scholarly journals Self-Organizing Map (SOM) in Wind Speed Forecasting: A New Approach in Computational Intelligence (CI) Forecasting Methods

2012 ◽  
Author(s):  
Mohammad Amin Esmaeili ◽  
Janet Twomey
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Cost Effective ◽  
Self Organizing Map ◽  
Electricity Grid ◽  
Average Maximum ◽  
Critical Issues ◽  
Electricity Grids ◽  
Optimal Maintenance ◽  
Self Organizing

While wind energy has been reported as the fastest growing among different sources of renewable energy, two critical issues are how to make wind energy cost effective and how to integrate it into electricity grids properly. The ability to predict power generated by wind not only allows the most effective integration of wind power into electricity grid but also makes it possible to have an optimal maintenance scheduling that can reduce cost significantly. This research investigates the practical use of Self Organizing Map (SOM) as a special type of neural network based forecasting method. In this paper, forecasting the average, maximum and minimum of one-day-ahead wind speed based on the past wind speed states of the previous 24 hours is the objective.

A New Method for Emulating Self-Organizing Maps for Visualization of Datasets

2018 ◽  
Vol 17 (03) ◽  
pp. 1850014 ◽  
Author(s):  
Macario O. Cordel ◽  
Arnulfo P. Azcarraga
Keyword(s):  
Disaster Response ◽  
Dimensional Space ◽  
Main Idea ◽  
Cost Effective ◽  
Fine Tuning ◽  
Visualization Tool ◽  
Self Organizing Map ◽  
Text Complexity ◽  
Self Organizing Maps ◽  
Self Organizing

Several time-critical problems relying on large amount of data, e.g., business trends, disaster response and disease outbreak, require cost-effective, timely and accurate data summary and visualization, in order to come up with an efficient and effective decision. Self-organizing map (SOM) is a very effective data clustering and visualization tool as it provides intuitive display of data in lower-dimensional space. However, with [Formula: see text] complexity, SOM becomes inappropriate for large datasets. In this paper, we propose a force-directed visualization method that emulates SOMs capability to display the data clusters with [Formula: see text] complexity. The main idea is to perform a force-directed fine-tuning of the 2D representation of data. To demonstrate the efficiency and the vast potential of the proposed method as a fast visualization tool, the methodology is used to do a 2D-projection of the MNIST handwritten digits dataset.

The impact of atmospheric circulation on wind energy resource using self-organizing maps

2021 ◽  
Author(s):  
Kostas Philippopoulos ◽  
Chris G. Tzanis
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Atmospheric Circulation ◽  
Large Scale ◽  
Synoptic Climatology ◽  
Energy Potential ◽  
Self Organizing Maps ◽  
Wind Energy Potential ◽  
The Impact ◽  
Self Organizing

<p>The sensitivity of wind to the Earth’s energy budget and the changes it causes in the climate system has a significant impact on the wind energy sector. The scope of this work is to examine the association of atmospheric circulation with the wind speed distribution characteristics on different timescales over Greece. Emphasis is given to the effect of specific regimes on the wind speed distributions at different locations. The work is based on using synoptic climatology as a tool for providing information regarding wind variability. This approach allows a more detailed description of the effect of changes in large-scale atmospheric circulation on wind energy potential. The atmospheric classification methodology, upon the selection of relevant atmospheric variables and domains, includes a Principal Components Analysis for dimension reduction purposes and subsequently, the classification is performed using an artificial neural network and in particular self-organizing maps. In the resulting feature map, the neighboring nodes are inter-connected and each one is associated with the composites of the selected large-scale variables. Upon the assignment and the characterization of each day in one of the resulting patterns, a daily catalog is constructed and frequency analysis is performed. In the context of estimating wind energy potential variability for each atmospheric pattern, the fit of multiple probability functions to the surface wind speed frequency distributions is performed. The most suitable function is selected based on a set of difference and correlation statistical measures, along with the use of goodness-of-fit statistical tests. The study employs the ERA5 reanalysis dataset with a 0.25° spatial resolution from 1979/01/01 up to 2019/12/31 and the wind field data are extracted at the 10m and the 100m levels. The approach could be valuable to the wind energy industry and can provide the required scientific understanding for the optimal siting of Wind Energy Conversion Systems considering the atmospheric circulation and the electricity interconnection infrastructure in the region. Considering the emerging issue of energy safety, accurate wind energy production estimates can contribute towards the establishment of wind as the primary energy source and in meeting the increasing energy demand.</p>

scholarly journals A Research on Electricity Generation from Wind Corridors of Pakistan (Two Provinces): A Technical Proposal for Remote Zones

