A Simulated Annealing based approach to solve the generator maintenance scheduling problem

The scheduling of maintenance actions of generators is not a new problem but gained in recent years a new interest with the advent of electricity markets because inadequate schedules can have a significative impact on the revenues of generation companies. In this paper we report the research on this topic developed during the preparation of the MSc Thesis of the second author. The scheduling problem of generator maintenance actions is formulated as a mixed integer optimization problem in which we aim at minimizing the operation cost along the scheduling period plus a penalty on energy not supplied. This objective function is subjected to a number of constraints detailed in the paper and it includes binary variables to indicate that a generator is in maintenance in a given week. This optimisation problem was solved using Simulated Annealing. Simulated Annealing is a very appealing metaheuristic easily implemented and providing good results in numerous optimization problems. The paper includes results obtained for a Case Study based on a realistic generation system that includes 29 generation groups. This research work was proposed and developed with the collaboration of the third and fourth authors, from EDP Produção, Portugal.     

A noise annealing neural network for hydroelectric generationscheduling with pumped-storage units

A new approach based on neural network is proposed for the hydroelectric generation scheduling with pumped-storage units at Taiwan power system. The purpose of hydroelectric generation scheduling is to determine the optimal amounts of generated powers for the hydro units in the system. To achieve an economical dispatching schedule for the hydro units including two large pumped-storage plants, a neural network is employed to reach a schedule in which total fuel cost of the thermal units over the study period is minimized. The neural network model presented can solve nonlinear constrained optimization problems with continuous decision variables. Incorporating the noise annealing concepts, the model is able to produce such a solution which is the global optimum of the original problem with probability close to 1. The proposed approach is applied to hydroelectric generation scheduling of Taiwan power system. It is concluded from the results that the proposed approach is very effective in reaching proper hydro generation schedules     

Generation allocation problem using a Hopfield-bisection approach including transmission losses

The objective of the paper is to solve generation allocation problem by minimizing total production cost, including transmission losses using a Hopfield neural network (HNN) algorithm. The generation allocation problem is commonly known as economic dispatch (ED). The computation procedure of the proposed HNN method is direct and do not need training and has been developed and mapped to solve the generation allocation problem of thermal generators. The procedure employs a linear input-output model for the neurons instead of the sigmoidal function. Formulations for solving the ED problem are explored. Through the application of these formulations, direct computation instead of iterations for solving the problem becomes possible. Not like the usual Hopfield methods, which select the weighting factors of the energy function by trials, the proposed method determines the corresponding factors by calculations. To include transmission losses in ED solution, we propose a dichotomy solution combined to the HNN. The effectiveness of the developed method is identified through its application to the 15-unit system. Computational results manifest that the method has a lot of excellent performances.     

A solution method using neural networks for the generator commitment problem

This paper studies the feasibility of applying the Hopfield-type neural network to unit commitment problems in a large power system. The unit commitment problem is to determine an optimal schedule of what thermal generation units must be started or shut off to meet the anticipated demand; it can be formulated as a complicated mixed integer programming problem with a number of equality and inequality constraints. In our approach, the neural network gives the on/off states of thermal units at each period and then the output power of each unit is adjusted to meet the total demand. Another feature of our approach is that an ad hoc neural network is installed to satisfy inequality constraints which take into account standby reserve constraints and minimum up/down time constraints. The proposed neural network approach has been applied to solve a generator scheduling problem involving 30 units and 24 time periods; results obtained were close to those obtained using the Lagrange relaxation method.     

A Practical Model for Generator Maintenance Scheduling with Transmission Constraints

In this paper an optimal maintenance scheduling of generating units in a power system has been developed with transmission network representation. Here a DC load flow has been embedded in the maintenance model to include network constraints resulting in a more practical maintenance schedule. The model developed here uses the minimization of system cost (production cost plus the unserved energy cost) as the objective criterion, whereas the reliability objective function used is the minimization of unserved energy. The optimization is achieved by integer linear programming. The incorporation of transmission network adds significant complexity to maintenance scheduling. The proposed model enables almost all practical maintenance scheduling constraints to be handled easily. The optimization has been carried out to minimize the cost function considering different cases (i.e., with and without incorporation of the transmission network). The effectiveness of the proposed method has been demonstrated by obtaining numerical results on sample and real scale test systems. A comparison of the cost objective function clearly indicates that the maintenance schedule obtained from the simple generation model alone is more expensive than the one with transmission, and that there is a considerable degree of suboptimality in the former case.     

A novel method for maintenance scheduling of generating units considering the demand side

This paper proposes a novel competitive mechanism for maintenance scheduling of generating units in the deregulated environment. In restructured power systems, the objective function of power producers is to maximize their benefits, and the aim of the Independent System Operator (ISO) is to increase the reliability throughout the year as much as possible. Therefore, there are two objective functions for finding an optimal maintenance schedule in the deregulated environment. The main contribution of this paper is considering the condition of demand side in the maintenance scheduling of generating units. In this scheme, authority of the maintenance scheduling has been granted to the ISO. The proposed method schedules the outage windows of generating units to attain maximum producers’ benefits and maximum annual social welfare. This method is tested in a bilateral energy market, and the IEEE-RTS system is used to demonstrate the effectiveness of the proposed method.     

