No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Development of ANN algorithms for forecasting Fresnel thermal power production
Abstract
Renewable energy production technologies are indispensable to the development of a clean and energy efficient built environment. Being dependent on climatic parameters, renewable energy production may vary causing a mismatch between energy demand and available production. Therefore, forecasting of renewable energy production allows the design and implementation of management schedules depending on expected production, thus assisting towards a more efficient and secure operation. The application of artificial neural networks (ANN) has been proved effective towards this aim. The present work is investigating the application of ANN for production forecasting of a concentrated solar power (CSP) fresnel system. The fresnel system production is optimum under clear skies and peak direct solar radiation. The system under investigation is connected to a thermal storage and its production is used to cover the heating/cooling loads of a building. The prediction can be used for scheduling the times that the system focalizes and de-focalizes for optimizing energy production and storage. The present work is relevant to researchers, engineers and developers of renewable energy production technologies that work on optimization of energy production and management. This work can be extended to smart grid energy management.
ResearchGate has not been able to resolve any citations for this publication.
A solar multi-generation approach has been implemented through four demonstrative plants in Italy, Cyprus, Jordan and Egypt based upon solar concentrating collectors. Different design options have been developed, including technologies that have been adapted and downsized from the utility scale of CSP plants, with the aim to be integrated at building, settlement and community scale. Demo plants have been conceived as living
labs in order to support the further development of the technologies in a real-life environment, supporting the local smart specialization strategies in collaboration with SMEs, local stakeholders and citizens.
CSP technologies can be applied for distributed energy production, on small-medium plants (on the 1 MW scale), to satisfy the needs of local communities, buildings and districts. In this perspective, reliable, low-cost, and flexible small/medium multi-generative CSP plants should be developed. Four pilot plants have been built in four Mediterranean countries (Cyprus, Egypt, Jordan, and Italy) to demonstrate the approach. In this paper, the plant built in Italy is presented, with specific innovations applied in the linear Fresnel collector design and the Thermal Energy Storage (TES) system, based on a single the use of molten salts but specifically tailored for small scale plants.
Solar concentration systems are usually deployed in large open spaces for electricity generation; they are rarely used to address the pressing energy needs of the built environment sector. Fresnel technology offers interesting and challenging CSP energy pathways suitable for the built environment, due to its relatively light weight (<30 kg.m⁻²) and low windage. The Cyprus Institute (CyI) and Consorzio ARCA are cooperating in such a research program; we report here the construction and integration of a 71kW Fresnel CSP system into the HVAC(Heating, Ventilation, and Air Conditioning) system of a recently constructed office & laboratory building, the Novel Technologies Laboratory (NTL). The multi-generative system will support cooling, heating and hot water production feeding the system of the NTL building, as a demonstration project, part of the STS-MED program (Small Scale Thermal Solar District Units for Mediterranean Communities) financed by the European Commission under the European Neighbourhood and Partnership Instrument (ENPI), CBCMED program.
Load forecasting (LF) plays important role in planning and operation of power systems. It is envisioned that future smart grids will utilize LF and dynamic pricing based techniques for effective Demand Side Management (DSM). This paper presents a comprehensive and comparative review of the LF and dynamic pricing schemes in smart grid environment. Real Time Pricing (RTP), Time of Use (ToU) and Critical Peak Pricing (CPP) are discussed in detail. Two major categories of LF: mathematical and artificial intelligence based computational models are elaborated with sub categories. Mathematical models including auto recursive, moving average, auto recursive moving average, auto recursive integrated moving average, exponential smoothing, iterative reweighted mean square, multiple regression, etc. used for effective DSM are discussed. Neural networks, fuzzy logic, expert systems of the second major category of LF models have also been described.
Electrical load forecasting plays a vital role in order to achieve the concept of next generation power system such as smart grid, efficient energy management and better power system planning. As a result, high forecast accuracy is required for multiple time horizons that are associated with regulation, dispatching, scheduling and unit commitment of power grid. Artificial Intelligence (AI) based techniques are being developed and deployed worldwide in on Varity of applications, because of its superior capability to handle the complex input and output relationship. This paper provides the comprehensive and systematic literature review of Artificial Intelligence based short term load forecasting techniques. The major objective of this study is to review, identify, evaluate and analyze the performance of Artificial Intelligence (AI) based load forecast models and research gaps. The accuracy of ANN based forecast model is found to be dependent on number of parameters such as forecast model architecture, input combination, activation functions and training algorithm of the network and other exogenous variables affecting on forecast model inputs. Published literature presented in this paper show the potential of AI techniques for effective load forecasting in order to achieve the concept of smart grid and buildings.
