Neural Computation and Applications for Sustainable Energy Systems

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Energy Systems".

Deadline for manuscript submissions: closed (31 July 2020) | Viewed by 56475

Special Issue Editors


E-Mail Website
Guest Editor
UNICT, Department of Electrical, Electronics and Informatics Engineering (DIEEI), University of Catania, 95125 Catania, Italy
Interests: neural networks; wavelet theory; statistical pattern recognition; Bayesian networks; integrated generation systems; renewable energy sources; battery storage modeling and simulation
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
UNICT, Department of Electrical, Electronics and Informatics Engineering (DIEEI), University of Catania, 95125 Catania, Italy
Interests: neural networks; electronic devices; organic solar cells; photovoltaic; renewable energy; renewable energy sources; pattern recognition
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Renewable energy sources, including photovoltaic (PV) and wind generators, are now utilized in integrated generation systems (IGSs) and smart grids (SGs) at sites that have a large potential of either solar power, wind power, or both. Nevertheless, such generation systems cannot be a continuous source of energy, due to their seasonal and intermittent nature, e.g., a stand-alone solar PV system cannot provide reliable power during non-sunny days, and a wind system cannot satisfy constant power demands due to significant fluctuations in the magnitude of wind speed from hour to hour for an entire year. Therefore, when using the above sources, the produced energy has to be properly managed in order to reduce the effect of the power fluctuations. The problems of data prediction and having an accurate source of power forecasting must be solved to provide help to the system operator to consider this renewable source in economic scheduling and other typical tasks of the electrical power system or smart grid applications. In this Special Issue, all the latest innovative methods based on neural networks and similar intelligent methods are welcomed. Possible submissions are not limited to these topics, and any other proposals in the field related to intelligent methods of sustainable energy systems are welcome too. Potential topics consist of but are not limited to the following:

  • Applications of intelligent methods to smart grids;
  • Energy management in photovoltaic plants that makes use of neural predictions;
  • Intelligent energy management in wind farms;
  • Optimal energy dispatch management using neural network (intelligent) predictors;
  • Optimal management of various renewable energy sources;
  • Cloud-based energy management in intelligent smart grids.

Prof. Dr. Giacomo Capizzi
Dr. Grazia Lo Sciuto
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • neural networks
  • renewable energy
  • energy management
  • photovoltaic plants
  • wind farm
  • fuzzy logic
  • genetic algorithms
  • cloud computing
  • nature-inspired predictions methods

Published Papers (16 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 7387 KiB  
Article
Performance Monitoring of Wind Turbines Gearbox Utilising Artificial Neural Networks — Steps toward Successful Implementation of Predictive Maintenance Strategy
by Basheer Wasef Shaheen and István Németh
Processes 2023, 11(1), 269; https://doi.org/10.3390/pr11010269 - 13 Jan 2023
Cited by 3 | Viewed by 2147
Abstract
Manufacturing and energy sectors provide vast amounts of maintenance data and information which can be used proactively for performance monitoring and prognostic analysis which lead to improve maintenance planning and scheduling activities. This leads to reduced unplanned shutdowns, maintenance costs and any fatal [...] Read more.
Manufacturing and energy sectors provide vast amounts of maintenance data and information which can be used proactively for performance monitoring and prognostic analysis which lead to improve maintenance planning and scheduling activities. This leads to reduced unplanned shutdowns, maintenance costs and any fatal events that could affect the operations of the overall system. Performance and condition monitoring are among the most used strategies for prognostic and health management (PHM), in which different methods and techniques can be implemented to analyse maintenance and online data. Offshore wind turbines (WTs) are complex systems increasingly needing maintenance. This study proposes a performance monitoring system to monitor the performance of the WT power generation process by exploiting artificial neural networks (ANN) composed of different network designs and training algorithms, using simulated supervisory control and data acquisition (SCADA) data. The performance monitoring is based on different operating modes of the same type of wind turbine. The degradation models were developed based on the generated active power resulting from different degradation levels of the gearbox, which is a critical component of the WTs. The deviations of the wind power curves for all operating modes over time are monitored in terms of the resulting power residuals and are modelled using ANN with a unique network architecture. The monitoring process uses the recursive form of the cumulative summation (CUSUM) change detection algorithm to detect the state change point in which the gearbox efficiency is degraded by evaluating the power residuals predicted by the ANN model. To increase the monitoring effectiveness, a second ANN model was developed to predict the gearbox efficiency to monitor any failure that could happen once the efficiency degrades below a threshold. The results show a high degree of accuracy in power and efficiency prediction in addition to monitoring the abnormal state or deviations of the power generation process resulting from the degraded gearbox efficiency and their corresponding time slots. The developed monitoring method can be a valuable tool to provide maintenance experts with alarms and insights into the general state of the power generation process, which can be used for further maintenance decision-making. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

