Research On Optimal Scheduling Strategy Of Multi-microgrid System

To cope with the energy crisis and increased environmental pollution,the world has begun to vigorously promote microgrids to achieve efficient and flexible application of clean energy.By implementing optimal scheduling of multi-microgrid systems composed of interconnected microgrids in adjacent areas,electrical energy can be distributed effectively,the proportion of new energy consumption may increase,and the stability and economy of operation in multi-microgrid systems can be improves significantly.The optimization scheduling problem of multi-microgrid systems is a typical complex and multi-objective nonlinear problem.The formation of an optimization scheduling strategy depends on accurate data prediction,reasonable mathematical description,and design of algorithm application scenarios.So,this paper updates the data prediction method with deep learning algorithms,takes the impact of network loss in the optimal scheduling of a single microgrid system into account,and on this basis,finally proposes a multi-microgrid system optimal scheduling strategy.Using deep learning technology to realize data prediction of clean energy and load in microgrid.Based on the analysis of deep learning principles,this paper builds a long and short sequence network prediction model to achieve short-term prediction and ultra-short-term prediction of light intensity,wind speed and load.The analysis of the prediction results of the power supply and the load effectively proves that the network not only has strong generalization ability and accurate prediction,but also lays a foundation for the optimal scheduling of multi-micro-network systems.Considering that most microgrids are connected to low-voltage or medium-voltage distribution systems,the losses on their lines cannot be neglected,so a single microgrid optimal scheduling strategy considering network losses has been studied.In view of the different operating characteristics of the source side of the microgrid,the mathematical model is first established.Based on this theory,a single microgrid optimal scheduling mathematical model to minimize microgrid operating costs,pollutant emission quality and network loss is constructed and solved using an improved particle swarm optimization algorithm,in which the calculation of network loss is obtained by power flow iteration.The simulation results of the example verify the effectiveness of the model,indicating that network loss is one of the factors that affect the economy of microgrid operation.Based on the research of single microgrid optimal scheduling,an optimized scheduling strategy for multi-microgrid systems considering the interaction power between microgrids is proposed.The strategy is based on the principle of "clean first,then economic",so that the system operating costs can be reduced as much as possible on the basis of the on-site consumption of clean energy in the system.Then build a multi-objective and multi-constrained scheduling model to minimize the operating cost of each microgrid,use the multi-objective particle swarm optimization algorithm with adaptive grid to find the Pareto optimal solution set,and take the minimum total operating cost of the system as the goal to select the final scheduling result.The results of the calculation examples show that the optimal scheduling strategy of multi-microgrid systems proposed in this paper can reduce the frequency of interaction between the microgrid and the power grid,realize the power complementation between the microgrids,and improve the stability and clean energy consumption.