The volatility of wind power generations could significantly challenge the economic and secure operation of combined electricity and heat networks. To tackle this challenge, this paper proposes a framework of optimal dispatch with distributed electric heating storage based on a correlation-based long short-term memory prediction model. The prediction model of distributed electric heating storage is developed to model its behavior characteristics which are obtained by the autocorrelation and correlation analysis with external factors including weather and time-of-use price. An optimal dispatch model of combined electricity and heat networks is then formulated and resolved by a constraint reduction technique with clustering and classification. Our method is verified through numerous simulations. The results show that, compared with the state-of-the-art techniques of support vector machine and recurrent neural networks, the mean absolute percentage error with the proposed correlation-based long short-term memory can be reduced by 1.009 and 0.481 respectively. Compared with conventional method, the peak wind power curtailment with dispatching distributed electric heating storage is reduced by nearly 30% and 50% in two cases respectively.
Among the issues of accurate power distribution, stability improvement, and harmonic suppression in micro-grid, each has been well studied as an individual, and most of the strategies about these issues aim at one inverter-based micro-grid, hence there is a need to establish a model to achieve these functions as a whole, aiming at a multi-inverter-based micro-grid. This paper proposes a comprehensive strategy which achieves this goal successfully; since the output voltage and frequency of micro-grid all consist of fundamental and harmonic components, the strategy contains two parts accordingly. On one hand, a fundamental control strategy is proposed upon the conventional droop control. The virtual impedance is introduced to solve the problem of accurate allocation of reactive power between inverters. Meanwhile, a secondary power balance controller is added to improve the stability of voltage and frequency while considering the aggravating problem of stability because of introducing virtual impedance. On the other hand, the fractional frequency harmonic control strategy is proposed. It can solve the influence of nonlinear loads, micro-grid inverters, and the distribution network on output voltage of inverters, which is focused on eliminating specific harmonics caused by the nonlinear loads, micro-grid converters, and the distribution network so that the power quality of micro-grid can be improved effectively. Finally, small signal analysis is used to analyze the stability of the multi-converter parallel system after introducing the whole control strategy. The simulation results show that the strategy proposed in this paper has a great performance on distributing reactive power, regulating and stabilizing output voltage of inverters and frequency, eliminating harmonic components, and improving the power quality of multi-inverter-based micro-grid.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.