10 pages, 933 KiB  
Article
Optimization of Energy Recovery from Hazardous Waste in a Waste Incineration Plant with the Use of an Application
by Agata Wajda, Rafał Brociek and Mariusz Pleszczyński
Processes 2022, 10(3), 462; https://doi.org/10.3390/pr10030462 - 24 Feb 2022
Cited by 8 | Viewed by 2329
Abstract
Recovering energy from waste is a positive element in the operation of a waste incineration plant. Hazardous waste is a very diverse group, including in terms of its fuel properties. Carrying out the thermal process in this case is associated with the difficulty [...] Read more.
Recovering energy from waste is a positive element in the operation of a waste incineration plant. Hazardous waste is a very diverse group, including in terms of its fuel properties. Carrying out the thermal process in this case is associated with the difficulty in maintaining stable conditions. This may translate into the efficiency of energy recovery from waste. The article presents a tool supporting the work of hazardous waste incineration plant operators, the aim of which is to select waste for a batch of input material in a manner that ensures process stability and efficient energy recovery. The tool is an application in which the bee algorithm is implemented. It selects the optimal solution to the problem, in accordance with the assumed parameters. The application tests in laboratory conditions were satisfactory and indicated compliance with the assumptions and stability of the solution. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

27 pages, 10064 KiB  
Article
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability
by Muna Mohammed Bazuhair, Siti Zulaikha Mohd Jamaludin, Nur Ezlin Zamri, Mohd Shareduwan Mohd Kasihmuddin, Mohd. Asyraf Mansor, Alyaa Alway and Syed Anayet Karim
Processes 2021, 9(8), 1292; https://doi.org/10.3390/pr9081292 - 26 Jul 2021
Cited by 20 | Viewed by 2331
Abstract
One of the influential models in the artificial neural network (ANN) research field for addressing the issue of knowledge in the non-systematic logical rule is Random k Satisfiability. In this context, knowledge structure representation is also the potential application of Random k Satisfiability. [...] Read more.
One of the influential models in the artificial neural network (ANN) research field for addressing the issue of knowledge in the non-systematic logical rule is Random k Satisfiability. In this context, knowledge structure representation is also the potential application of Random k Satisfiability. Despite many attempts to represent logical rules in a non-systematic structure, previous studies have failed to consider higher-order logical rules. As the amount of information in the logical rule increases, the proposed network is unable to proceed to the retrieval phase, where the behavior of the Random Satisfiability can be observed. This study approaches these issues by proposing higher-order Random k Satisfiability for k ≤ 3 in the Hopfield Neural Network (HNN). In this regard, introducing the 3 Satisfiability logical rule to the existing network increases the synaptic weight dimensions in Lyapunov’s energy function and local field. In this study, we proposed an Election Algorithm (EA) to optimize the learning phase of HNN to compensate for the high computational complexity during the learning phase. This research extensively evaluates the proposed model using various performance metrics. The main findings of this research indicated the compatibility and performance of Random 3 Satisfiability logical representation during the learning and retrieval phase via EA with HNN in terms of error evaluations, energy analysis, similarity indices, and variability measures. The results also emphasized that the proposed Random 3 Satisfiability representation incorporates with EA in HNN is capable to optimize the learning and retrieval phase as compared to the conventional model, which deployed Exhaustive Search (ES). Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

