scholarly journals Stream Learning in Energy IoT Systems: A Case Study in Combined Cycle Power Plants

Energies ◽  
2020 ◽  
Vol 13 (3) ◽  
pp. 740 ◽  
Author(s):  
Jesus L. Lobo ◽  
Igor Ballesteros ◽  
Izaskun Oregi ◽  
Javier Del Ser ◽  
Sancho Salcedo-Sanz
Keyword(s):  
Power Plants ◽  
Electrical Power ◽  
Predictive Performance ◽  
Power Production ◽  
Combined Cycle ◽  
Machine Learning Techniques ◽  
Power Prediction ◽  
New Information ◽  
Power And Energy Systems ◽  
Power And Energy

The prediction of electrical power produced in combined cycle power plants is a key challenge in the electrical power and energy systems field. This power production can vary depending on environmental variables, such as temperature, pressure, and humidity. Thus, the business problem is how to predict the power production as a function of these environmental conditions, in order to maximize the profit. The research community has solved this problem by applying Machine Learning techniques, and has managed to reduce the computational and time costs in comparison with the traditional thermodynamical analysis. Until now, this challenge has been tackled from a batch learning perspective, in which data is assumed to be at rest, and where models do not continuously integrate new information into already constructed models. We present an approach closer to the Big Data and Internet of Things paradigms, in which data are continuously arriving and where models learn incrementally, achieving significant enhancements in terms of data processing (time, memory and computational costs), and obtaining competitive performances. This work compares and examines the hourly electrical power prediction of several streaming regressors, and discusses about the best technique in terms of time processing and predictive performance to be applied on this streaming scenario.

scholarly journals Electrical Power Prediction through a Combination of Multilayer Perceptron with Water Cycle Ant Lion and Satin Bowerbird Searching Optimizers

2021 ◽  
Vol 13 (4) ◽  
pp. 2336
Author(s):  
Hossein Moayedi ◽  
Amir Mosavi
Keyword(s):  
Power Plants ◽  
Water Cycle ◽  
Electrical Power ◽  
Optimal Solution ◽  
Population Based ◽  
Influential Factors ◽  
Combined Cycle ◽  
Power Prediction ◽  
Satin Bowerbird ◽  
Ant Lion

Predicting the electrical power (PE) output is a significant step toward the sustainable development of combined cycle power plants. Due to the effect of several parameters on the simulation of PE, utilizing a robust method is of high importance. Hence, in this study, a potent metaheuristic strategy, namely, the water cycle algorithm (WCA), is employed to solve this issue. First, a nonlinear neural network framework is formed to link the PE with influential parameters. Then, the network is optimized by the WCA algorithm. A publicly available dataset is used to feed the hybrid model. Since the WCA is a population-based technique, its sensitivity to the population size is assessed by a trial-and-error effort to attain the most suitable configuration. The results in the training phase showed that the proposed WCA can find an optimal solution for capturing the relationship between the PE and influential factors with less than 1% error. Likewise, examining the test results revealed that this model can forecast the PE with high accuracy. Moreover, a comparison with two powerful benchmark techniques, namely, ant lion optimization and a satin bowerbird optimizer, pointed to the WCA as a more accurate technique for the sustainable design of the intended system. Lastly, two potential predictive formulas, based on the most efficient WCAs, are extracted and presented.

The Elephant in the Room–Gas Turbine Power

2010 ◽  
Vol 132 (12) ◽  
pp. 57-57
Author(s):  
Lee S. Langston
Keyword(s):  
Power Plant ◽  
Electric Power ◽  
Gas Turbine ◽  
Power Plants ◽  
Electrical Power ◽  
Electric Power Industry ◽  
Hydrocarbon Fuel ◽  
Combined Cycle ◽  
Electrical Generator ◽  
Gas Turbine Exhaust

This article presents an overview of gas turbine combined cycle (CCGT) power plants. Modern CCGT power plants are producing electric power as high as half a gigawatt with thermal efficiencies approaching the 60% mark. In a CCGT power plant, the gas turbine is the key player, driving an electrical generator. Heat from the hot gas turbine exhaust is recovered in a heat recovery steam generator, to generate steam, which drives a steam turbine to generate more electrical power. Thus, it is a combined power plant burning one unit of fuel to supply two sources of electrical power. Most of these CCGT plants burn natural gas, which has the lowest carbon content of any other hydrocarbon fuel. Their near 60% thermal efficiencies lower fuel costs by almost half compared to other gas-fired power plants. Their installed capital cost is the lowest in the electric power industry. Moreover, environmental permits, necessary for new plant construction, are much easier to obtain for CCGT power plants.

