Accelerated solution of the transmission maintenance schedule problem:a Bayesian optimization approach

To maximize the maintenance willingness of the owner of transmission lines,this study presents a transmission maintenance scheduling model that considers the energy constraints of the power system and the security constraints of on-site maintenance operations.Considering the computational complexity of the mixed integer programming(MIP)problem,a machine learning(ML)approach is presented to solve the transmission maintenance scheduling model efficiently.The value of the branching score factor value is optimized by Bayesian optimization(BO)in the proposed algorithm,which plays an important role in the size of the branch-and-bound search tree in the solution process.The test case in a modified version of the IEEE 30-bus system shows that the proposed algorithm can not only reach the optimal solution but also improve the computational efficiency.

Multivariate Analyses for Finding Significant Track Irregularities to Generate an Optimal Track Maintenance Schedule

We first discuss the relationship between the optimal track maintenance scheduling model and an efficient detection method for abnormal track irregularities given by the longitudinal level irregularity displacement (LLID). The results of applying the cluster analysis technique to the sampling data showed that maintenance operation is required for approximately 10% of the total lots, and these lots were further classified into three groups according to the degree of maintenance need. To analyze the background factors for detecting abnormal LLID lots, a principal component analysis was performed;the results showed that the first principal component represents LLIDs from the viewpoints of the rail structure, equipment, and operating conditions. Binomial and ordinal logit regression models (LRMs) were used to quantitatively investigate the determinants of abnormal LLIDs. Binomial LRM was used to characterize the abnormal LLIDs, whereas ordinal LRM was used to distinguish the degree of influence of factors that are considered to have a significant impact on LLIDs.

Wind Turbine Optimal Preventive Maintenance Scheduling Using Fibonacci Search and Genetic Algorithm

Maintenance scheduling is essential and crucial for wind turbines (WTs) to avoid breakdowns andreduce maintenance costs. Many maintenance models have been developed for WTs’ maintenance planning, suchas corrective, preventive, and predictive maintenance. Due to communities’ dependence on WTs for electricityneeds, preventive maintenance is the most widely used method for maintenance scheduling. The downside tousing this approach is that preventive maintenance (PM) is often done in fixed intervals, which is inefficient. In thispaper, a more detailed maintenance plan for a 2 MW WT has been developed. The paper’s focus is to minimize aWT’s maintenance cost based on a WT’s reliability model. This study uses a two-layer optimization framework:Fibonacci and genetic algorithm. The first layer in the optimization method (Fibonacci) finds the optimal numberof PM required for the system. In the second layer, the optimal times for preventative maintenance and optimalcomponents to maintain have been determined to minimize maintenance costs. The Monte Carlo simulationestimates WT component failure times using their lifetime distributions from the reliability model. The estimatedfailure times are then used to determine the overall corrective and PM costs during the system’s lifetime. Finally,an optimal PM schedule is proposed for a 2 MW WT using the presented method. The method used in this papercan be expanded to a wind farm or similar engineering systems.

Learning to branch in the generation maintenance scheduling problem

To maximize the reliability index of a power system,this study modeled a generation maintenance scheduling problem that considers the network security constraints and rationality constraints of the generation maintenance practice in a power system.In view of the computational complexity of the generation maintenance scheduling model,a variable selection method based on a support vector machine(SVM)is proposed to solve the 0-1 mixed integer programming problem(MIP).The algorithm observes and collects data from the decisions made by strong branching(SB)and then learns a surrogate function that mimics the SB strategy using a support vector machine.The learned ranking function is then used for variable branching during the solution process of the model.The test case showed that the proposed variable selection algorithm-based on the features of the proposed generation maintenance scheduling problem during branch-and-bound-can increase the solution efficiency of the generation-scheduling model on the premise of guaranteed accuracy.

Breeding Particle Swarm Optimization for Railways Rolling Stock Preventive Maintenance Scheduling

The goal of railway rolling stock maintenance and replacement approaches is to reduce overall cost while increasing reliability which is multi objective optimization problem and a proper predictive maintenance scheduling table should be adequately designed. We propose Breeding Particle Swarm Optimization (BPSO) model based on the concepts of Breeding Swarm and Genetic Algorithm (GA) operators to design this table. The practical experiment shows that our model reduces cost while increasing reliability compared to other models previously utilized.