28 pages, 9838 KiB  
Article
Artificial Immune System in Doing 2-Satisfiability Based Reverse Analysis Method via a Radial Basis Function Neural Network
by Shehab Abdulhabib Alzaeemi and Saratha Sathasivam
Processes 2020, 8(10), 1295; https://doi.org/10.3390/pr8101295 - 16 Oct 2020
Cited by 8 | Viewed by 2411
Abstract
A radial basis function neural network-based 2-satisfiability reverse analysis (RBFNN-2SATRA) primarily depends on adequately obtaining the linear optimal output weights, alongside the lowest iteration error. This study aims to investigate the effectiveness, as well as the capability of the artificial immune system (AIS) [...] Read more.
A radial basis function neural network-based 2-satisfiability reverse analysis (RBFNN-2SATRA) primarily depends on adequately obtaining the linear optimal output weights, alongside the lowest iteration error. This study aims to investigate the effectiveness, as well as the capability of the artificial immune system (AIS) algorithm in RBFNN-2SATRA. Moreover, it aims to improve the output linearity to obtain the optimal output weights. In this paper, the artificial immune system (AIS) algorithm will be introduced and implemented to enhance the effectiveness of the connection weights throughout the RBFNN-2SATRA training. To prove that the introduced method functions efficiently, five well-established datasets were solved. Moreover, the use of AIS for the RBFNN-2SATRA training is compared with the genetic algorithm (GA), differential evolution (DE), particle swarm optimization (PSO), and artificial bee colony (ABC) algorithms. In terms of measurements and accuracy, the simulation results showed that the proposed method outperformed in the terms of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), Schwarz Bayesian Criterion (SBC), and Central Process Unit time (CPU time). The introduced method outperformed the existing four algorithms in the aspect of robustness, accuracy, and sensitivity throughout the simulation process. Therefore, it has been proven that the proposed AIS algorithm effectively conformed to the RBFNN-2SATRA in relation to (or in terms of) the average value of training of RMSE rose up to 97.5%, SBC rose up to 99.9%, and CPU time by 99.8%. Moreover, the average value of testing in MAE was rose up to 78.5%, MAPE was rose up to 71.4%, and was capable of classifying a higher percentage (81.6%) of the test samples compared with the results for the GA, DE, PSO, and ABC algorithms. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

19 pages, 1711 KiB  
Article
Election Algorithm for Random k Satisfiability in the Hopfield Neural Network
by Saratha Sathasivam, Mohd. Asyraf Mansor, Mohd Shareduwan Mohd Kasihmuddin and Hamza Abubakar
Processes 2020, 8(5), 568; https://doi.org/10.3390/pr8050568 - 11 May 2020
Cited by 41 | Viewed by 3147
Abstract
Election Algorithm (EA) is a novel variant of the socio-political metaheuristic algorithm, inspired by the presidential election model conducted globally. In this research, we will investigate the effect of Bipolar EA in enhancing the learning processes of a Hopfield Neural Network (HNN) to [...] Read more.
Election Algorithm (EA) is a novel variant of the socio-political metaheuristic algorithm, inspired by the presidential election model conducted globally. In this research, we will investigate the effect of Bipolar EA in enhancing the learning processes of a Hopfield Neural Network (HNN) to generate global solutions for Random k Satisfiability (RANkSAT) logical representation. Specifically, this paper utilizes a bipolar EA incorporated with the HNN in optimizing RANkSAT representation. The main goal of the learning processes in our study is to ensure the cost function of RANkSAT converges to zero, indicating the logic function is satisfied. The effective learning phase will affect the final states of RANkSAT and determine whether the final energy is a global minimum or local minimum. The comparison will be made by adopting the same network and logical rule with the conventional learning algorithm, namely, exhaustive search (ES) and genetic algorithm (GA), respectively. Performance evaluation analysis is conducted on our proposed hybrid model and the existing models based on the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Sum of Squared Error (SSE), and Mean Absolute Error (MAPE). The result demonstrates the capability of EA in terms of accuracy and effectiveness as the learning algorithm in HNN for RANkSAT with a different number of neurons compared to ES and GA. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

