Data‐driven chance‐constrained dispatch for integrated power and natural gas systems considering wind power prediction errors

Stochastic wind power prediction errors hurt the normal operation of integrated power and natural gas systems (IPGS). First, the data‐driven stochastic chance‐constrained programming method is applied to deal with wind power prediction errors, and its probability distribution is accurately fitted by variational Bayesian Gaussian mixture model with massive historical data. In addition, the data‐driven chance constraints of tie‐line power and reserve capacity of gas turbine are built. Next, to utilize wind power more reasonably, the operational characteristics and optimal commitment of power‐to‐hydrogen devices are considered and modelled in proposed strategy to reflect the actual situation of IPGS. Then, the original complicated dispatch problem is converted into a tractable second‐order cone programming problem via convex relaxation and quantile‐based analytical reformulation techniques. Finally, the effectiveness of the proposed strategy is validated by numerical experiments based on a modified IEEE 33‐bus system integrated with a 10‐node natural gas system and a micro hydrogen system. A data‐driven chance‐constrained dispatch strategyis applied to handle wind power prediction errors, whose probability distribution is accurately fitted by the variational Bayesian Gaussian mixture model with massive historical data. The data‐driven chance constraints of tie‐line power and gas turbine reserve are built. Meanwhile, the operational characteristics and optimal commitment of the power‐to‐hydrogen devices are modelled to reflectits actual situation.