The electric vehicles (EVs) rapid growth can potentially lead power grids to face new challenges due to load profile changes. To this end, a new method is presented to forecast the EV charging station loads with machine learning techniques. The plug-in hybrid EVs (PHEVs) charging can be cetergorized into three main techniques (smart, uncoordinated, and coordinated). To have a good prediction of the future PHEV loads in this paper, the Q-learning technique, which is a kind of the reinforcement learning (RL), is used for different charging scenarios. The proposed Q-learning technique improves the forecasting of the conventional artificial intelligence techniques such as the recurrent neural network (RNN) and long short-term memory (LSTM). Results prove that PHEV loads can accurately be forecasted by using the Q-learning technique under three different scenarios (smart, uncoordinated, and coordinated). The simulations of three different scenarios are obtained in the Keras open source software to validate the effectiveness and advantages of the proposed Q-learning technique.

This paper addresses the optimal operation and scheduling of reconfigurable microgrids incorporating the dynamic line rating limitations during the islanded and grid-connected mode operations. The incorporation of the dynamic line rating of overhead feeders can potentially improve the system security when providing economical and technical benefits for the microgrid. The proposed framework takes into account a realistic formulation to minimize the total microgrid costs in both grid-connected and multi-period islanded modes. Also, a stochastic framework based on unscented transform (UT) is proposed to model the uncertainties associated with renewable energy sources (RESs) output power, market energy price, load demand as well as the weather uncertain parameters such as solar radiation, wind speed, and ambient temperature. Due to the high nonlinearity and complexity of the proposed problem, an efficient optimization algorithm based on collective decision optimization algorithm (CDOA) is proposed. A new two-stage modification method is also developed to improve the algorithm search ability and avoid premature convergence. The proposed problem is examined on the IEEE 32-bus microgrid test system. The simulation results show the effectiveness of the proposed model and verify its economic and reliability merits.

Power grid resilience, reliability, and sustainability can be improved significantly, by decomposing the large grids into networked microgrids (NMGs). However, optimal energy management problem and preserving the security in NMGs are more complicated and challenging. This paper aims to propose an effective secured stochastic energy management framework for NMGs based on the modified blockchain approach utilizing Directed Acyclic Graph (DAG). Using the decentralized and transparent blockchain technology will help to have higher security, lower risks within the network, eliminating the financial fraud, and cutting down the total operational cost. In order to address the issues arising in the traditional blockchain models mainly due to the storage and high complexities of hash address calculations, in this paper, a new modified blockchain technology is developed based on the DAG method. Also, a novel data restoration technique is developed to provide a way to restore the data with appropriate accuracy. Moreover, the unscented transform (UT) approach is employed to model the uncertainties of forecast errors in hourly load demand, solar power, and wind turbines output power. The proposed model is tested on an NMG system with four MGs including two residential MGs (as the non-crucial loads), a commercial MG (as the intermediate level loads), and a hospital MG (as the crucial loads).

Power grid resilience, reliability, and sustainability can be improved by decomposing the large-scale grids into the Networked Microgrids (NMGs). However, different MGs may have different roles and policies. Hence, in comparison with conventional networks, energy management, as well as the security of the NMGs is more completed and challenging. This paper develops a three-layer cloud-fog computing architecture for energy management of reconfigurable NMGs considering dynamic thermal line rating (DLR) constraint. DLR can potentially affect the ampacity of feeders, especially in the islanding mode, when lines approach their maximum capacity. In order to avoid any feeder contingency in the off-grid (islanded) mode, the reconfiguration technique as well as the cloud fogs framework are employed to change the topology of the NMG network swiftly and release the line capacity. Finally, the proposed problem is formulated as a mixed-integer linear optimization problem considering DLR constraint. The proposed model is examined on a modified IEEE 69 bus test network. Results demonstrate the high performance and effectiveness of the developed model and also validate its reliability and economic assets.

This paper aims to investigate the optimal scheduling of stochastic reconfigurable hybrid ac-dc microgrid (MG) in the presence of renewable energies and also considering dynamic line rating (DLR) constraint. DLR is a practical limitation that can potentially affect the ampacity of lines, particularly in the islanded mode when the lines reach their maximum capacity in lack of main generation source at the point of interconnection with the utility. In order to prevent overloading of the lines, the reconfiguration technique is developed to change the topology of the network by some prelocated switches. A linearization technique is adapted to address the nonlinearity of both nodal ac power flow and the DLR constraints. The unscented transform technique is utilized to model uncertainties including renewable energy generations, hourly load demands, and hourly market prices along with the DLR uncertainties such as solar radiation, wind speed, and ambient temperature. Finally, a sensitivity analysis is performed to see the effect of wind speed and solar radiation on the energy management of hybrid ac-dc MG. The performance of the proposed methodology is examined on a modified IEEE-33 bus test system, which demonstrates the high efficiency and importance of the proposed techniques in minimizing the hybrid ac-dc MG operation cost while all of the constraints of the network are satisfied.

This paper investigates the impact of uncoordinated, coordinated, and smart charging of plug-in hybrid electric vehicles (PHEVs) on the optimal operation of microgrids (MGs) incorporating the dynamic line rating (DLR) security constraint. The DLR constraint, particularly in the islanding mode, influences the ampacity of MG feeders, when distribution lines reach their maximum capacity. To overcome any line outage or contingency situation, smart PHEVs are utilized to help improve the grid security. However, using PHEVs can cause higher power losses and feeder overloading issues. To address these concerns, a reconfiguration technique is employed in this paper. A heuristic algorithm, known as the collective decision-based optimization algorithm, is utilized to overcome the non-convexity and nonlinearity of the problem. The unscented transform technique is employed to model DLR uncertainties caused by solar radiation, load demand, and weather temperature, as well as PHEVs' uncertainties caused by varying charging strategies, numbers of PHEVs being charged, charging start time, and charging duration. Moreover, a deep learning gated recurrent unit technique is designed to forecast renewable power output for mitigating the uncertainties in renewable energy components. A modified IEEE 33-bus test network is deployed to evaluate the efficiency and performance of the proposed model.