11 pages, 2245 KiB  
Article
The Integration of Collaborative Robot Systems and Their Environmental Impacts
by Lucian Stefanita Grigore, Iustin Priescu, Daniela Joita and Ionica Oncioiu
Processes 2020, 8(4), 494; https://doi.org/10.3390/pr8040494 - 23 Apr 2020
Cited by 19 | Viewed by 3921
Abstract
Today, industrial robots are used in dangerous environments in all sectors, including the sustainable energy sector. Sensors and processors collect and transmit information and data from users as a result of the application of robot control systems and sensory feedback. This paper proposes [...] Read more.
Today, industrial robots are used in dangerous environments in all sectors, including the sustainable energy sector. Sensors and processors collect and transmit information and data from users as a result of the application of robot control systems and sensory feedback. This paper proposes that the estimation of a collaborative robot system’s performance can be achieved by evaluating the mobility of robots. Scenarios have been determined in which an autonomous system has been used for intervention in crisis situations due to fire. The experimental model consists of three autonomous vehicles, two of which are ground vehicles and the other is an aerial vehicle. The conclusion of the research described in this paper highlights the fact that the integration of robotic systems made up of autonomous vehicles working in unstructured environments is difficult and at present there is no unitary analytical model. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

13 pages, 951 KiB  
Article
A New Improved Learning Algorithm for Convolutional Neural Networks
by Jie Yang, Junhong Zhao, Lu Lu, Tingting Pan and Sidra Jubair
Processes 2020, 8(3), 295; https://doi.org/10.3390/pr8030295 - 4 Mar 2020
Cited by 5 | Viewed by 3481
Abstract
The back-propagation (BP) algorithm is usually used to train convolutional neural networks (CNNs) and has made greater progress in image classification. It updates weights with the gradient descent, and the farther the sample is from the target, the greater the contribution of it [...] Read more.
The back-propagation (BP) algorithm is usually used to train convolutional neural networks (CNNs) and has made greater progress in image classification. It updates weights with the gradient descent, and the farther the sample is from the target, the greater the contribution of it to the weight change. However, the influence of samples classified correctly but that are close to the classification boundary is diminished. This paper defines the classification confidence as the degree to which a sample belongs to its correct category, and divides samples of each category into dangerous and safe according to a dynamic classification confidence threshold. Then a new learning algorithm is presented to penalize the loss function with danger samples but not all samples to enable CNN to pay more attention to danger samples and to learn effective information more accurately. The experiment results, carried out on the MNIST dataset and three sub-datasets of CIFAR-10, showed that for the MNIST dataset, the accuracy of Non-improve CNN reached 99.246%, while that of PCNN reached 99.3%; for three sub-datasets of CIFAR-10, the accuracies of Non-improve CNN are 96.15%, 88.93%, and 94.92%, respectively, while those of PCNN are 96.44%, 89.37%, and 95.22%, respectively. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

18 pages, 5097 KiB  
Article
Exergo-Economic Optimization of Organic Rankine Cycle for Saving of Thermal Energy in a Sample Power Plant by Using of Strength Pareto Evolutionary Algorithm II
by Sina Mehrdad, Reza Dadsetani, Alireza Amiriyoon, Arturo S. Leon, Mohammad Reza Safaei and Marjan Goodarzi
Processes 2020, 8(3), 264; https://doi.org/10.3390/pr8030264 - 26 Feb 2020
Cited by 31 | Viewed by 3018
Abstract
Waste heat recovery plays an important role in energy source management. Organic Rankine Cycle (ORC) can be used to recover low-temperature waste heat. In the present work a sample power plant waste heat was used to operate an ORC. First, two pure working [...] Read more.
Waste heat recovery plays an important role in energy source management. Organic Rankine Cycle (ORC) can be used to recover low-temperature waste heat. In the present work a sample power plant waste heat was used to operate an ORC. First, two pure working fluids were selected based on their merits. Four possible thermodynamic models were considered in the analysis. They were defined based on where the condenser and evaporator temperatures are located. Four main thermal parameters, evaporator temperature, condenser temperature, degree of superheat and pinch point temperature difference were taken as key parameters. Levelized energy cost values and exergy efficiency were calculated as the optimization criteria. To optimize exergy and economic aspects of the system, Strength Pareto evolutionary algorithm II (SPEA II) was implemented. The Pareto frontier solutions were ordered and chose by TOPSIS. Model 3 outperformed all other models. After evaluating exergy efficiency by mixture mass fraction, R245fa [0.6]/Pentane [0.4] selected as the most efficient working fluid. Finally, every component’s role in determining the levelized energy cost and the exergy efficiency and were discussed. The turbine, condenser and evaporator were found as the costliest components. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