Cycling Tolerance: Natural Circulation Vertical HRSGs

2003 ◽  
Author(s):  
Pascal Fontaine
Keyword(s):  
Gas Turbines ◽  
Power Plants ◽  
Natural Circulation ◽  
Electrical Power ◽  
Combined Cycle ◽  
Public Utility ◽  
Published Data ◽  
Operating Pressure ◽  
Load Following ◽  
To Come

The US market is currently making a double jump in its HRSG requirements. Heretofore, HRSGs were used largely in industrial size cogen applications. According to the PURPA (Public Utility Regulatory Policy Act), public utilities were required to purchase that electric power generated in excess of the steam host’s needs. Thus, HRSGs were relatively small and operated under constant conditions. Now, HRSGs are much larger (utility size) and also more complex due to the introduction of triple pressure plus reheat behind powerful heavy duty gas turbines. With the onset of deregulation and consequent merchant power, combined cycle plants are now required to supply electrical power to the grid as and when needed with consequent day/night and weekday/weekend cycling. Those merchant plants have to come on and off line with minimal notice and be run sometimes at partial loads. Even units which were originally designed for base load are all eventually forced to cycle as new more efficient power plants are built. Thus, substantial changes in basic HRSG design are needed to cope with these changes. Coincidentally, the types of service projected for USA HRSGs have been in effect in Europe for over two decades. For this reason, European HRSG manufacturers/operators have adopted cycling tolerant Vertical HRSGs based on designs which permit the tubes to expand/contract freely and independently of one another, as distinguished from the more rigid horizontal gas pass design. Thus, fatigue stresses related to load following swings are minimized. This is just an illustration of the specific features of the Vertical European HRSGs for minimizing damages due to cycling related fatigue stresses. Vertical HRSG design shall be considered not only in terms of smaller footprint, but also as a solution to cycling related problems. As generally recognized, the cycling criterion is an integral part of HRSG design. This paper presents solutions to HRSG design issues for cycling tolerant operation. It relates to published data on problems observed with cycling Horizontal HRSGs, and it describes how these problems can be overcome. Concepts, design features and calculation methods applied to cycling tolerant HRSGs are reviewed in detail. Vertical HRSGs have been criticized because of their need for circulation pumps. Interestingly, the need for such pumps was eliminated a decade ago, with the advent of natural circulation for Vertical HRSGs up to 1800 psia (124 bar A) operating pressure.

scholarly journals Planning Under Uncertainty Applications in Power Plants Using Factored Markov Decision Processes

Energies ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2302 ◽  
Author(s):  
Alberto Reyes ◽  
L. Enrique Sucar ◽  
Pablo H. Ibargüengoytia ◽  
Eduardo F. Morales
Keyword(s):  
Markov Decision Processes ◽  
Power Plants ◽  
Combined Cycle ◽  
Decision Processes ◽  
Machine Learning Techniques ◽  
Planning Under Uncertainty ◽  
Hydroelectric Power ◽  
Steam Generation ◽  
Power Domain ◽  
Markov Decision

Due to its ability to deal with non-determinism and partial observability, represent goals as an immediate reward function and find optimal solutions, planning under uncertainty using factored Markov Decision Processes (FMDPs) has increased its importance and usage in power plants and power systems. In this paper, three different applications using this approach are described: (i) optimal dam management in hydroelectric power plants, (ii) inspection and surveillance in electric substations, and (iii) optimization of steam generation in a combined cycle power plant. For each case, the technique has demonstrated to find optimal action policies in uncertain settings, present good response and compilation times, deal with stochastic variables and be a good alternative to traditional control systems. The main contributions of this work are as follows, a methodology to approximate a decision model using machine learning techniques, and examples of how to specify and solve problems in the electric power domain in terms of a FMDP.

Sign in / Sign up

Export Citation Format

Share Document