A probabilistic approach to generation maintenance scheduler with network constraints

Most generating unit maintenance scheduling packages consider the preventive maintenance schedule of generating units over a one or two year operational planning period in order to minimize the total operating cost while satisfying system energy requirements and maintenance constraints. In a global maintenance scheduling problem, we propose to consider network constraints and generating unit outages in generation maintenance scheduling. The inclusion of network constraints in generating unit maintenance will increase the complexity of the problem, so we decompose the global generator scheduling problem into a master problem and sub-problems using Benders decomposition. At the first stage, a master problem is solved to determine a solution for maintenance schedule decision variables. In the second stage, sub-problems are solved to minimize operating costs while satisfying network constraints and generators’ forced outages. Benders cuts based on the solution of the sub-problem are introduced to the master problem for improving the existing solution. The iterative procedure continues until an optimal or near optimal solution is found.     

电力系统运行计划和节能

电力系统的运行计划关系到从一小时到几年时间范围内的生产效益和发电节能。运行计划一般包括机组组合、水电计划和检修计划等问题。本文阐述如何将这一综合问题分解成长期、中期和短期问题,并为求解这些问题探讨各种算法的可用性。     

基于网络拓扑和遗传算法的配电设备检修计划优化模型

根据配电网设备检修计划编制的实际情况,建立了考虑多种约束条件的检修计划优化数学模型。该模型以检修停电电量最小为目标,采用网络拓扑方法实现配电网内在的各种约束,并采用改进遗传算法对优化问题进行求解。网络拓扑方法的引入明确了线路间的关联关系,使检修计划可以按轻重缓急情况排序。对遗传算法的改进可有效地保证其收敛能力并提高其优化能力。最后的算例分析表明,上述方法可以快速有效地得到最优检修计划并降低检修停电损失。     

基于混沌模拟退火神经网络模型的电力系统经济负荷分配

在传统混沌神经网络模型的基础上，提出了一种具有衰减混沌噪声的混沌模拟退火神经网络模型(CSA-DCN)。该模型结合了Hopfield神经网络(HNN)与模拟退火算法(SA)的优点，并引入通过Logistic映射迭代函数产生的衰减混沌噪声，从而使该模型可以有效地解决高维、离散、非凸的非线性约束优化问题。例如电力系统经济负荷分配(ELD)问题，在考虑网损、阀点效应的情况下，将该模型应用于解决ELD问题。通过多个算例仿真计算表明，该模型的算法是可行和有效的。CSA-DCN模型是一种适用性很强的优化模型，可以应用于电力系统或其它行业系统的优化问题中。     

参数在线跟踪的交流传动系统双神经网络模型参考自适应控制

该文研究的目的在于将一种具有优越的非线性并行处理特征的神经网络引入自适应控制器的设计中，将其并行收敛特性和便于实行的参数设计原则与模型参考自适应控制模式结合起来，进行具有很高自适应控制要求的交流传动系统控制器设计。该文将Hopfield神经网络引入交流传动系统的模型参考自适应控制，通过神经网络控制器来给出交流传动系统的励磁及速度控制器输出，使控制效果具有对某些参数变化的一定程度的鲁棒性。对于不可控的负载转矩分量，加入参数自动跟踪神经网络，构成上有参数在线跟踪功能的交流传动双神经网络模型参考自适应控制模式，进一步提高了系统的控制性能。结果充分证明了Hopfield神经网络在处理自适应交流传动系统控制问题中的适用特征。     

A hybrid HNN-QP approach for dynamic economic dispatch problem

This paper introduces a solution of the dynamic economic dispatch (DED) problem using a hybrid approach of Hopfield neural network (HNN) and quadratic programming (QP). The hybrid algorithm is based on using enhanced HNN; to solve the static part of the problem; the QP algorithm for solving the dynamic part of the DED. This technique guarantees the global optimality of the solution due to its look-ahead capability. The new algorithm is applied and tested to an example from the literature and the solution is then compared with that obtained by some other techniques to prove the superiority and effectiveness of the proposed algorithm.     

智能化检修票和操作票系统的实时数据库设计

实时网络数据库的数据结构设计和实现方法在很大程度上决定了计算机辅助的检修票和操作票开票软件的成败与效果.文中介绍了国电自动化研究院开发的智能化检修票和操作票系统中的实时网络数据库设计要点,该系统已在大型供电网调度部门的实际应用中取得了令人满意的结果.这一设计方法对该领域同类软件的开发具有重要参考价值.     