17 pages, 3369 KiB  
Article
An Integrated LHS–CD Approach for Power System Security Risk Assessment with Consideration of Source–Network and Load Uncertainties
by Shiwei Xia, Liangyun Song, Yi Wu, Zhoujun Ma, Jiangping Jing, Zhaohao Ding and Gengyin Li
Processes 2019, 7(12), 900; https://doi.org/10.3390/pr7120900 - 2 Dec 2019
Cited by 8 | Viewed by 2170
Abstract
Large-scale wind power integrated into power grids brings serious uncertainties and risks for power system safe operation, and it is imperative to evaluate power system security risk pertinent to high-level of uncertainties. In this paper, a comprehensive source–network–load probabilistic model, representing the typical [...] Read more.
Large-scale wind power integrated into power grids brings serious uncertainties and risks for power system safe operation, and it is imperative to evaluate power system security risk pertinent to high-level of uncertainties. In this paper, a comprehensive source–network–load probabilistic model, representing the typical uncertainties penetrated in power generation transmission consumption portion, is firstly set for power system operation. Afterwards an integrated LHS–CD approach based on the Latin hypercube sampling (LHS) and Cholesky decomposition (CD) is tailored to effectively conduct the security risk assessment, in which the LHS is utilized to stratified sample the uncertainties of wind power and thermal power, transmission line outage, and load demands, while the CD part is adopted to address the correlations of uncertainties by rearranging the sampled matrix generated by LHS. Moreover, static voltage risk and transmission line overloaded risk index are properly defined for quantitatively evaluating power system operational security risk. Simulation results of a modified New England 39-bus system confirm that the proposed integrated LHS–CD approach is effective and efficient for power system security risk assessment with consideration of source–network–load demand uncertainties. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

17 pages, 1757 KiB  
Article
Applications of TQM Processes to Increase the Management Performance of Enterprises in the Romanian Renewable Energy Sector
by Mihail Busu
Processes 2019, 7(10), 685; https://doi.org/10.3390/pr7100685 - 2 Oct 2019
Cited by 14 | Viewed by 4681
Abstract
This paper focuses on total quality management (TQM) processes and their applications to increase the management performance of enterprises in the renewable energy sector (RES). TQM is a modern tool used by enterprises to increase their management performance. We start with a description [...] Read more.
This paper focuses on total quality management (TQM) processes and their applications to increase the management performance of enterprises in the renewable energy sector (RES). TQM is a modern tool used by enterprises to increase their management performance. We start with a description of Edwards Deming’s conceptualized model, highlighting different phases of its development as described in the literature. The TQM process is then used for an application to the RES in Romania. The quantitative model analyzes the influence of TQM process implementation in achieving competitive advantage and the management performance of the undertakings in the RES. Data was collected through a survey based on a questionnaire addressed to employees and managers in the RES. Structural equation modeling (SEM) was used and the research hypotheses were tested with the partial least squares path method (PLS). Data analysis was performed with the statistical software SmartPLS 3.2.8. The main contribution of this article is to evaluate the relationship between the management performance of enterprises in the RES sector in Romania and TQM process indicators. The results underline the fact that the most important attributes of a TQM process to increase the management performance are: integrated operational processes, policies and trading strategies, integrated operational management, company social responsibility, motivated workforce, knowledge, and competencies. The conclusions of the research are in line with the latest findings in the area, underlining that management performance is the direct result of the association between a group of factors and processes, such as the integrated operational processes, trade strategies and policies, integrated operational management, corporate social responsibility (CSR), motivated workforce, knowledge, and competencies. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Graphical abstract

14 pages, 2606 KiB  
Article
Air-Conditioning Resource Management and Control Method based on Cloud Platform for Wind Power Consumption
by Kaixin Liang, Jinying Yu and Xin Wu
Processes 2019, 7(7), 467; https://doi.org/10.3390/pr7070467 - 19 Jul 2019
Cited by 1 | Viewed by 3019
Abstract
Air-conditionings have energy storage functions. Through reasonable aggregation control, the output tracking can be implemented for wind power with stronger fluctuation to enhance its utilization rate. Cloud technology and intelligent appliances enable the appliance vendor to implement information interaction with the air-conditioning through [...] Read more.
Air-conditionings have energy storage functions. Through reasonable aggregation control, the output tracking can be implemented for wind power with stronger fluctuation to enhance its utilization rate. Cloud technology and intelligent appliances enable the appliance vendor to implement information interaction with the air-conditioning through cloud platforms to realize flexible regulation. In this paper, a management and control method of air-conditioning based on cloud platform is established. Based on this structure, the air-conditionings are divided into several aggregation groups according to the similarity of parameters, and each group completes the consumption task collaboratively. The consumption evaluation model of the air-conditioning group is established. On this basis, the allocation problem on consumption task for the aggregated group is constructed to implement the optimal solution under the condition of guaranteeing the degree of completion and user comfort. Each group implements the control for air-conditioning inside the group through the sliding mode control model. The simulation experiment verifies that the algorithm can effectively follow the output of clean energy, while intervening less in the air-conditioning operation. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