2017 ◽  
Vol 9 (9) ◽  
pp. 1611 ◽  
Author(s):  
Mazhar Baloch ◽  
Safdar Abro ◽  
Ghulam Sarwar Kaloi ◽  
Nayyar Mirjat ◽  
Sohaib Tahir ◽  
...  
Keyword(s):  
Renewable Energy ◽  
Wind Speed ◽  
Wind Energy ◽  
Alternative Energy ◽  
Cost Effective ◽  
Load Shedding ◽  
Energy Resources ◽  
Renewable Energy Resources ◽  
Average Wind Speed ◽  
Advantages And Disadvantages

The non-renewable energy resources are limited and depleting gradually. As such, energy security has attained the greatest amount of attention globally than ever before. In the meantime, energy crises are already affecting the developing countries such as Pakistan, even though one-third of the population of the country is not even not connected to the national electricity grid. The population with access to on-grid electricity is enduring load shedding of more than 12 h a day. This situation is alarming and require immediate attention is required so as to add alternative energy resources to the country, which has long been relying on imported fuels. It is, therefore, high time that the abundant potential in the renewable energy resources of Pakistan such as solar, wind, and biomass are harnessed. These renewable energy resources are economical and environmentally friendly, and thus considered as sustainable, and the utilization of these in meeting energy demands can help to conserve conventional resources early diminishing. This paper provides a detailed description of the energy consumption and load-shedding scenario in Pakistan thereby focusing specifically Sindh and Baluchistan provinces. Since, wind energy is considered one of the cost-effective renewable resources, six potential sites in these two provinces are considered in this study. These sites lie within 250 km of the southeastern and 800 km of the southwestern regions of Pakistan. One-year wind speed data have been reported for variable heights of these proposed sites which represent to have an annual average wind speed of 6.63 m/s and 5.33 m/s respectively. The power generation data for these location of two provinces is 7.653 GWh, and 5.456 GWh per annum respectively. This study also elaborates on the advantages and disadvantages of harvesting and installing the wind energy and provides a technical proposal for the generation of electricity from the wind in the selected remote zones which are off the national grid. The findings of this paper will help concerned government departments to devise appropriate policies and attract investment in the wind energy sector to eradicate the on-going electricity crisis.

scholarly journals Contribution of Cartography to the Optimization of the Evaluation of Wind Energy Potential in the Republic of Cameroon: Case of Bitchoua Highlands

2021 ◽  
pp. 53-66
Author(s):  
VadelTsopgni Eneckdem ◽  
Rodrigue Aimé Feumba ◽  
Odovie Tsomo ◽  
Jean Roger Bogning
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Power Density ◽  
Average Power ◽  
Operating Conditions ◽  
In Situ Observation ◽  
Average Wind Speed ◽  
Average Wind ◽  
Average Maximum ◽  
Wind Potential

This study deals with a model combining cartography with mathematical simulation for the optimal evaluation of wind potential in the context of the absence of networks of in-situ observation stations. It is based on both geographic Information Systems (GIS), climate data from NASA Surface Meteorology and Solar Energy (SSE) from 1985 to 2018, and field survey data from 2018.The NASA-SSE data, made it possible to obtain information on the direction of the winds, to determine parameters of distribution of wind speed frequencies (by the Weibull method).Then, we proceeded to the processing and numerical simulation of the data to provide predictions of the electrical energy that could be generated. By mobilizing GIS, the study proposes a decisional mapping allowing the planning and realization of wind energy projects in the studied area. It appears from the work carried out in the field that with an average wind speed of 2.56m / s (at 50 m from the ground) the winds of Bitchoua have an average power density estimated at 1612.64 W. Under current operating conditions defined by the Betz limit, it would be possible to recover from the local wind, thanks to a 50 m diameter wind turbine, an electrical power of approximately 956.87 W / s, for a maximum average of 974.17 W / s. The spatial representation of this potential presents the Center and North-East of Bitchoua as the most suitable sectors for the installation of wind turbines in the locality. Indeed, with an average wind speed of 2.8m / s, the area has an average wind power density evaluated at 13.45 W, for an available power of 4221.53 W. Under current conditions of exploitability, the recoverable potential in this part would be about 1251.79 W / s, for 1275.07W / s on average maximum (well above the local average).

scholarly journals CPU based prediction with Self Organizing Map in Dynamic Cloud Data Centers

2020 ◽  
Vol 10 ◽  
Author(s):  
Nabila Djennane ◽  
Meziane Yacoub ◽  
Rachida Aoudjit ◽  
Samia Bouzefrane
Keyword(s):  
Resource Management ◽  
Cost Effective ◽  
Resource Provisioning ◽  
Management Systems ◽  
Self Organizing Map ◽  
Self Organizing Maps ◽  
Cloud Data ◽  
Demand Prediction ◽  
The Future ◽  
Self Organizing

