Abstract
In this paper, a hybrid machine learning model is applied to evaluate the relationship between random initial states and the power system's vulnerability to cascading outages. A cascading outage simulator (CS), which uses off-line AC power flows, is proposed for generating training data. The initial states are randomly selected and the CS model is deployed for each initial state, where power system generation and loads are adjusted dynamically and power flows are redistributed to quantify the vulnerability metric. Furthermore, the proposed hybrid machine learning model deploys a combined Support Vector Machine (SVM) classification and Gradient Boosting Regression (GBR) to improve the learning precision. The classification model is trained by SVM, which divides the data into two categories with and without load shedding. Then, GBR is adopted only for the data with load shedding to determine the relationship between input power outage states and the vulnerability metric. The proposed vulnerability analysis approach is applied to several test systems and the results are analyzed. Note to Practitioners-The power system vulnerability can be quantified by cascading outage simulations. However, there are two challenges: i) there are a huge number of possible initial states and we cannot enumerate all these initial states for the cascading outage simulation. Neither can we precisely quantify the bus vulnerability. ii) The cascading outage simulation may be time-consuming for large-scale power systems, which is challenging for the online application. To address the above challenges, we expect to design a machine learning technique to predict the power system vulnerability, which can train the model in an offline way and then use it for the online application. Firstly, since there is not enough operation data from practical power systems, we develop a cascading outage simulator, using off-line AC power flows, for generating synthetic training data. Secondly, we observe that the training precision by directly applying the regression model may be very poor because the output of the machine learning model may take on an uneven distribution concerning input parameters. Thus, we propose a hybrid machine learning model with a combined classification and regression method, where the classification model is employed to remove the data without the load shedding, and the regression model then determines the relationship between input power outage states and the vulnerability metric. The proposed model and method have been tested on several systems including a practical large-scale Polish power system to show the effectiveness.

Abstract
Due to the rising of both economic and environmental concerns in the energy sector, each subdivision of the community is investigating new solutions to overcome this critical issue. For this reason, electric vehicles (EVs) have gained more significance in the transportation sector owing to their efficient and clean operation chance. These improvements, however, bring new challenges such as installation costs, infrastructure renovation, and loading of the existing power system. Here, optimal sizing and siting of EV charging stations (CSs) are examined in a mixed-integer linear programming framework with the aim of minimizing the number of EVCSs in the distribution system (which in turn means to minimize CS-related investment while satisfying EV owners' needs) while satisfying constraints. The proposed optimization model considers EVCS types with different charging rate capabilities to provide opportunities for demand-side management. Moreover, the model takes the actual behaviour of the battery charging pattern into account by using real measured EV charging data together with the consideration of an actual distribution system belonging to a region in Turkey. Lastly, a bunch of case studies is conducted in order to validate the accuracy and effectiveness of the devised model.

Abstract
This article presents a distributed resilient demand response program integrated with electrical energy storage systems for residential consumers to maximize their comfort level. A dynamic real-time pricing method is proposed to determine the hourly electricity prices and schedule the electricity consumption of smart home appliances and energy storage systems commitment. The algorithm is employed in normal and emergency operating conditions, taking into account the comfort level of consumers. In emergency conditions, the power outage of consumers is modeled for different hours and outage patterns. To evaluate the applicability of the proposed model, real samples of Southern California households are considered to model the smart homes and their appliances. Further, a sensitivity analysis is performed to assess the impacts of the number of households and number of persons per household on the output results. The results showed that the proposed model reduced the costs of utility in normal and emergency conditions by about 33.77% and 30.92%, respectively. The values of total payments of consumers in normal and emergency conditions were decreased by about 34.26% and 31.31%, respectively. Further, the consumers comfort level for normal and emergency conditions increased by about 146.78% and 110.2%, respectively. Finally, the social welfare for normal and emergency conditions increased by about 46% and 49.06%, respectively.

Abstract
Integration of multiple energy systems and the presence of smart energy hubs have provided increased flexibility and improved efficiency for the system. In this article, a bi-level decomposition approach (BLDA) is presented for coplanning of electricity and gas networks as well as the energy hub in distribution networks. The proposed multistage planning determines the investment candidates with optimum capacity for the components of integrated systems. Due to the complexity and nonlinearity of the models and energy subsystems interactions, the expansion planning problem is a difficult task with many limitations, especially for large-scale systems. To overcome these obstacles, achieve an optimum response and reduce computation time, a mixed integer linear programming model and a new BLDA methodology are developed in this article. Moreover, to evaluate the effectiveness and superiority of the proposed approach, the interactions among the energy systems are simulated in a large-scale distribution system and the results are compared.

Abstract
Large solar power stations are usually located in remote areas and connect to the main grid via a long transmission line. The energy storage unit is deployed locally with the solar plant to smooth its output. Capacities of the grid-connection transmission line and the energy storage unit have a significant impact on the utilization rate of solar energy, as well as the investment cost. This article characterizes the feasible set of capacity parameters under a given solar spillage rate and a fixed investment budget. A linear programming-based projection algorithm is proposed to obtain such a feasible set, offering valuable references for system planning and policy making.

Abstract
High accurate wind speed forecasting plays an important role in ensuring the sustainability of wind power utilization. Although deep neural networks (DNNs) have been recently applied to wind time-series datasets, their maximum performance largely leans on their designed architecture. By the current state-of-the-art DNNs, their architectures are mainly configured in manual way, which is a time-consuming task. Thus, it is difficult and frustrating for regular users who do not have comprehensive experience in DNNs to design their optimal architectures to forecast problems of interest. This paper proposes a novel framework to optimize the hyperparameters and architecture of DNNs used for wind speed forecasting. Thus, we introduce a novel enhanced version of the grasshopper optimization algorithm called EGOA to optimize the deep long short-term memory (LSTM) neural network architecture, which optimally evolves four of its key hyperparameters. For designing the enhanced version of GOA, the chaotic theory and levy flight strategies are applied to make an efficient balance between the exploitation and exploration phases of the GOA. Moreover, the mutual information (MI) feature selection algorithm is utilized to select more correlated and effective historical wind speed time series features. The proposed model's performance is comprehensively evaluated on two datasets gathered from the wind stations located in the United States (US) for two forecasting horizons of the next 30-min and 1-h ahead. The experimental results reveal that the proposed model achieves the best forecasting performance compared to seven prominent classical and state-of-the-art forecasting algorithms.