22 pages, 5720 KiB  
Article
Online Operation Risk Assessment of the Wind Power System of the Convolution Neural Network (CNN) Considering Multiple Random Factors
by Qingwu Gong, Si Tan, Yubo Wang, Dong Liu, Hui Qiao and Liuchuang Wu
Processes 2019, 7(7), 464; https://doi.org/10.3390/pr7070464 - 19 Jul 2019
Cited by 2 | Viewed by 2938
Abstract
In order to solve the problem of the inaccuracy of the traditional online operation risk assessment model based on a physical mechanism and the inability to adapt to the actual operation of massive online operation monitoring data, this paper proposes an online operation [...] Read more.
In order to solve the problem of the inaccuracy of the traditional online operation risk assessment model based on a physical mechanism and the inability to adapt to the actual operation of massive online operation monitoring data, this paper proposes an online operation risk assessment of the wind power system of the convolution neural network (CNN) considering multiple random factors. This paper analyzes multiple random factors of the wind power system, including uncertain wind power output, load fluctuations, frequent changes in operation patterns, and the electrical equipment failure rate, and generates the sample data based on multi-random factors. It uses the CNN algorithm network, offline training to obtain the risk assessment model, and online application to obtain the real-time online operation risk state of the wind power system. Finally, the online operation risk assessment model is verified by simulation using the standard network of 39 nodes of 10 machines New England system. The results prove that the risk assessment model presented in this paper is more rapid and suitable for online application. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

14 pages, 3800 KiB  
Article
Multi-Label Classification Based on Random Forest Algorithm for Non-Intrusive Load Monitoring System
by Xin Wu, Yuchen Gao and Dian Jiao
Processes 2019, 7(6), 337; https://doi.org/10.3390/pr7060337 - 3 Jun 2019
Cited by 63 | Viewed by 9134
Abstract
Non-intrusive load monitoring (NILM) is an effective method to optimize energy consumption patterns. Since the concept of NILM was proposed, extensive research has focused on energy disaggregation or load identification. The traditional method is to disaggregate mixed signals, and then identify the independent [...] Read more.
Non-intrusive load monitoring (NILM) is an effective method to optimize energy consumption patterns. Since the concept of NILM was proposed, extensive research has focused on energy disaggregation or load identification. The traditional method is to disaggregate mixed signals, and then identify the independent load. This paper proposes a multi-label classification method using Random Forest (RF) as a learning algorithm for non-intrusive load identification. Multi-label classification can be used to determine which categories data belong to. This classification can help to identify the operation states of independent loads from mixed signals without disaggregation. The experiments are conducted in real environment and public data set respectively. Several basic electrical features are selected as the classification feature to build the classification model. These features are also compared to select the most suitable features for classification by feature importance parameters. The classification accuracy and F-score of the proposed method can reach 0.97 and 0.98, respectively. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

