Transmission network self-healing considering uncertain wind power becomes crucial with increasing penetration of wind power. A hybrid reinforcement learning (HRL) method combining offline ...self-learning with online Monte Carlo tree search (MCTS) is designed to deal with the strong uncertainty induced by wind power restoration. The HRL method trains a policy network with offline self-learning based on historical wind and transmission system data. It then applies the policy network to guide MCTS to realize step-by-step transmission network self-healing based on real-time and forecast data in different wind power scenarios. Besides, a model predictive control method for active power dispatch is proposed to improve wind power generation credibility during self-healing. Simulation results of both test and real-life power systems demonstrate that the proposed method can realize online transmission system self-healing reliably. Comparisons among different reinforcement learning methods indicate that the number of scenarios dominated by HRL is more than twice that dominated by MCTS and a dozen times that dominated by deep Q-network. Meanwhile, the online method is more flexible in uncertain wind power scenarios than optimization methods.
Load restoration coordinating transmission grid, distribution grid, and microgrids is an effective measure that is taken into consideration while improving the power system resilience in extreme ...weather conditions. An online decision-making method is proposed to deal with the unexpected nature of power supply issues regarding the re-energization of microgrids and transmission grids. In this research work, an online multi-agent interaction technique is used for coordinated load restoration. The main algorithm comprises of two subsections, namely, a resilience index and a multi-agent-based decision-making system which are used to administer the coordination among the transmission grid, distribution grid, and microgrids. A distributionally robust optimization model is used to evaluate the power supply capability of microgrids on the basis of load restoration parameters. Finally, a step-by-step decision-making method, based on a deep Q-network, is proposed for distribution network reconfiguration considering the uncertainty of power supply capabilities of transmission grid and microgrids. Simulation results demonstrated that the proposed method can perform the online decision-making of substation load restoration, which significantly improves the load restoration efficiency.
Generator start-up is a pivotal step of transmission system self-healing after large-scale blackouts. Considering the uncertainty of initial power system situation after blackouts and line ...restoration during power system restoration, an online generator start-up algorithm based on Monte Carlo tree search (MCTS) and sparse autoencoder (SAE) is proposed for real-time decision making. First, an online decision support system and a generator start-up efficiency indicator involving the total generation capability and number of restored lines are proposed. Then, the SAE is deployed to learn the data relevant to generator start-up offline to establish a value network, which is used to rapidly estimate the optimal generator start-up efficiency indicator. Next, MCTS used for the online generator start-up is improved by the modified upper confidence bound apply to tree algorithm, move pruning technique, and value network. It is used to search the next line to be restored based on real-time situation. Finally, root parallelization computation is adopted and a decision-making method is proposed to improve the reliability of decision making. Simulation results of the New England 10-unit 39-bus power system and Western Shandong Power Grid of China demonstrate that the proposed algorithm can accomplish generator start-up step by step reliably.
•Mutual information based pre-screening eliminates the redundant and irrelevant features.•Multilayer SDAE based feature extraction using data of all the hidden layers.•Smart identification of ...secure/insecure branches.•Execution of the proposed model on Modified new England IEEE 39 bus power system and IEEE 118 bus power system.
The phenomenon of cascading failures (CF) has a great research potential for wind integrated power systems (WIPS) because of stochastic nature of wind. CF may cause unwanted power system blackout if not handled effectively. To evaluate the impact of N-k contingencies which causes CF, this paper proposes multi-layer stacked de-noising auto-encoder (SDAE) based online static security assessment (SSA) using risk based feature set construction for WIPS. A feature set is constructed taking into account the branch overloading probability and risk along with other features. Online SSA is performed after SDAE training is done successfully. Multi-level feature extraction is performed by multi-layer SDAE after executing the pre-screening process for redundant and irrelevant input features using mutual information theory. The proposed method is executed on modified New England 39 bus power system which is further extended for larger power system of IEEE 118 bus power system. Training time and root mean square error (RMSE) of the proposed method are compared with those of long short term memory (LSTM) and auto-encoder (AE). The effectiveness of the proposed method is also demonstrated by comparing the results with ORNL-PSerc-Alaska (OPA) model.
•An adaptive load restoration strategy fitting to power grid operating conditions and outage scenarios.•Step-by-step load restoration taking full use of flexible control of air conditioners and ...multiple power sources.•An aggregated power estimation model for cold load pickup of air conditioners.•A flexible load pickup amount reduction method considering the impact degree of air conditioners control on the customer.