The term Smart Grid has become a term to represent the benefits of a smart and sophisticated electrical grid, which can meet various social expectations related to sustainability and energy efficiency. The Smart Grid promises to enable a better power management for energy utilities and consumers, to provide the ability to integrate the power grid, to support the development of micro grids, and to involve citizens in energy management with higher levels of responsibility. However, this context comes with potential pitfalls, such as vulnerabilities to cyber-security and privacy risks. In this article, a prospective study about energy management, and exploring critical issues of modeling of energy management systems in a context Smart. Grid is presented along with background of energy management systems. An analysis of the demand response condition is also presented. Finally, the advantages and disadvantages of the implementation of energy management systems, and a comparison with the Brazilian electricity system are discussed.
Concentrating solar power (CSP) has received significant attention among researchers, power-producing companies and state policymakers for its bulk electricity generation capability, overcoming the intermittency of solar resources. The parabolic trough collector (PTC) and solar power tower (SPT) are the two dominant CSP systems that are either operational or in the construction stage. The USA and Spain are global leaders in CSP electricity generation, whereas developing countries such as China and India are emerging by aggressive investment. Each year, hundreds of articles have been published on CSP. However, there is a need to observe the overall research development of this field which is missing in the current body of literature. To bridge this gap, this study 1) provides a most up-to-date overview of the CSP technologies implemented across the globe, 2) reviews previously published review articles on this issue to highlight major findings and 3) analyzes future research trends in the CSP research. Text mining approach is utilized to analyze and visualize the scientific landscape of the research. Thermal energy storage, solar collector and policy-level analysis are found as core topics of discussion in the previous studies. With a holistic analysis, it is found that direct steam generation (DSG) is a promising innovation which is reviewed in this study. This paper provides a comprehensive outlook on the CSP technologies and its research which offers practical help to the future researchers who start to research on this topic.
Solar and wind energy are inherently time-varying sources of energy on scales from minutes to seasons. Thus, the incorporation of such intermittent and stochastic renewable energy systems (ISRES) into an electricity grid provides some new challenges in managing a stable and safe energy supply, in using energy storage and/or 'back-up' energy from other sources. In such cases, the ability to accurately forecast the output of “unpredictable” energy facilities is essential for ensuring an optimal management of the energy production means. This review syntheses the reasons to predict solar or wind fluctuations, it shows that variability and stochastic variation of renewable sources have a cost, sometimes high. It provides useful information on the intermittence cost and on the decreasing of this cost due to an efficient forecasting of the source fluctuation; this paper is for engineers and researchers who are not necessarily familiar with the issue of the notions of cost and economy and justify future investments in the ISRES production forecasting.
Traditional electricity grids lack flexibility in power generation and load operation in contrast to smart-micro grids that form semi-autonomous entities with energy management capabilities. Load forecasting is invaluable to smart micro-grids towards assisting the implementation of energy management schedules for cost-efficient and secure operation. In the present paper is examined the 24h forecasting of excess production in an existing micro-grid. Alternative input parameters are considered for achieving an accurate prediction. The prediction can be used for scheduling the charging process of a thermal storage during weekends based on excess power production levels.
Energy efficiency, advanced controls and renewable energy systems for operating industrial, residential and tertiary sector buildings designed to be Near-Zero Energy are investigated to explore the performance gap. The analysis involves a comparison of energy dynamic and quasi-dynamic models with data from smart monitoring systems, indoor and outdoor environment measurements, power consumption and production data. Specific issues and conclusions have been drawn as the basis for addressing the performance gap between energy efficiency prediction in the design phase and measurements’ evaluation in operational phase.
One of the available solutions for utilities to deal with intermittency issues resulted from renewable energy resources, is battery energy storage systems (BESSs). BESS needs to have a control algorithm to provide a very good estimation of the load on the grid at each time step. Short-term load forecast (STLF) is necessary for efficient and optimized control of BESSs that are connected to the grid. In this work, two parallel-series techniques for load forecasting are proposed to optimize the performance of a grid-scale BESS (1 MW, 1.1 kWh) in 15-min steps within a moving 24-hour window. In both techniques, a complex-valued neural network (CVNN) is used for parallel forecasting. The parallel component is based on the search for similar days of historical data that have a weekly index comparable to the forecast day. For series forecasting, historical data of each day is used within a moving forecast window by CVNN along with the spline method. For both techniques, parallel forecasting is mixed with series forecasting by an adjustment coefficient. Both techniques are tested on a set of real data for a grid with high PV penetration, and the obtained results are compared.