34 pages, 5005 KiB  
Article
Designing, Developing and Validating a Forecasting Method for the Month Ahead Hourly Electricity Consumption in the Case of Medium Industrial Consumers
by Dana-Mihaela Petroșanu
Processes 2019, 7(5), 310; https://doi.org/10.3390/pr7050310 - 23 May 2019
Cited by 12 | Viewed by 3759
Abstract
An accurate forecast of the electricity consumption is particularly important to both consumers and system operators. The purpose of this study is to develop a forecasting method that provides such an accurate forecast of the month-ahead hourly electricity consumption in the case of [...] Read more.
An accurate forecast of the electricity consumption is particularly important to both consumers and system operators. The purpose of this study is to develop a forecasting method that provides such an accurate forecast of the month-ahead hourly electricity consumption in the case of medium industrial consumers, therefore assuring an intelligent energy management and an efficient economic scheduling of their resources, having the possibility to negotiate in advance appropriate billing tariffs relying on accurate hourly forecasts, in the same time facilitating an optimal energy management for the dispatch operator. The forecasting method consists of developing first non-linear autoregressive, with exogenous inputs (NARX) artificial neural networks (ANNs) in order to forecast an initial daily electricity consumption, a forecast that is being further processed with custom developed long short-term memory (LSTM) neural networks with exogenous variables support in order to refine the daily forecast as to achieve an accurate hourly forecasted consumed electricity for the whole month-ahead. The obtained experimental results (highlighted also through a very good value of 0.0244 for the root mean square error performance metric, obtained when forecasting the month-ahead hourly electricity consumption and comparing it with the real consumption), the validation of the developed forecasting method, the comparison of the method with other forecasting approaches from the scientific literature substantiate the fact that the proposed approach manages to fill a gap in the current body of knowledge consisting of the need of a high-accuracy forecasting method for the month-ahead hourly electricity consumption in the case of medium industrial consumers. The developed forecasting method targets medium industrial consumers, but, due to its accuracy, it can also be a useful tool for promoting innovative business models with regard to industrial consumers willing to produce a part of their own electricity using renewable energy resources, benefiting from reduced production costs and reliable electricity prices. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

13 pages, 1718 KiB  
Article
Risk Rating Method Based on the Severity Probability Risk Value and Reserved Risk Maintenance Resource Cost of the Node Disconnection of the Power System
by Qingwu Gong and Si Tan
Processes 2019, 7(5), 307; https://doi.org/10.3390/pr7050307 - 22 May 2019
Cited by 1 | Viewed by 2832
Abstract
In order to solve the problem of traditional risk rating methods without considering the cost of risk maintenance resources and ignoring the low risk of “High Loss Severity (HLS) with low probability” and the low risk of “High Failure Probability (HFP) with low [...] Read more.
In order to solve the problem of traditional risk rating methods without considering the cost of risk maintenance resources and ignoring the low risk of “High Loss Severity (HLS) with low probability” and the low risk of “High Failure Probability (HFP) with low loss severity”, a node disconnection risk rating method (NDRRM) is proposed. This method considers the severity probability risk valuation (SPRV) and reserve risk maintenance resource cost (RRMRC). The risk rating method based on SPRV developed from the traditional risk valuation method can simultaneously identify the nodes with the highest severity values, the nodes with the highest probability of failure, and the nodes with the largest risk valuation. On the basis of the above model, we consider the cost constraints of the reserve risk maintenance resource and put forward a risk rating method based on SPRV and RRMRC. The risk rating results of this model are suitable for guiding risk maintenance in practice. Simulations are carried out on the modified IEEE RTS-79 system to illustrate the effectiveness of the proposed models, and the simulation results show that the model is reasonable and effective. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

20 pages, 887 KiB  
Article
Convergence of Subtangent-Based Relaxations of Nonlinear Programs
by Huiyi Cao, Yingkai Song and Kamil A. Khan
Processes 2019, 7(4), 221; https://doi.org/10.3390/pr7040221 - 18 Apr 2019
Cited by 9 | Viewed by 3906
Abstract
Convex relaxations of functions are used to provide bounding information to deterministic global optimization methods for nonconvex systems. To be useful, these relaxations must converge rapidly to the original system as the considered domain shrinks. This article examines the convergence rates of convex [...] Read more.
Convex relaxations of functions are used to provide bounding information to deterministic global optimization methods for nonconvex systems. To be useful, these relaxations must converge rapidly to the original system as the considered domain shrinks. This article examines the convergence rates of convex outer approximations for functions and nonlinear programs (NLPs), constructed using affine subtangents of an existing convex relaxation scheme. It is shown that these outer approximations inherit rapid second-order pointwise convergence from the original scheme under certain assumptions. To support this analysis, the notion of second-order pointwise convergence is extended to constrained optimization problems, and general sufficient conditions for guaranteeing this convergence are developed. The implications are discussed. An implementation of subtangent-based relaxations of NLPs in Julia is discussed and is applied to example problems for illustration. Full article
(This article belongs to the Special Issue Neural Computation and Applications for Sustainable Energy Systems)
Show Figures

Figure 1

Back to TopTop