Deep Learning in Power Systems Research:A Review

With the rapid growth of power systems measurements in terms of size and complexity,discovering statistical patterns for a large variety of real-world applications such as renewable energy prediction,demand response,energy disaggregation,and state estimation is considered a crucial challenge.In recent years,deep learning has emerged as a novel class of machine learning algorithms that represents power systems data via a large hypothesis space that leads to the state-of-the-art performance compared to most recent data-driven algorithms.This study explores the theoretical advantages of deep representation learning in power systems research.We review deep learning methodologies presented and applied in a wide range of supervised,unsupervised,and semi-supervised applications as well as reinforcement learning tasks.We discuss various settings of problems solved by discriminative deep models including stacked autoencoders and convolutional neural networks as well as generative deep architectures such as deep belief networks and variational autoencoders.The theoretical and experimental analysis of deep neural networks in this study motivates longterm research on optimizing this cutting-edge class of models to achieve significant improvements in the future power systems research.

Preventive reinforcement under uncertainty for islanded microgrids with electricity and natural gas networks

This paper presents an approach to determine the vulnerable components in the electricity and natural gas networks of an islanded microgrid that is exposed to deliberate disruptions. The vulnerable components in the microgrid are identified by solving a bi-level optimization problem. The objective of the upper-level problem(the attacker's objective) is to maximize the expected operation cost of microgrid by capturing the penalties associated with the curtailed electricity and heat demands as a result of the disruption. In the lower-level problem, the adverse effects of disruptions and outages in the electricity and natural gas networks are mitigated by leveraging the available resources in the microgrid(the defender's objective). The uncertainties in the electricity and heat demand profiles were captured by introducing scenarios with certain probabilities. The formulated bi-level optimization problem provides effective guidelines for the microgrid operator to adopt the reinforcement strategies in the interdependent natural gas and electricity distribution networks and improve the resilience of energy supply. The presented case study shows that as more components are reinforced in the interdependent energy networks, the reinforcement cost is increased and the expected operation cost as a result of disruption is decreased.

Operation of natural gas and electricity networks with line pack

This paper addresses the coordinated operation of natural gas and electricity networks considering the line pack flexibility in the natural gas pipelines.The problem is formulated as a mixed integer linear programming problem.The objective is to minimize the operation cost of natural gas and electricity networks considering the price of the natural gas supply.Benders decomposition is used to solve the formulated problem.The master problem minimizes the startup and shutdown costs as well as the operation cost of the thermal units other than the gasfired generation units in the electricity network.The first subproblem validates the feasibility of the decisions made in the master problem in the electricity network.And if there is any violation,feasibility Benders cut is generated and added to the master problem.The second subproblem ensures the feasibility of the decisions of the master problem in the natural gas transportation network considering the line pack constraints.The last sub-problem ensuresthe optimality of the natural gas network operation problem considering the demand of the gas-fired generation units and line pack.The nonlinear line pack and flow constraints in the feasibility and optimality subproblems of natural gas transportation network are linearized using Newton-Raphson technique.The presented case study shows the effectiveness of the proposed approach.It is shown that leveraging the stored gas in the natural gas pipelines would further reduce the total operation cost.

A convex relaxation approach for power flow problem

A solution to the power flow problem is imperative for many power system applications and several iterative approaches are employed to achieve this objective.However,the chance of finding a solution is dependent on the choice of the initial point because of the nonconvex feasibility region of this problem.In this paper,a non-iterative approach that leverages a convexified relaxed power flow problem is employed to verify the existence of a feasible solution.To ensure the scalability of the proposed convex relaxation,the problem is formulated as a sparse semi-definite programming problem.The variables associated with each maximal clique within the network form several positive semidefinite matrices.Perturbation and network reconfiguration schemes are employed to improve the tightness of the proposed convex relaxation in order to validate the existence of a feasible solution for the original non-convex problem.Multiple case studies including an ill-conditioned power flow problem are examined to show the effectiveness of the proposed approach to find a feasible solution.