Real-Time Operation of Microgrids

Microgrid (MG) systems effectively integrate a generation mix of solar, wind, and other renewable energy resources. The intermittent nature of renewable resources and the unpredictable weather conditions contribute largely to the unreliability of microgrid real-time operation. This paper investigates the behavior of microgrid for different intermittent scenarios of photovoltaic generation in real-time. Reactive power coordination control and load shedding mechanisms are used for reliable operation and are implemented using OPAL-RT simulator integrated with Matlab. In an islanded MG, load shedding can be an effective mechanism to maintain generation-load balance. The microgrid of the German Jordanian University (GJU) is used for illustration. The results show that reactive power coordination control not only stabilizes the MG operation in real-time but also reduces power losses on transmission lines. The results also show that the power losses at some substations are reduced by a range of 6% - 9.8%.

Energy Exchange Control in Multiple Microgrids with Transactive Energy Management

In recent years,the advent of microgrids with numerous renewable energy sources has created some fundamental challenges in the control,coordination,and management of energy trading between microgrids and the power grid.To respond to these challenges,some techniques such as the transactive energy(TE)technology are proposed to control energy sharing.Therefore,this paper uses TE technology for energy exchange control among the microgrids,and applies three operation cases for analyzing the energy trading control of four and ten microgrids with the aim of minimizing the energy cost of each microgrid,respectively.In this regard,Monte Carlo simulation and fast forward selection(FFS)methods are respectively exerted for scenario generation and reduction in uncertainty modeling process.The first case is assumed that all microgrids can only receive energy from the network and do not have any connection with each other.In order to maximize the energy cost saving of each microgrid,the second case is proposed to provide a positive percentage of cost saving for microgrids.All microgrids can also trade energy with each other to get the most benefit by reducing the dependency on the main grid.The third case is similar to the second case,but its target is to indicate the scalability of the models based on the proposed TE technology by considering ten commercial microgrids.Finally,the simulation results indicate that microgrids can achieve the positive amount of cost saving in the second and third cases.In addition,the total energy cost of microgrids has been reduced in comparison with the first case.

A soft actor-critic deep reinforcement learning method for multi-timescale coordinated operation of microgrids

This paper develops a multi-timescale coordinated operation method for microgrids based on modern deep rein-forcement learning.Considering the complementary characteristics of different storage devices,the proposed approach achieves multi-timescale coordination of battery and supercapacitor by introducing a hierarchical two-stage dispatch model.The first stage makes an initial decision irrespective of the uncertainties using the hourly predicted data to minimize the operational cost.For the second stage,it aims to generate corrective actions for the first-stage decisions to compensate for real-time renewable generation fluctuations.The first stage is formulated as a non-convex deterministic optimization problem,while the second stage is modeled as a Markov decision process solved by an entropy-regularized deep reinforcement learning method,i.e.,the Soft Actor-Critic.The Soft Actor-Critic method can efficiently address the exploration-exploitation dilemma and suppress variations.This improves the robustness of decisions.Simulation results demonstrate that different types of energy storage devices can be used at two stages to achieve the multi-timescale coordinated operation.This proves the effectiveness of the proposed method.