A fuzzy reinforcement learning approach to thermal unit commitment problem

Unit commitment problem (UCP) aims at optimizing generation cost for meeting a given load demand under several operational constraints. We propose to use fuzzy reinforcement learning (RL) approach for efficient and reliable solution to the unit commitment problem. In particular, we cast UCP as a multiagent fuzzy reinforcement learning task wherein individual generators act as players for optimizing the cost to meet a given load over a twenty-four-hour period. Unit commitment task has been fuzzified, and the most optimal unit commitment solution is generated by employing RL on this fuzzy multigenerator setup. Our proposed multiagent RL framework does not assume any a priori task or system knowledge, and the generators gradually learn to produce most optimal output solely based on their collective generation. We look at the UCP as a sequential decision-making task with reward/penalty to reduce the collective generation cost of generators. To the best of our knowledge, ours is a first attempt at solving UCP by employing fuzzy reinforcement learning. We test our approach on a ten-generating-unit system with several equality and inequality constraints. Simulation results and comparisons against several recent UCP solution methods prove superiority and viability of our proposed multiagent fuzzy reinforcement learning technique.

     

Profit based unit commitment: A parallel ABC approach using a workstation cluster

This paper proposes a parallel artificial bee colony (PABC) approach for committing generating units thereby maximizing the profit of generation companies. Profit based unit commitment (PBUC) must be obtained in a short time even though there is an increase in generating units. Nowadays, computing resources are available in plenty, and effective utilization of these resources will be advantageous for reducing the time complexity for a large scale power system. Here, the message passing interface based technique is used in the PABC algorithm in distributed and shared memory models. The time complexity and the solution quality with respect to the number of processors in a cluster are thoroughly analyzed. PABC for PBUC is tested for a power system ranging from 10 to 1000 generating units. Also the PABC is validated for economic dispatch and the unit commitment problem in a traditional power system on 40 and 10 unit systems, respectively.     

A hybrid neural network and simulated annealing approach to the unit commitment problem

In this paper, the authors present an approach combining the feedforward neural network and the simulated annealing method to solve unit commitment, a mixed integer combinatorial optimisation problem in power system. The artificial neural network is used to determine the discrete variables corresponding to the state of each unit at each time interval. The simulated annealing method is used to generate the continuous variables corresponding to the power output of each unit and the production cost. The type of neural network used in this method is a multi-layer perceptron trained by the back-propagation algorithm. A set of load profiles as inputs and the corresponding unit commitment schedules as outputs (satisfying the minimum up–down, spinning reserve and crew constraints) are utilized to train the network. A method to generate the training patterns is also presented. The experimental result demonstrates that the proposed approach can solve unit commitment in a reduced computational time with an optimum generation schedule.     

Stochastic unit commitment problem

The electric power industry is undergoing restructuring and deregulation. We need to incorporate the uncertainty of electric power demand or power generators into the unit commitment problem. The unit commitment problem is to determine the schedule of power generating units and the generating level of each unit. The objective is to minimize the operational cost which is given by the sum of the fuel cost and the start‐up cost. In this paper we propose a new algorithm for the stochastic unit commitment problem which is based on column generation approach. The algorithm continues adding schedules from the dual solution of the restricted linear master program until the algorithm cannot generate new schedules. The schedule generation problem is solved by the calculation of dynamic programming on the scenario tree.     

An ICA based approach for solving profit based unit commitment problem market

With the advent of paralleling and implementation of restructuring in the power market, some routine rules and patterns of traditional market should be accomplished in a way different from the past. To this end, the unit commitment (UC) scheduling that has once been aimed at minimizing operating costs in an integrated power market, is metamorphosed to profit based unit commitment (PBUC) by adopting a new schema, in which generation companies (GENCOs) have a common tendency to maximize their own profit. In this paper, a novel optimization technique called imperialist competitive algorithm (ICA) as well as an improved version of this evolutionary algorithm are employed for solving the PBUC problem. Moreover, traditional binary approach of coding of initial solutions is replaced with an improved integer based coding method in order to reduce computational complexity and subsequently ameliorate convergence procedure of the proposed method. Then, a sub-ICA algorithm is proposed to obtain optimal generation power of thermal units. Simulation results validate effectiveness and applicability of the proposed method on two scenarios: (a) a set of unimodal and multimodal standard benchmark functions, (b) two GENCOs consist of 10 and 100 generating units.     

