This paper proposes a multi-data driven hybrid learning method for weekly photovoltaic (PV) power scenario forecast that is coordinately driven by weather forecasts and historical PV power output data. Patterns of historical data and weather forecast information are simultaneously captured to ensure the quality of the generated scenarios. By combining bicubic interpolation and bidirectional long-short term memory (BiLSTM), a super resolution algorithm is first presented to enhance the time resolution of weather forecast data from three hours to one hour and increase the precision of weather forecasting. A weather process-based weekly PV power classification strategy is proposed to capture the coupling relationships between meteorological elements, continuous weather changes and weekly PV power. A gated recurrent unit (GRU)-convolutional neural network (CNN)-based scenario forecast method is developed to generate weekly PV power scenarios. Evaluation indices are presented to comprehensively assess the quality of the generated weekly scenarios of PV power. Finally, the PV power, weather observation and weather forecast data collected from five PV plants located in Northeast Asia are used to verify the effectiveness and correctness of the proposed method.

Microgrid is a typical low-inertia system with uncertainty due to the high penetration of power electronics and renewable energy. Therefore, it is necessary to consider the issue of frequency security when planning microgrids. In this paper, we propose a frequency-constrained optimal planning approach involving both long- and short-term uncertainties to optimally design the critical equipment size for a microgrid while ensuring frequency security in case of a power disturbance. This approach explicitly considers the distinct characteristics of primary frequency responses (e.g., different delivery times) and formulates the frequency constraints as second-order cone constraints. The long-term uncertainties about load demand and unit investment cost of developing technology are addressed by a set of credible scenarios. In each long-term scenario, the short-term uncertainty in the operational stage associated with wind power is described by the Wasserstein-metric ambiguity set. To efficiently solve the proposed model, we first reformulate the distributionally robust joint chance constraint and bilinear terms to enable the proposed model as a mixed-integer second-order cone programming (MISCOP) and then a logic-based Benders decomposition is introduced to solve the MISOCP. Case studies demonstrate the effectiveness and scalability of the proposed method.

This paper proposes a noncooperative game-based planning method for microgrid (MG) considering the interconnection between developing and developed privately-owned clustered MGs on an island. A noncooperative game with imperfect information is designed to regulate the decision-making in planning and operating strategies for rational MG owners. The optimization models for both developing and developed MGs are presented. Different levels of maturity of MG development are modeled by diverse objective functions and constraints, while the data privacy of privately-owned MGs is preserved through imperfect information and prior beliefs. To tackle the seasonality of renewable energy and load on an island, hydrogen storage is considered in the developing MG on the island. Diagonalization and realization are incorporated to develop an effective solving methodology in searching the mixed strategy equilibrium for each MG. The effectiveness of the proposed method is verified using comprehensive case studies.

This paper proposes an optimal planning method for the dual-zero microgrid (DZMG) on an island. The DZMG is the off-grid microgrid that exchanges zero power with entity grids and operates in a net-zero carbon emission mode. A net-zero emission operating strategy is designed considering the positive interaction between $\rm CO_{2}$ flow and energy flow. The multi-scale circulation of $\rm CO_{2}$ flow is realized by coordinating the carbon capture system, solvent storage tank (SST), and direct air capture (DAC), while the seasonal shift of energy flow is completed by the hydrogen storage system (HSS) and DAC. An optimization planning model for DZMG is developed to size the SST, DAC, and HSS optimally. The net-zero emission target and the net-zero operating strategy are involved in the model to balance the environmental and economic concerns in the planning. Numerical experiments are carried out on two IEEE test systems and a real-world island microgrid to validate the effectiveness and adaptability of the proposed method. Simulation results reveal that the proposed method reduces the planning cost by over 25% compared with the extant zero-carbon-based method. Besides, the economy of the DZMG positively correlates to carbon prices and technological maturity, while inversely relates to fuel prices.