An accurate load forecasting is always particularly important for optimal planning and energy management in smart buildings and power systems. Millions of dollars can be saved annually by increasing a small degree of improvement in prediction accuracy. However, forecasting load demand accurately is a challenging task due to multiple factors such as meteorological and exogenous variables. This paper develops a novel load forecasting model, which is based on a feed-forward artificial neural network (ANN), to predict hourly load demand for various seasons of a year. In this model, a global best particle swarm optimization (GPSO) algorithm is applied as a new training technique to enhance the performance of ANN prediction. The fitness function is defined and a weight bias encoding/decoding scheme is presented to improve network training. Influential meteorological and exogenous variables along with correlated lagged load data are also employed as inputs in the presented model. The data of an ISO New England grid are used to validate the performance of the developed model. The results demonstrate that the proposed forecasting model can provide significantly better forecast accuracy, training performances and convergence characteristics than contemporary techniques found in the literature.
As an emerging technology, the photovoltaic/concentrated solar power (PV-CSP) hybrid technology is considered as one of the research focuses currently in solar energy field, due to various advantages compared with the PV-alone and CSP-alone technologies. Compared with the PV-alone system, the PV-CSP hybrid system can produce electricity with better power quality. While compared with the CSP-alone system, the cost of power production can be reduced. The overall generating efficiency will also be greatly improved if the PV component and the CSP component of the hybrid system are “compactly” hybridized by PV-topping or spectral beam splitting (SBS) technologies. The development of PV-CSP hybrid systems accelerated in recent years with the increase of maturity of PV and CSP technologies. This paper presents an exhaustive review on the state-of-the-art of the PV-CSP hybrid technologies, including the non-compact hybrid system, the PV-topping hybrid system, the SBS hybrid system, and the hybrid system combining SBS and PV-topping technologies. Recent progresses of the key technologies of the PV-CSP hybrid systems, such as high temperature solar cells, spectral beam filters, and high flux heat exchangers, are generally discussed. After that, the research status and the hybrid system performance are summarized from the literature to provide a global point of view on the PV-CSP hybrid technology. The advantages and limitations of the hybrid technology are also concluded according to the literature reviewed.
Smart grid engineering is the key for a beneficial use of widespread energy resources, it is a modernized electrical grid that uses analog or digital information and communications technology. Renewable energy itself a thrust area of research due to its availability, applicability and environmental friendly nature and the application of smart grid in renewable energy makes it vast and more promising. This fusion enables the efficient use of renewable energies which is a key challenge for now. The present review paper attempts to investigate the role of smart grid in the renewable energy. The introductory section sets the role of renewable energy and distributed power in a smart grid system. Subsections cover the concept and availability of renewable energies, renewable energy power calculation formulae, smart grid concepts and its feasibility, case studied as performed by different researchers around the World, discussion and future recommendations and finally the conclusions from the study. To achieve this, articles from different sources such as internet, reports, conferences and journals of Elsevier, Springer, Tailor and Franacis, Wiley and many more have been collected and reviewed. This paper concludes that renewable energies can be used efficiently and in a smart way by using the smart grids. However, the smart grid technology is not mature enough and needs more research on the same.
The deep penetration of renewable energy sources is on the cutting edge of smart grid vision. However, the variability and limited predictability of these sources have brought many technical challenges to grids. Many regulatory communities and system operators in the power sector have established grid codes to ensure proper connection of these renewable sources. This paper investigates the up-to-date methods used to enhance power system performance in the presence of a large share of renewable energy generation. In particular, two areas are addressed; the first is the techniques used for improving the wind and photovoltaic low-voltage ride-through capabilities to meet the required grid codes. The second is the contribution of these sources to the small signal stability of the power system in terms of inter-area oscillation damping.
The aim of this work is the development of an optimization model in order to minimize the cost of Leaf Community microgrid. This cost is a sum of energy cost and the maintenance cost of the energy storage system (ESS). The developed objective function is constrained and the problem here is solved by using the method of genetic algorithms at Matlab. The genetic algorithm decides about the transportation of the energy from or to the ESS and it calculates an optimum cost. The optimization time horizon is 24 h ahead, thus the prediction of energy production and consumption was necessary. This was achieved by using neural networks. In order to verify the performance of the developed model, some scenarios were tested. This study concludes that a management of a microgrid can achieve energy and money savings.
Comparison of thermal and optical performance of Linear Fresnel and Parabolic Trough Concentrator
- M H Ahmed
- M Rady
- A M A Amin
- F M Montagnino
- F Paredes
M. H. Ahmed, M. Rady, A. M. A. Amin, F. M.
Montagnino, and F. Paredes, "Comparison of thermal
and optical performance of Linear Fresnel and Parabolic
Trough Concentrator," 2015 Int. Conf. Renew. Energy
Res. Appl., vol. 5, pp. 626-629, 2015.