Search

Recent years have seen a rapid uptake in distributed energy resources (DER). Such technologies pose a number of challenges to network operators, which ultimately can limit the amount of rooftop solar photovoltaic (PV) systems that can be connected to a network. The objective of this industry-based research was to determine the potential network effects of forecast levels of customer-owned rooftop solar PV on Energy Queensland's distribution network and formulate functions that can be used to determine such effects without the requirement for detailed network modeling and analysis. In this research, many of Energy Queensland's distribution feeders were modeled using DIgSILENT PowerFactory and analyzed with forecast levels of solar PV and customer load. Python scripts were used to automate this process, and quasi-dynamic simulation (QDSL) models were used to represent the dynamic volt–watt and volt–var response of inverters, as mandated by the Australian Standard AS/NZS 4777. In analyzing the results, linear relationships were revealed between the number of PV systems on a feeder and various network characteristics. Regression was used to form trend equations that represent the linear relationships for each scenario analyzed. The trend equations provide a way of approximating network characteristics for other feeders under various levels of customer-owned rooftop solar PV without the need for detailed modeling. [ABSTRACT FROM AUTHOR]

Electricity load forecasting plays an essential role in improving the management efficiency of power generation systems. A large number of load forecasting models aiming at promoting the forecasting effectiveness have been put forward in the past. However, many traditional models have no consideration for the significance of data preprocessing and the constraints of individual forecasting models. Moreover, most of them only focus on the forecasting accuracy but ignore the forecasting stability, resulting in nonoptimal performance in practical applications. This paper presents a novel hybrid model that combines an advanced data preprocessing strategy, a deep neural network, and an avant-garde multi-objective optimization algorithm, overcoming the defects of traditional models and thus improving the forecasting performance effectively. In order to evaluate the validity of the proposed hybrid model, the electricity load data sampled in 30-min intervals from Queensland, Australia are used as a case to study. The experiments show that the new proposed model is obviously superior to all other traditional models. Furthermore, it provides an effective technical forecasting means for smart grid management. [ABSTRACT FROM AUTHOR]