scholarly journals Optimization Method of Power Equipment Maintenance Plan Decision-Making Based on Deep Reinforcement Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Yanhua Yang ◽  
Ligang Yao
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Optimization Model ◽  
Power Grid ◽  
Optimization Method ◽  
Optimal Decision ◽  
Maintenance Cost ◽  
Equipment Maintenance ◽  
Safety Constraints ◽  
Maintenance Plan

The safe and reliable operation of power grid equipment is the basis for ensuring the safe operation of the power system. At present, the traditional periodical maintenance has exposed the abuses such as deficient maintenance and excess maintenance. Based on a multiagent deep reinforcement learning decision-making optimization algorithm, a method for decision-making and optimization of power grid equipment maintenance plans is proposed. In this paper, an optimization model of power grid equipment maintenance plan that takes into account the reliability and economics of power grid operation is constructed with maintenance constraints and power grid safety constraints as its constraints. The deep distributed recurrent Q-networks multiagent deep reinforcement learning is adopted to solve the optimization model. The deep distributed recurrent Q-networks multiagent deep reinforcement learning uses the high-dimensional feature extraction capabilities of deep learning and decision-making capabilities of reinforcement learning to solve the multiobjective decision-making problem of power grid maintenance planning. Through case analysis, the comparative results show that the proposed algorithm has better optimization and decision-making ability, as well as lower maintenance cost. Accordingly, the algorithm can realize the optimal decision of power grid equipment maintenance plan. The expected value of power shortage and maintenance cost obtained by the proposed method is $71.75$ $MW·H$ and $496000$ $yuan$.

scholarly journals Optimization strategy of operation and maintenance based on econometric model

2021 ◽  
Vol 292 ◽  
pp. 03028
Author(s):  
Xuefei Zhang ◽  
Zhiwei Li ◽  
Chengzhi Wang ◽  
Xuejun Tang ◽  
Sen Yang
Keyword(s):  
Econometric Model ◽  
Power Grid ◽  
Optimal Decision ◽  
Maintenance Cost ◽  
Equipment Maintenance ◽  
Optimization Strategy ◽  
Operation And Maintenance ◽  
Inspection And Maintenance ◽  
Qualification Rate

With the continuous development of power grid, the investment of equipment assets is increasing sharply during the 13th Five Year Plan Period. There is a growing need for equipment maintenance as the equipment ages and varies in different types from transmission to distribution equipment. Equipment is the base element of healthy power grid development. Therefore, it is important to raise the efficiency and quality of equipment status via operation and maintenance. To improve the effectiveness of equipment maintenance, reduce the maintenance cost, improve the safe operation level and power supply reliability of power grid, this paper uses econometric model of correlation analysis to build the correlation between daily overhaul, operation and maintenance and fault frequency and voltage qualification rate, so as to provide optimal decision for the development of operation, inspection and maintenance of power grid company.

scholarly journals Economic Development Based on a Mathematical Model: An Optimal Solution Method for the Fuel Supply of International Road Transport Activity

Energies ◽  
2021 ◽  
Vol 14 (10) ◽  
pp. 2963
Author(s):  
Melinda Timea Fülöp ◽  
Miklós Gubán ◽  
György Kovács ◽  
Mihály Avornicului
Keyword(s):  
Decision Making ◽  
Ad Hoc ◽  
Market Competition ◽  
Optimal Solution ◽  
Cost Savings ◽  
Cost Effective ◽  
Optimization Method ◽  
Optimal Decision ◽  
Environmental Damage ◽  
Fuel Cost

Due to globalization and increased market competition, forwarding companies must focus on the optimization of their international transport activities and on cost reduction. The minimization of the amount and cost of fuel results in increased competition and profitability of the companies as well as the reduction of environmental damage. Nowadays, these aspects are particularly important. This research aims to develop a new optimization method for road freight transport costs in order to reduce the fuel costs and determine optimal fueling stations and to calculate the optimal quantity of fuel to refill. The mathematical method developed in this research has two phases. In the first phase the optimal, most cost-effective fuel station is determined based on the potential fuel stations. The specific fuel prices differ per fuel station, and the stations are located at different distances from the main transport way. The method developed in this study supports drivers’ decision-making regarding whether to refuel at a farther but cheaper fuel station or at a nearer but more expensive fuel station based on the more economical choice. Thereafter, it is necessary to determine the optimal fuel volume, i.e., the exact volume required including a safe amount to cover stochastic incidents (e.g., road closures). This aspect of the optimization method supports drivers’ optimal decision-making regarding optimal fuel stations and how much fuel to obtain in order to reduce the fuel cost. Therefore, the application of this new method instead of the recently applied ad-hoc individual decision-making of the drivers results in significant fuel cost savings. A case study confirmed the efficiency of the proposed method.

The Nature Of Strategic-Decision-Making Models

2011 ◽  
pp. 241-271
Author(s):  
Tamio Shimizu ◽  
Marley Monteiro de Carvalho ◽  
Fernando Jose Barbin
Keyword(s):  
Decision Making ◽  
Goal Function ◽  
Optimization Method ◽  
Strategic Decision ◽  
Optimal Decision ◽  
Problem Solution ◽  
Goal Functions ◽  
Optimal Decision Making ◽  
The Individual ◽  
Optimum Solution

In the multiple goal function problems, there is no optimum solution fully satisfying all goals at the same time. The individual goal’s functions are, in general, conflicting and it is not possible to have an optimization method to solve the problem. There is usually a consensus solution satisfying minimal criteria of optimum values for each individual goal function. This consensus is based on the Pareto’s principle presented in chapter nine. The optimal decision making in problems with multiple goals will be analyzed at the end of this chapter (Goicoechea et al., 1982; Keeney & Raiffa, 1976; Dyson, 1990; Saaty, 1980, 1994; Bonabeau, 2003; Charan, 2001; Choo, 1998; Day et al., 1997). In considering restrictions across several scenarios, the problem solution becomes more difficult due to the high number of possible combinations of goal functions and scenarios to be considered.