Cyber-physical Collaborative Restoration Strategy for Power Transmission System Considering Maintenance Scheduling

In order to improve the ability of power transmission system to cope with compound faults on the communication side and power side,a cyber-physical collaborative restoration strategy is proposed.First,according to the information system’s role in fault diagnosis,remote control of equipment maintenance and automatic output adjustment of generator restoration,a cyber-physical coupling model is proposed.On this basis,a collaborative restoration model of power transmission system is established by studying interactions among maintenance schedule paths,information system operation,and power system operation.Based on power flow linearization and the large M-ε method,the above model is transformed into a mixed integer linear programming model,whose computational burden is reduced further by the clustering algorithm.According to the parameters of IEEE39 New England system,the geographic wiring diagram of the cyber-physical system is established.Simulation results show the proposed restoration strategy can consider the support function of the information system and space-time coordination of equipment maintenance at both sides comprehensively to speed up load recovery progress.

Risk-based maintenance scheduling of generating units in the deregulated environment considering transmission network congestion

In restructured power systems,the traditional approaches of unit maintenance scheduling(UMS)need to undergo major changes in order to be compatible with new competitive structures.Performing the maintenance on generating units may decrease the security level of transmission network and result in electricity shortage in power system;as a result,it can impose a kind of cost on transmission network as called security cost.Moreover,taking off line a generating unit for performing maintenance can change power flow in some transmission lines,and may lead to network congestion.In this study,generating unit maintenance is scheduled considering security and congestion cost with N-1 examination for transmission lines random failures.The proposed UMS approach would lead to optimum operation of power system in terms of economy and security.To achieve this goal,the optimal power flow(OPF)compatible with market mechanism is implemented.Moreover,the electricity price discovery mechanism as locational marginal pricing(LMP)is restated to analyze the impacts of UMS on nodal electricity price.Considering security and congestion cost simultaneously,this novel approach can reveal some new costs which are imposed to transmission network on behalf of generation units;as a result,it provides a great opportunity to perform maintenance in a fair environment for both generating companies(GenCo)and transmission companies(TransCo).At the end,simulation results on nine-bus test power system demonstrate that by using this method,the proposed UMS can guarantee fairness among market participants including GenCos and TransCo and ensure power system security.

Short-term Transmission Maintenance Scheduling Considering Network Topology Optimization

With the increasing penetration of renewable energy sources,transmission maintenance scheduling(TMS)will have a larger impact on the accommodation of wind power.Meanwhile,the more flexible transmission network topology owing to the network topology optimization(NTO)technique can ensure the secure and economic operation of power systems.This paper proposes a TMS model considering NTO to decrease the wind curtailment without adding control devices.The problem is formulated as a two-stage stochastic mixed-integer programming model.The first stage arranges the maintenance periods of transmission lines.The second stage optimizes the transmission network topology to minimize the maintenance cost and system operation in different wind speed scenarios.The proposed model cannot be solved efficiently with off-theshelf solvers due to the binary variables in both stages.Therefore,the progressive hedging algorithm is applied.The results on the modified IEEE RTS-79 system show that the proposed method can reduce the negative impact of transmission maintenance on wind accommodation by 65.49%,which proves its effectiveness.

Generation maintenance scheduling based on multiple objectives and their relationship analysis

In a market environment of power systems, each producer pursues its maximal profit while the independent system operator is in charge of the system reliability and the minimization of the total generation cost when generating the generation maintenance scheduling(GMS). Thus, the GMS is inherently a multi-objective optimization problem as its objectives usually conflict with each other. This paper proposes a multi-objective GMS model in a market environment which includes three types of objectives, i.e., each producer's profit, the system reliability, and the total generation cost. The GMS model has been solved by the group search optimizer with multiple producers(GSOMP) on two test systems. The simulation results show that the model is well solved by the GSOMP with a set of evenly distributed Pareto-optimal solutions obtained. The simulation results also illustrate that one producer's profit conflicts with another one's, that the total generation cost does not conflict with the profit of the producer possessing the cheapest units while the total generation cost conflicts with the other producers' profits, and that the reliability objective conflicts with the other objectives.