Joint Energy Disaggregation of Behind-the-Meter PV and Battery Storage: A Contextually Supervised Source Separation Approach

Dynamic directed graph convolution network based ultra‐short‐term forecasting method of distributed photovoltaic power to enhance the resilience and flexibility of distribution network

“…However, a large number of DPVs bring great challenges to the reliability and resilience of distribution network, especially for some distribution networks that did not consider DPV integration in early planning. Firstly, the high penetration DPV increases the peak-valley difference of load which is called the duck curve problem [5,6], bringing great challenges to the demand and supply balance of the electricity grid [2,7,8]; secondly, easily affected by the weather variation [9],…”

“…However, a large number of DPVs bring great challenges to the reliability and resilience of distribution network, especially for some distribution networks that did not consider DPV integration in early planning. Firstly, the high penetration DPV increases the peak‐valley difference of load which is called the duck curve problem [5, 6], bringing great challenges to the demand and supply balance of the electricity grid [2, 7, 8]; secondly, easily affected by the weather variation [9], DPV couples its randomness, intermittency, and volatility into the distributed network load and increases the difficulty of net load forecasting [10], which imposes an adverse influence on the scheduling and operation of distribution network; thirdly, when a large amount of DPV output cannot be absorbed, a reverse power flow will form on the feeder, which will lead to serious overvoltage problems in distribution network [11].…”