Most power systems’ approaches are currently tending towards stochastic and probabilistic methods due to the high variability of renewable sources and the stochastic nature of loads. Conventional power flow (PF) approaches such as forward-backward sweep (FBS) and Newton-Raphson require a high number of iterations to solve non-linear PF equations making them computationally very intensive. PF is the most important study performed by utility, required in all stages of the power system, especially in operations and planning. This paper discusses the applications of deep learning (DL) to predict PF solutions for three-phase unbalanced power distribution grids. Three deep neural networks (DNNs); Radial Basis Function Network (RBFnet), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN), are proposed in this paper to predict PF solutions. The strength of the proposed DNN models over the traditional iterative-based PF solvers is that these models can capture the nonlinear relationships in PF calculations to accurately predict the solutions. The PF problem is formulated as a multi-output regression model where two or more output values are predicted based on the inputs. The training and testing data are generated through the OpenDSS-MATLAB COM interface. These methods are completely data-driven where the training relies on reducing the mismatch at each node without the need for the knowledge of the system. The novelty of the proposed methodology is that the models can accurately predict the PF solutions for the unbalanced distribution grids with mutual coupling and are robust to different R/X ratios, topology changes as well as generation and load variability introduced by the integration of distributed energy resources (DERs) and electric vehicles (EVs). To test the efficacy of the DNN models, they are applied to IEEE 4-node and 123-node test cases, and the American Electric Power (AEP) feeder model. The PF results for RBFnet, MLP, and CNN models are discussed in this paper which demonstrate that all three DNN models provide highly accurate results in predicting PF solutions.
This paper proposes a novel optimization technique using Linear Programming (LP) method to solve the optimal scheduling problem of Distributed Energy Resources (DERs) including Battery Energy Storage Systems (BESS). The proposed optimization technique has a dual objective function of economics and peak-shaving. Optimization of the BESS operation is a complex problem as it has special constraints such as Depth of Discharge (DOD) requirements, State of Charge (SOC) limitations, Charge and Discharge rates, etc. The proposed LP method would be a useful tool for distribution operators to optimally dispatch the distributed resources in their systems. The derived charge/discharge schedules of BESS ensure maximum energy arbitrage revenue. The proposed optimization technique is tested on a taxonomy feeder developed by Pacific Northwest National Laboratory (PNNL) with a fictitious microgrid that consists of DERs including a BESS. The optimization problem is modeled and solved using the Matlab optimization toolbox with industry standard load and electricity price data.
In the future grids, to reduce greenhouse gas emissions Electric Vehicles (EVs) seems to be an important means of transportation. One of the major disadvantages of the future grid is the demand-supply mismatch which can be mitigated by incorporating the EVs into the grid. The paper introduces the concept of the Distributed Resource Allocation (DRA) approach for incorporating a large number of Plug-in EV (PEVs) with the power grid utilizing the concept of achieving output consensus. The charging/discharging time of all the participating PEVs are separated with respect to time slots and are considered as strategies. The major aim of the paper is to obtain a favorable charging strategy for each grid-connected PEVs in such a way that it satisfies both grid objectives in terms of load profile smoothening and minimizing of load shifting as well as economic and social interests of vehicle owners i.e. a fair share of the rate of charging for all connected PEVs. The three-fold contribution of the paper in smoothening of load profile, load shifting minimization, and fair charging rate is validated using a representative case study. The results confirm improvement in load profile and also highlight a fair deal in the charging rate for each PEV.