A low-cost evolutionary algorithm for the unit commitment problem considering probabilistic unit outages

This article presents a solution method to the unit commitment problem with probabilistic unit failures and repairs, which is based on evolutionary algorithms and Monte Carlo simulations. Regarding the latter, thousands of availability–unavailability trial time patterns along the scheduling horizon are generated. The objective function to be minimised is the expected total operating cost, computed after adapting any candidate solution, i.e. any series of generating/non-generating (ON/OFF) unit states, to the availability–unavailability patterns and performing evaluations by considering fuel, start-up and shutdown costs as well as the cost for buying electricity from external resources, if necessary. The proposed method introduces a new efficient chromosome representation: the decision variables are integer IDs corresponding to the binary-to-decimal converted ON/OFF (1/0) scenarios that cover the demand in each hour. In contrast to previous methods using binary strings as chromosomes, the new chromosome must be penalised only if any of the constraints regarding start-up, shutdown and ramp times cannot be met, chromosome repair is avoided and, consequently, the dispatch problems are solved once in the preparatory phase instead of during the evolution. For all these reasons, with or without probabilistic outages, the proposed algorithm has much lower CPU cost. In addition, if probabilistic outages are taken into account, a hierarchical evaluation scheme offers extra noticeable gain in CPU cost: the population members are approximately pre-evaluated using a small ‘representative’ set of the Monte Carlo simulations and only a few top population members undergo evaluations through the full Monte Carlo simulations. The hierarchical scheme makes the proposed method about one order of magnitude faster than its conventional counterpart.     

Heuristic solutions to the long-term unit commitment problem with cogeneration plants

We consider a long-term version of the unit commitment problem that spans over one year divided into hourly time intervals. It includes constraints on electricity and heating production as well as on biomass consumption. The problem is of interest for scenario analysis in long-term strategic planning. We model the problem as a large mixed integer programming problem. Two solutions to this problem are of interest but computationally intractable: the optimal solution and the solution derived by market simulation. To achieve good and fast approximations to these two solutions, we design heuristic algorithms, including mixed integer programming heuristics, construction heuristics and local search procedures. Two setups are the best: a relax and fix mixed integer programming approach with an objective function reformulation and a combination of a dispatching heuristic with stochastic local search. The work is developed in the context of the Danish electricity market and the computational analysis is carried out on real-life data.     

A deterministic annular crossover genetic algorithm optimisation for the unit commitment problem

One of the disadvantages of traditional genetic algorithms is premature convergence because the selection operator depends on the quality of the individual, with the result that the genetic information of the best individuals tends to dominate the characteristics of the population. Furthermore, when the representation of the chromosome is linear, the crossover is sensitive to the encoding or depends on the gene position. The ends of this type of chromosome have only a very low probability of changing by mutation. In this work a genetic algorithm is applied to the unit commitment problem using a deterministic selection operator, where all the individuals of the population are selected as parents according to an established strategy, and an annular crossover operator where the chromosome is in the shape of a ring. The results obtained show that, with the application of the proposed operators to the unit commitment problem, better convergences and solutions are obtained than with the application of traditional genetic operators.     

Genetic algorithm with binary representation of generating unit start-up and shut-down times for the unit commitment problem

An approach for solving the unit commitment problem based on genetic algorithm with binary representation of the unit start-up and shut-down times is presented. The proposed definition of the decision variables and their binary representation reduce the solution space and computational time in comparison to the classical genetic algorithm approach to unit commitment. The method incorporates time-dependent start-up costs, demand and reserve constraints, minimum up and down time constraints and units power generation limits. Penalty functions are applied to the infeasible solutions. Test results showed an improvement in effectiveness and computational time compared to results obtained from genetic algorithm with standard binary representation of the unit states and other methods.     