基于柔性策略-评价网络的微电网源储协同优化调度策略

近年来,微电网中的可再生能源与储能占比不断增大,给其优化调度带来了新的挑战。针对微电网源储协同调度问题中非凸非线性约束带来的求解困难,利用深度强化学习算法构建基于数据的策略函数,通过不断地与环境进行交互学习寻找最优策略,避免了对原非凸非线性问题的直接求解。考虑到训练过程中策略函数可能不满足安全约束,进一步提出了一种利用部分模型信息的微电网源储协同优化调度安全策略学习方法,得到了满足网络安全约束的优化策略。此外,针对强化学习的智能体在训练过程中与环境的交互耗时较长的问题,采用神经网络对环境进行建模以提高学习效率。     

Optimal short-term scheduling for a large-scale cascaded hydrosystem

This paper describes a short term hydro generation optimization program that has been developed by the Hydro Electric Commission (HEC) to determine optimal generation schedules and to investigate export and import capabilities of the Tasmanian system under a proposed DC interconnection with mainland Australia. The optimal hydro scheduling problem is formulated as a large scale linear programming algorithm and is solved using a commercially-available linear programming package. The selected objective function requires minimization of the value of energy used by turbines and spilled during the study period. Alternative formulations of the objective function are also discussed. The system model incorporates the following elements: hydro station (turbine efficiency, turbine flow limits, penstock head losses, tailrace elevation and generator losses), hydro system (reservoirs and hydro network: active volume, spillway flow, flow between reservoirs and travel time), and other models including thermal plant and DC link. A valuable by-product of the linear programming solution is system and unit incremental costs which may be used for interchange scheduling and short-term generation dispatch     

大规模小水电群一体化发电计划编制方法

针对小水电无序管理,弃水、窝电现象严重,水资源浪费问题突出的现状,设计省地一体化小水电发电计划编制方法。该方法规范了小水电计划编制流程,对发电计划实行分级制作与管理,增加了输电断面安全校核环节,并给出了超限断面计划调整方法,通过建议计划上报–输电断面校核–计划协调发布的闭环方式有效提高了发电计划的准确性和可操作性。该方法目前已应用于云南电网小水电管理系统,方法的科学性与有效性得到了实际工程的验证。     

Application of genetic-based neural networks to thermal unitcommitment

A new approach using genetic algorithms based neural networks and dynamic programming (GANN-DP) to solve power system unit commitment problems is proposed in this paper. A set of feasible generator commitment schedules is first formulated by genetic-enhanced neural networks. These pre-committed schedules are then optimized by the dynamic programming technique. By the proposed approach, learning stagnation is avoided. The neural network stability and accuracy are significantly increased. The computational performance of unit commitment in a power system is therefore highly improved. The proposed method has been tested on a practical Taiwan Power (Taipower) thermal system through the utility data. The results demonstrate the feasibility and practicality of this approach     

Algorithms for Itinerary Planning in Multimodal Transportation Networks

The itinerary planning problem in an urban public transport system constitutes a common routing and scheduling decision faced by travelers. The objective of this paper is to present a new formulation and an algorithm for solving the itinerary planning problem, i.e., determination of the itinerary that lexicographically optimizes a set of criteria (i.e., total travel time, number of transfers, and total walking and waiting time) while departing from the origin and arriving at the destination within specified time windows. Based on the proposed formulation, the itinerary planning problem is expressed as a shortest path problem in a multimodal time-schedule network with time windows and time-dependent travel times. A dynamic programming-based algorithm has been developed for the solution of the emerging problem. The special case of the problem involving a mandatory visit at an intermediate stop within a given time window is formulated as two nested itinerary planning problems which are solved by the aforementioned algorithm. The proposed algorithm has been integrated in a Web-based journey planning system, whereas its performance has been assessed by solving real-life itinerary planning problems defined on the Athens urban public transport network, providing fast and accurate solutions.     

电力市场环境下的发电机组检修问题

传统的发电机组检修计划安排在电力市场环境下面临着新的问题和挑战。文中对国内外此领域的研究工作进行了简要而系统的综述。重点论述了下述几个问题：机组检修计划的安排方式,即应由调度机构集中确定还是由发电公司自主确定;检修协调机制;机组检修计划对系统可靠性的影响;发电公司最优机组检修策略;机组检修安排与市场模式、输电设备检修安排和发电容量充裕性等问题的关系。     

Power plant maintenance scheduling: optimizing economics andreliability

The objective of this study is to show the effects that costs, reliability, and constraints have on each other in power plant outage scheduling. A unique and powerful optimizing method is used to study data from a medium-sized utility. Four optimization studies were made. It was found that different optimization criteria give different best maintenance schedules. The optimal reliability and production cost values are coupled to operating constraints and may be improved by relaxing some constraints. The potential savings must be evaluated against the inconvenience and costs of relaxing these operating constraints. Use of an optimum maintenance schedule and judicious relaxation of constraints can lead to production cost reduction on the order of 0.3%. Integer programming can solve real-life maintenance-scheduling problems in reasonable computer time