Backgroud: The major objective of resource management systems in the cloud environments is to assist providers in making consistent and cost-effective decisions related to the dynamic resource allocation. However, because of the demand changes of the applications and the exponential evolution of the cloud, the resource management systems are constantly called into question with regard to their ability to guarantee an effective resource provisioning. Objective: To tackle these challenges, the future demand prediction is a practical solution that has been adopted in the literature. The prediction has widely relied on the CPU utilization since it is considered as a leading cause of the Quality of Service dropping. Method: The successful application of artificial intelligence techniques in forecasting problems motivated us to use the Kohonen Self Organizing Maps that tries to capture the gathered empirical CPU load time series in regular behaviors to perform an accurate forecast. The proposed solution is a two-step approach that first classifies the collected data and then predicts the future CPU load. Results and conclusion: The experimental results show that our proposed system outperforms other models reported in the literature. In addition, we proved that Self Organizing Maps known for its strength in classification is also effective for prediction.

Performance assessment of a balloon assisted micro airborne wind turbine system

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Naveen Prakash Noronha ◽  
Krishna Munishamaih
Keyword(s):  
Wind Speed ◽  
Wind Energy ◽  
Wind Turbine ◽  
Power Output ◽  
Cost Effective ◽  
Energy System ◽  
Maximum Power ◽  
Power Coefficient ◽  
Average Wind Speed ◽  
Low Wind Speed

Abstract This study intends to examine the performance of a balloon-assisted micro airborne wind turbine in a low wind speed location. The influence of the balloon separation gap on the airborne wind energy system (AWES) performance is also explored. A micro-AWES with a diameter of 3 m and a power output of 1 kW was fabricated and tested at 50, 100, 150, 200, and 250 m. Further, the optimum separation spacing of 13 m was maintained between the balloon and the ducted turbine to reduce balloon turbulence on the turbine. The airborne wind turbine achieved a maximum power output of 250 W at 250 m height while the average wind speed remained 6 m/s. The maximum power coefficient obtained was 0.25 while annual energy production (AEP) remained 1200 kWh. The low power coefficient is credited to the turbulence and drifting in the airborne system and the drag caused by the airborne structure. While a cost-effective commercial model of micro AWES is still being developed, the present work attempts to harvest wind energy at high elevations in low wind speed areas.

scholarly journals Multivariate Analysis Applied to Aquifer Hydrogeochemical Evaluation: A Case Study in the Coastal Significant Subterranean Water Body between “Cecina River and San Vincenzo”, Tuscany (Italy)

2021 ◽  
Vol 11 (16) ◽  
pp. 7595
Author(s):  
Alessia Bastianoni ◽  
Enrico Guastaldi ◽  
Alessio Barbagli ◽  
Stefano Bernardinetti ◽  
Andrea Zirulia ◽  
...  
Keyword(s):  
Water Body ◽  
Major Ions ◽  
Principal Component ◽  
Cost Effective ◽  
Self Organizing Map ◽  
Cluster Assignment ◽  
Low Salinity ◽  
Som Clustering ◽  
Subterranean Water ◽  
Self Organizing

The hydrogeochemical characteristics of the significant subterranean water body between “Cecina River and San Vincenzo” (Italy) was evaluated using multivariate statistical analysis methods, like principal component analysis and self-organizing maps (SOMs), with the objective to study the spatiotemporal relationships of the aquifer. The dataset used consisted of the chemical composition of groundwater samples collected between 2010 and 2018 at 16 wells distributed across the whole aquifer. For these wells, all major ions were determined. A self-organizing map of 4 × 8 was constructed to evaluate spatiotemporal changes in the water body. After SOM clustering, we obtained three clusters that successfully grouped all data with similar chemical characteristics. These clusters can be viewed to reflect the presence of three water types: (i) Cluster 1: low salinity/mixed waters; (ii) Cluster 2: high salinity waters; and (iii) Cluster 3: low salinity/fresh waters. Results showed that the major ions had the greater influence over the groundwater chemistry, and the difference in their concentrations allowed the definition of three clusters among the obtained SOM. Temporal changes in cluster assignment were only observed in two wells, located in areas more susceptible to changes in the water table levels, and therefore, hydrodynamic conditions. The result of the SOM clustering was also displayed using the classical hydrochemical approach of the Piper plot. It was observed that these changes were not as easily identified when the raw data were used. The spatial display of the clustering results, allowed the evaluation in a hydrogeological context in a quick and cost-effective way. Thus, our approach can be used to quickly analyze large datasets, suggest recharge areas, and recognize spatiotemporal patterns.

Sign in / Sign up

Export Citation Format

Share Document