A fuzzy logic approach for dealing with qualitative quality characteristics of a process

Dealing with qualitative information is quite common in real life problems. So far research focused on developing process adjustment models only for quantitative data. This paper presents a process adjustment approach of a deteriorating process in which quality characteristics are expressed in qualitative form. This approach jointly determines the initial setting of process mean and production run. A fuzzy logic is adopted to implement the process adjustment approach. The features of this approach are lack of mathematical complexity and ability to deal with qualitative data. Detailed implementation of the fuzzy process adjustment model is also given in this paper.     

Multi-agent modeling for solving profit based unit commitment problem

Profit based unit commitment problem (PBUC) from power system domain is a high-dimensional, mixed variables and complex problem due to its combinatorial nature. Many optimization techniques for solving PBUC exist in the literature. However, they are either parameter sensitive or computationally expensive. The quality of PBUC solution is important for a power generating company (GENCO) because this solution would be the basis for a good bidding strategy in the competitive deregulated power market. In this paper, the thermal generators of a GENCO is modeled as a system of intelligent agents in order to generate the best profit solution. A modeling for multi-agents is done by decomposing PBUC problem so that the profit maximization can be distributed among the agents. Six communication and negotiation stages are developed for agents that can explore the possibilities of profit maximization while respecting PBUC problem constraints. The proposed multi-agent modeling is tested for different systems having 10–100 thermal generators considering a day ahead scheduling. The results demonstrate the superiority of proposed multi-agent modeling for PBUC over the benchmark optimization techniques for generating the best profit solutions in substantially smaller computation time.     

A unit test approach for database schema evolution

Context

The constant changes in today’s business requirements demand continuous database revisions. Hence, database structures, not unlike software applications, deteriorate during their lifespan and thus require refactoring in order to achieve a longer life span. Although unit tests support changes to application programs and refactoring, there is currently a lack of testing strategies for database schema evolution.

Objective

This work examines the challenges for database schema evolution and explores the possibility of using various testing strategies to assist with schema evolution. Specifically, the work proposes a novel unit test approach for the application code that accesses databases with the objective of proactively evaluating the code against the altered database.

Method

The approach was validated through the implementation of a testing framework in conjunction with a sample application and a relatively simple database schema. Although the database schema in this study was simple, it was nevertheless able to demonstrate the advantages of the proposed approach.

Results

After changes in the database schema, the proposed approach found all SELECT statements as well as the majority of other statements requiring modifications in the application code. Due to its efficiency with SELECT statements, the proposed approach is expected to be more successful with database warehouse applications where SELECT statements are dominant.

Conclusion

The unit test approach that accesses databases has proven to be successful in evaluating the application code against the evolved database. In particular, the approach is simple and straightforward to implement, which makes it easily adoptable in practice.     

A novel process monitoring approach with dynamic independent component analysis

A novel process monitoring scheme is proposed to compensate for shortcomings in the conventional independent component analysis (ICA) based monitoring method. The primary idea is first to augment the observed data matrix in order to take the process dynamic into consideration. An outlier rejection rule is then proposed to screen out outliers, in order to better describe the majority of the data. Finally, a rectangular measure is used as a monitoring statistic. The proposed approach is investigated via three cases: a simulation example, the Tennessee Eastman process and a real industrial case. Results indicate that the proposed method is more efficient as compared to alternate methods.     

A systemic approach to process modeling

This article presents a system's view of a common sense management model for systems (COSMOS) [1]. Salient features of COSMOS are introduced through the unfolding story of process development of a hypothetical corporation called IM Co. This systemic view models the dynamic complexity of a system or organization so that inerrelationships, rather than things, patterns of changes, rather than snapshots, are captured. COSMOS views changes as an ongoing opportunity and provides guidance for system changes to be performed in small steps. However, these small steps can build a long lever that is capable of producing dramatic effects. When performing changes, essential trade-offs have to be considered. COSMOS provides three perspectives—activity, communication, and infrastructure—of a process to assist managers in dealing with these trade-offs. The model also includes a generic two-level hierarchy—control and execution levels—to keep balance among the three perspectives.Small Is Beautiful — Ernst Fredrich Schumacher Give me a lever long enough ... and single-handed I can move the world — Archimedes     

Identification of a process with control valve stiction using a fuzzy system: A data-driven approach

