Large-scale deployment of intermittent renewable energy (namely wind energy and solar PV) may entail new challenges in power systems and more volatility in power prices in liberalized electricity markets. Energy storage can diminish this imbalance, relieving the grid congestion, and promoting distributed generation. The economic implications of grid-scale electrical energy storage technologies are however obscure for the experts, power grid operators, regulators, and power producers. A meticulous techno-economic or cost-benefit analysis of electricity storage systems requires consistent, updated cost data and a holistic cost analysis framework. To this end, this study critically examines the existing literature in the analysis of life cycle costs of utility-scale electricity storage systems, providing an updated database for the cost elements (capital costs, operational and maintenance costs, and replacement costs). Moreover, life cycle costs and levelized cost of electricity delivered by electrical energy storage is analyzed, employing Monte Carlo method to consider uncertainties. The examined energy storage technologies include pumped hydropower storage, compressed air energy storage (CAES), flywheel, electrochemical batteries (e.g. lead–acid, NaS, Li-ion, and Ni–Cd), flow batteries (e.g. vanadium-redox), superconducting magnetic energy storage, supercapacitors, and hydrogen energy storage (power to gas technologies). The results illustrate the economy of different storage systems for three main applications: bulk energy storage, T&D support services, and frequency regulation.

Electrical energy storage systems: A comparative life cycle cost analysis

This paper presents a comprehensive review of the industrial applications of artificial neural networks (ANNs), in the last 12 years. Common questions that arise to practitioners and control engineers while deciding how to use NNs for specific industrial tasks are answered. Workable issues regarding implementation details, training and performance evaluation of such algorithms are also discussed, based on a judiciously chronological organization of topologies and training methods effectively used in the past years. The most popular ANN topologies and training methods are listed and briefly discussed, as a reference to the application engineer. Finally, ANN industrial applications are grouped and tabulated by their main functions and what they actually performed on the referenced papers. The authors prepared this paper bearing in mind that an organized and normalized review would be suitable to help industrial managing and operational personnel decide which kind of ANN topology and training method would be adequate for their specific problems.

A comprehensive review for industrial applicability of artificial neural networks

Review of the applications of neural networks in chemical process control : simulation and online implementation

Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing presents an introduction to some of the cutting edge technological paradigms under the umbrella of computational intelligence. Computational intelligence schemes are investigated with the development of a suitable framework for fuzzy logic, neural networks and evolutionary computing, neuro-fuzzy systems, evolutionary-fuzzy systems and evolutionary neural systems. Applications to linear and non-linear systems are discussed with examples.Key features:Covers all the aspects of fuzzy, neural and evolutionary approaches with worked out examples, MATLAB exercises and applications in each chapterPresents the synergies of technologies of computational intelligence such as evolutionary fuzzy neural fuzzy and evolutionary neural systemsConsiders real world problems in the domain of systems modelling, control and optimizationContains a foreword written by Lotfi ZadehComputational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing is an ideal text for final year undergraduate, postgraduate and research students in electrical, control, computer, industrial and manufacturing engineering.

Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing

We fabricate near-infrared absorbing organic photovoltaics that are highly transparent to visible light. By optimizing near-infrared optical-interference, we demonstrate power efficiencies of 1.3±0.1% with simultaneous average visible transmission of >65%. Subsequent incorporation of near-infrared distributed-Bragg-reflector mirrors leads to an increase in the efficiency to 1.7±0.1%, approaching the 2.4±0.2% efficiency of the opaque cell, while maintaining high visible-transparency of >55%. Finally, we demonstrate that a series-integrated array of these transparent cells is capable of powering electronic devices under near-ambient lighting. This architecture suggests strategies for high-efficiency power-generating windows and highlights an application uniquely benefiting from excitonic electronics.

Transparent, near-infrared organic photovoltaic solar cells for window and energy-scavenging applications

In this paper a direct adaptive neural-network control strategy for unknown nonlinear systems is presented. The system considered is described by an unknown NARMA model, and a feedforward neural network is used to learn the system. Taking the neural network as a neural model of the system, control signals are directly obtained by minimizing either the instant difference or the cumulative differences between a set point and the output of the neural model. Since the training algorithm guarantees that the output of the neural model approaches that of the actual system, it is shown that the control signals obtained can also make the real system output close to the set point. An application to a flow-rate control system is included to demonstrate the applicability of the proposed method and desired results are obtained.

A direct adaptive neural-network control for unknown nonlinear systems and its application

Presents a direct adaptive neural network control strategy for unknown nonlinear systems which are described by an unknown NARMA model. Taking the neural network as a neuro model of the system, control signals are directly obtained by minimizing either the instant difference or the cummulative differences between a setpoint and the output of the neuro model. An application to a flow rate control system is studied and desired results are obtained.

A direct adaptive neural network control for unknown nonlinear systems and its application

In this work a characterization system for high energy-density capacitors is described and demonstrated. Capacitors are being designed using thin-film technology in an attempt to achieve higher energy-density levels by operating the devices at a high voltage. These devices are fabricated from layers of 100 nm aluminum and a layer of polyvinylidene fluoride-hexafluoropropylene on a polyethylene naphthalate plastic substrate. The devices have been designed to store electrical charge at up to 200 V. Characterizations of these devices focus on the measurement of capacitance vs bias voltage and temperature, equivalent series resistance, and charge/discharge cycles. For the purpose of the characterization of these capacitors, an electronic charge/discharge interface was designed and tested.

Characterization system for research on energy storage capacitors

http://www.scielo.org.mx/pdf/jart/v8n2/v8n2a4.pdf

Automation Of An I-V Characterization System

An algorithm for the detection and diagnosis of faults in sensors and actuators in unknown nonlinear systems is presented. Firstly the normal operation of the nonlinear system is modelled via a feedforward neural network in order to produce a healthy model which is used later as a redundant relation. A residual signal is evaluated from the difference of the output of the healthy model and that of the system. The estimation of the fault is then computed by minimising the differences between the output of system and that of the healthy neuro model with the help of the gradient descent rule. The algorithm is able to estimate a fault with large magnitude accurately. However, if the fault is small, a linearised healthy model, together with the recursive least squares algorithm, can be used to estimate the fault. As a result, a combination of both methods will provide a powerful technique for accurate fault diagnosis.

J. R. Noriega

Papers

A direct adaptive neural-network control for unknown nonlinear systems and its application

A direct adaptive neural network control for unknown nonlinear systems and its application

Characterization system for research on energy storage capacitors

Automation Of An I-V Characterization System

Fault diagnosis for unknown nonlinear systems via neural networks and its comparisons combinations with RLS based techniques