Application of Reactive Power Optimization in Power Grid in AVC

2014 ◽  
Vol 971-973 ◽  
pp. 979-982
Author(s):  
Yan Hong Li ◽  
Zhi Rong Zhang
Keyword(s):  
Optimization Model ◽  
Reactive Power ◽  
Power Optimization ◽  
Power Grid ◽  
Optimization Method ◽  
Reactive Power Optimization ◽  
Synchronous Generators ◽  
Hierarchical Partition ◽  
Operating Limits ◽  
External Conditions

Automatic voltage control(AVC) is the highest form of current power grid voltage and reactive power control,during the implementation of AVC, the whole network reactive power optimization isthe core and foundation. Thispaper researches and discuses the application of reactive power optimization inpower grid AVC. In the traditional reactive power optimization, the reactivepower limits of synchronous generators are fixed. In this paper, thesynchronous generator PQ operating limits change with external conditions,thus establishes reactive power optimization model in accordance with therequirements of AVC. Thispaper presents reactive power optimization method based on the principle ofpartition. The method decomposes the system to several partitions. Eachpartition separately optimized, thus reduces the system scale.And the convergence of the algorithm, the calculation speed and the discretevariable processing etc. improve. At the same time, this method reflects theclassification, hierarchical, partition, characteristics of coordinated controlof AVC.

scholarly journals Flexibility to contingency changes distinguishes habitual and goal-directed strategies in humans

2017 ◽  
Author(s):  
Julie J. Lee ◽  
Mehdi Keramati
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Human Subjects ◽  
Relative Influence ◽  
Optimal Decision ◽  
Hybrid Strategy ◽  
Model Free ◽  
Optimal Decision Making ◽  
Value Changes ◽  
Change Task

AbstractDecision-making in the real world presents the challenge of requiring flexible yet prompt behavior, a balance that has been characterized in terms of a trade-off between a slower, prospective goal-directed model-based (MB) strategy and a fast, retrospective habitual model-free (MF) strategy. Theory predicts that flexibility to changes in both reward values and transition contingencies can determine the relative influence of the two systems in reinforcement learning, but few studies have manipulated the latter. Therefore, we developed a novel two-level contingency change task in which transition contingencies between states change every few trials; MB and MF control predict different responses following these contingency changes, allowing their relative influence to be inferred. Additionally, we manipulated the rate of contingency changes in order to determine whether contingency change volatility would play a role in shifting subjects between a MB and MF strategy. We found that human subjects employed a hybrid MB/MF strategy on the task, corroborating the parallel contribution of MB and MF systems in reinforcement learning. Further, subjects did not remain at one level of MB/MF behavior but rather displayed a shift towards more MB behavior over the first two blocks that was not attributable to the rate of contingency changes but rather to the extent of training. We demonstrate that flexibility to contingency changes can distinguish MB and MF strategies, with human subjects utilizing a hybrid strategy that shifts towards more MB behavior over blocks, consequently corresponding to a higher payoff.Author SummaryTo make good decisions, we must learn to associate actions with their true outcomes. Flexibility to changes in action/outcome relationships, therefore, is essential for optimal decision-making. For example, actions can lead to outcomes that change in value – one day, your favorite food is poorly made and thus less pleasant. Alternatively, changes can occur in terms of contingencies – ordering a dish of one kind and instead receiving another. How we respond to such changes is indicative of our decision-making strategy; habitual learners will continue to choose their favorite food even if the quality has gone down, whereas goal-directed learners will soon learn it is better to choose another dish. A popular paradigm probes the effect of value changes on decision making, but the effect of contingency changes is still unexplored. Therefore, we developed a novel task to study the latter. We find that humans used a mixed habitual/goal-directed strategy in which they became more goal-directed over the course of the task, and also earned more rewards with increasing goal-directed behavior. This shows that flexibility to contingency changes is adaptive for learning from rewards, and indicates that flexibility to contingency changes can reveal which decision-making strategy is used.

Probabilistic Spinning Reserve Model of Power System Containing Wind

2015 ◽  
Vol 799-800 ◽  
pp. 1238-1243
Author(s):  
Ning Ning Cui ◽  
Zhe Nan Zhang ◽  
Wei Liu ◽  
Yang Zhang ◽  
Qiang Li
Keyword(s):  
Decision Making ◽  
Power System ◽  
Wind Power ◽  
Optimization Model ◽  
Unit Commitment ◽  
Optimal Scheduling ◽  
Optimal Decision ◽  
Spinning Reserve ◽  
Probability Table ◽  
Optimal Decision Making

In order to reflect the influences of the stochastic uncertain of wind power on the optimal decision-making of the power system spinning reserve, a probabilistic optimization model of the spinning reserve is proposed. Considering uncertain factors such as predicted-deviation of wind, predicted-deviation of load and fault outage of generator, the capacity outage probability table is combined with predicted-deviation of wind and predicted-deviation of load. By introducing the analytic expressed probability reserve constraints into the unit commitment model considering the wind power, the spinning reserve of power system can be optimized to the expectable contingency level. Using a calculation example, the effectiveness of the model is proved, providing a new model for uncertainty analysis and optimal scheduling decisions of power system containing wind.

Sign in / Sign up

Export Citation Format

Share Document