Frequent extreme hot weather brings a surge of air conditioner load and further increases the probability of outages. Fitting to different power grid operating conditions and outage scenarios, an adaptive load restoration strategy is proposed, which can take full use of flexible control of air conditioners and reliable power sources from the power grid and distributed generations or microgrids. Considering the influence of outage duration and environmental temperature, an air conditioner aggregated power estimation model is established to evaluate the cold load pickup amount. Based on the allowable maximum load pickup amount, a load pickup amount reduction method by flexible control of air conditioners considering the impact degree on the customer is proposed to guarantee secure load pickup operation. Simulation results of the IEEE 14-bus system and a practical power grid demonstrate that the proposed method can restore the power supply of customers rapidly and securely to enhance power grid resilience under extreme hot weather.
Considering the uncertainty of initial power network topology, restoration time of lines and downtime of generators during generator start-up, this paper presents an on-line decision making strategy ...of generator start-up based on deep learning and Monte Carlo tree search (MCTS). At first, in order to generate labeled samples of generator start-up atomically, a self-generated samples method is proposed. The sparse autoencoder (SAE) is applied to train the samples to establish a value network, which is used to estimate the optimal value of decision indicator under certain circumstances. Then, the upper confidence bound apply to tree (UCT) algorithm, move pruning technology and value network are applied to MCTS to search the line needed to be restored based on the situation of power system. Finally, a weighted total power generation capability is proposed to integrate the parallel computing results of MCTS and determine the next restored line. The New England 10-unit 39-bus power system is used to show the feasibility and effectiveness of the proposed strategy, and the on-line decision making strategy is compared with traditional method to show its effectiveness for uncertain situations in generator start-up.
Rapid load restoration after large-scale power system blackouts is of virtual importance to reduce economic losses. Network reconfiguration is an essential foundation of load restoration. ...Incorporating the preference for different objectives, a network reconfiguration approach based on preference-based multiobjective optimization is proposed for network reconfiguration schemes. On the one hand, considering the influences of generators, lines and loads, three evaluation indicators are proposed as objectives to establish a preference multiobjective optimization model. On the other hand, a preference-based discrete nondominated sorting genetic algorithm II (PD-NSGA-II) is designed considering the preference and high discreteness of the suggested model. For efficient decision making, the algorithm is equipped with two sorts of population and two dominance relations to obtain solutions with required quantity and high quality. The simulation results demonstrate that the preference-based multiobjective optimization can reasonably leverage the tradeoff among different factors about network reconfiguration. Furthermore, comparison with other algorithms indicates the efficiency of PD-NSGA-II in solving network reconfiguration optimization problems.
•Network reconfiguration model incorporating preference for different objectives.•Transmission line betweenness considering features of power system topology.•Preference-based multiobjective optimization for convenient decision making.•PD-NSGA-II algorithm for preference discrete multiobjective optimization problem.
The objective of power system restoration is to restore the load as soon as possible, while the successful start-up of generator is the precondition of load recovery and the emphasis of power system ...restoration. In this paper, both the generator start-up sequence and the restoration path are considered. A preference multi-objective model which considers the difference of the objectives' importance is proposed. To get the most preferred alternatives, a non-r-dominance sorting genetic algorithm II (r-NSGA-II) is used to solve the model. The reference point determination method and solution set scale controlling method are proposed to improve the algorithm, which makes the solution set scale controllable and the preference to be better expressed. Simulation results show that the proposed method has practical value when solving the generator start-up problem for network reconfiguration.
Power network reconfiguration is a complex non-convex, nonsmooth and nonlinear optimization problem. A preference-based multiobjective evolutionary algorithm is proposed to incorporate the preference ...for different objectives for network reconfiguration optimization. Three objectives about generators, lines and loads are proposed to establish a preference multiobjective optimization model. To handle the preference and high discreteness of the suggest model, a preference-based discrete nondominated sorting genetic algorithm II (PD-NSGA-II) is designed, with which solutions with required quantity and high quality are obtained. The simulation results demonstrate that the proposed method can reasonably balance different objectives about network reconfiguration, and PD-NSGA-II is more efficient than other algorithms in solving network reconfiguration optimization problem.
Load restoration fitting to the change of load amount, available power and outdoor temperature is an important measure to enhance power system resilience under extreme hot weather. A multi-time scale ...substation load restoration method considering active control of air conditioners is proposed for adaptive restoration. First, a framework of adaptive load restoration is formulated to coordinate the longtime scale whole process scheme making and short-time scale active air conditioners control. Second, an optimization model considering the whole process of substation load restoration is established to make feeder switch schemes to improve load restoration efficiency from the perspective of a long-time scale. Third, model predictive control is adopted to realize the active control of air conditioners from the perspective of a short-time scale to fit the continuously changed load amount, available power and outdoor temperature during restoration. The simulation results demonstrate that the proposed substation load restoration method can make schemes adaptively with better restoration benefit under extreme hot weather.
