Forecasting hourly spot prices for real-time electricity markets is a key activity in economic and energy trading operations. This paper proposes a novel two-stage approach that uses a combination of Auto-Regressive Integrated Moving Average (ARIMA) with other forecasting models to improve residual errors in predicting the hourly spot prices. In Stage-1, the day-ahead price is forecasted using ARIMA and then the resulting residuals are fed to another forecasting method in Stage-2. This approach was successfully tested using datasets from the Iberian electricity market with duration periods ranging from one-week to ninety days for variables such as price, load and temperature. A comprehensive set of 17 variables were included in the proposed model to predict the day-ahead electricity price. The Mean Absolute Percentage Error (MAPE) results indicate that ARIMA-GLM combination performs better for longer duration periods, while ARIMA-SVM combination performs better for shorter duration periods.

This paper proposes a controller design for battery energy storage systems (BESS) and plug-in hybrid electric vehicles (PHEV) integration for frequency control in microgrid communities (MG) with solar photovoltaics (PV's) and wind turbines as distributed generators (DG). These DG's are intermittent power sources and are the causes of possible severe frequency fluctuations in MG's. The proposed control is a PID controller, while the design is based on neural networks. To obtain the appropriate input parameters of the proposed PID controller, a multilayer feedforward neural network is configured and implemented using MATLAB's Deep Learning Toolbox with random values as input. Results demonstrate the effectiveness of the proposed design method. A comparison of the results from the proposed approach with those from particle swarm optimization method proves proposed method is better and more effective.

Modern microgrids are networked systems comprising physical and cyber components for networking, computation, and monitoring. These cyber components make microgrids more reliable but increase the system complexity. Therefore, risk assessment methods are an imperative technology for cyber-physical systems to ensure safe and secure operations. The authors propose a reliability approach that utilizes the failure modes of power and cyber network key components to perform the risk analysis in microgrids. In this work, the authors have used the Failure Mode and Effect Analysis (FMEA) approach for risk assessment of microgrid systems and determine the influence of various failure modes on their performance. FMEA is one of the most effective methods to assess the risk involving the cyber components. It is the method of examining components, modules, and subsystems to determine failure modes in a system and their causes and consequences. A novel approach is proposed to calculate risk priority numbers based on factors like severity, occurrence, and detection. A risk matrix is calculated from the proposed FMEA worksheet, which acts as a graphical representation for evaluating components risk based on risk priority number or criticality metrics.

One of the important aspects of smart grid is to make the best use of existing assets. One way (among others) to achieve this objective is by scheduling effective maintenance routines. Abnormal conditions, including short circuits or overloads, would affect not only the exposed components, but also those farther away from the fault locations. This exposure may cause some of the components fail right away or at a later time. Therefore, the severity, frequency, and timings of system faults are important factors in planning maintenance programs. In this paper, the impact of increased current flows, in the form of short circuits and overloads, on component failure rates are studied and a maintenance scheduling model taking into account such impacts is developed. Using the developed model, the optimum mean time to preventive maintenance is derived and used to maximize the components availability. Results of this paper would help in preventing damage to the equipment by optimally scheduling maintenance programs based on short circuit current levels of the system.