Many researchers focus on detecting and modelling the valve stiction because it has undesirable effects on the control loop performance, which consequently results in poor product quality and increased energy consumption. It is difficult to model a process with a sticky valve using the mathematical definition because of its nonlinear properties such as stiction, hysteresis, dead band and dead zone. This work aims to develop and determine the appropriate model of a process with stiction, which can be used in controller design to mitigate the undesirable effect of the stiction. To achieve this goal by mapping the process with valve stiction to a fuzzy system, a dynamic fuzzy model of the plant is derived through an iterative well-developed fuzzy clustering algorithm, which generates suitable antecedent parameters from a set of input–output measurements that are obtained from the control output (OP) and the process output (PV). To determine the consequent parameters, the least square (LS) estimation is applied. The results reveal that the obtained data-driven Takagi–Sugeno-type (TS) fuzzy rule-based model can effectively represent an appropriate model of the process with stiction for different amounts of stiction that are obtained from the simulation and different industrial loops.     

An efficient hybrid Taguchi-immune algorithm for the unit commitment problem

In this paper, a hybrid Taguchi-immune algorithm (HTIA) is presented to deal with the unit commitment problem. HTIA integrates the Taguchi method and the traditional immune algorithm (TIA), providing a powerful global exploration capability. Taguchi method (TM) has been widely used in experimental designs for problems with multiple parameters, and is incorporated into TIA in this paper for the crossover operation to select a better gene. The effectiveness and efficiency of HTIA are demonstrated by several case studies, and the results are compared with other methods published before. Test results show that the proposed method is feasible, robust, and more effective than many other previously developed computation algorithms.     

An improved binary particle swarm optimization for unit commitment problem

This paper proposes a new improved binary PSO (IBPSO) method to solve the unit commitment (UC) problem, which is integrated binary particle swarm optimization (BPSO) with lambda-iteration method. The IBPSO is improved by priority list based on the unit characteristics and heuristic search strategies to repair the spinning reserve and minimum up/down time constraints. To verify the advantages of the IBPSO method, the IBPSO is tested and compared to the other methods on the systems with the number of units in the range of 10–100. Numerical results demonstrate that the IBPSO is superior to other methods reported in the literature in terms of lower production cost and shorter computational time.     

Advanced process control system for a crude distillation unit. A case study

Development, implementation, and operation of an advanced control system for a crude distillation unit are described. The system is based on Honeywell Profit® Controller software. The paper outlines the CDU/VDU-4 plant of Gasprom Neftekhim Salavat JSC (Bashkortostan Republic, Russia) as a control object, discusses project implementation phases, mentions APC maintenance issues, and summarizes key success factors.     

A neuro-genetic approach for modeling and optimizing a complex cogeneration process

Cogeneration is the simultaneous generation of electricity and useful heat with the aim of exploiting more efficiently the energy stored in the fuel. Cogeneration is, however, a complex process that encompasses a great amount of sub-systems and variables. This fact makes it very difficult to obtain an analytical model of the whole plant, and therefore providing a mechanism or a methodology able to optimize the global behavior. This paper proposes a neuro-genetic strategy for modeling and optimizing a cogeneration process of a real industrial plant. Firstly, the modeling of the process is carried out by means of several interconnected neural networks where, each neural network deals with a particular sub-system of the plant. Next, the obtained models are used by a genetic algorithm, which solves a multiobjective optimization problem of the plant, where the goal is to minimize the fuel consumption and maximize both the generated electricity and the use of the heat. The proposed approach is evaluated with data of a real cogeneration plant collected over a one-year period. Obtained results show not only that the modeling of the plant is correct but also that the optimization increases significantly the efficiency of the cogeneration plant.     

A systematic approach to business process reengineering

In this study, a business process is defined as a set of various tasks which are closely inter-related and is assumed to have its own objectives to achieve. A set of processes constitute a business system. Many business process reengineering plans turned out to be unsuccessful because they are based on the existing process which assumed tasks along the process independent or based on the assumption that a process is independent of other processes. This approach generated redundant tasks or led to conflict between business processes. Under this approach, it very difficult to predict the result of the plan due to localized analysis of the process. To avoid aforementioned problems, a systematic, analytic and iterative approach to build up a master plan for business process reengineering is proposed.