heat exchange stations are located are regarded as load nodes.…”

A deep learning based hybrid method for hourly solar radiation forecasting

“…Most of the existing hybrid methods utilizing the clustering techniques for solar forecasting usually adopt traditional clustering methods (Azimi et al, 2016;Li et al, 2017;Feng et al, 2018;Fu et al, 2019) which may result in sub-optimal clustering outcomes because the feature extraction and clustering are conducted in two separate independent stages rather than jointly considered. Besides, the GHI features (e.g., historical GHI, clear-sky GHI) and the meteorological features (e.g., temperature, wind speed) are often used to forecast the future solar irradiance (Jeno and Kim, 2020;Pan et al, 2020;Wu et al, 2020). The features are treated equally to forecast solar radiation in some previous studies.…”