Dynamic artificial neural network for electricity market prices forecast

This paper presents an artificial neural network applied to the forecasting of electricity market prices, with the special feature of being dynamic. The dynamism is verified at two different levels. The first level is characterized as a re-training of the network in every iteration, so that the artificial neural network can able to consider the most recent data at all times, and constantly adapt itself to the most recent happenings. The second level considers the adaptation of the neural network’s execution time depending on the circumstances of its use. The execution time adaptation is performed through the automatic adjustment of the amount of data considered for training the network. This is an advantageous and indispensable feature for this neural network’s integration in ALBidS (Adaptive Learning strategic Bidding System), a multi-agent system that has the purpose of providing decision support to the market negotiating players of MASCEM (Multi-Agent Simulator of Competitive Electricity Markets).

Scheduling distributed energy resources in an isolated grid - an artificial neural network approach

Power Systems (PS), have been affected by substantial penetration of Distributed Generation (DG) and the operation in competitive environments. The future PS will have to deal with large-scale integration of DG and other distributed energy resources (DER), such as storage means, and provide to market agents the means to ensure a flexible and secure operation. Virtual power players (VPP) can aggregate a diversity of players, namely generators and consumers, and a diversity of energy resources, including electricity generation based on several technologies, storage and demand response. This paper proposes an artificial neural network (ANN) based methodology to support VPP resource schedule. The trained network is able to achieve good schedule results requiring modest computational means. A real data test case is presented.

Thermodynamic pathway for the formation of SnSe and SnSe2 polycrystalline thin films by selenization of metal precursors

In this work, tin selenide thin films (SnSex) were grown on soda lime glass substrates by selenization of dc magnetron sputtered Sn metallic precursors. Selenization was performed at maximum temperatures in the range 300 °C to 570 °C. The thickness and the composition of the films were analysed using step profilometry and energy dispersive spectroscopy, respectively. The films were structurally and optically investigated by X-ray diffraction, Raman spectroscopy and optical transmittance and reflectance measurements. X-Ray diffraction patterns suggest that for temperatures between 300 °C and 470 °C, the films are composed of the hexagonal-SnSe2 phase. By increasing the temperature, the films selenized at maximum temperatures of 530 °C and 570 °C show orthorhombic-SnSe as the dominant phase with a preferential crystal orientation along the (400) crystallographic plane. Raman scattering analysis allowed the assignment of peaks at 119 cm−1 and 185 cm−1 to the hexagonal-SnSe2 phase and those at 108 cm−1, 130 cm−1 and 150 cm−1 to the orthorhombic-SnSe phase. All samples presented traces of condensed amorphous Se with a characteristic Raman peak located at 255 cm−1. From optical measurements, the estimated band gap energies for hexagonal-SnSe2 were close to 0.9 eV and 1.7 eV for indirect forbidden and direct transitions, respectively. The samples with the dominant orthorhombic-SnSe phase presented estimated band gap energies of 0.95 eV and 1.15 eV for indirect allowed and direct allowed transitions, respectively.

Effects of sulphurization time on Cu2ZnSnS4 absorbers and thin films solar cells obtained from metallic precursors

We report the results of a study of the sulphurization time effects on Cu2ZnSnS4 absorbers and thin film solar cells prepared from dc-sputtered tackedmetallic precursors. Three different time intervals, 10 min, 30min and 60 min, at maximum sulphurization temperature were considered. The effects of this parameter' change were studied both on the absorber layer properties and on the final solar cell performance. The composition, structure, morphology and thicknesses of the CZTS layers were analyzed. The electrical characterization of the absorber layer was carried out by measuring the transversal electrical resistance of the samples as a function of temperature. This study shows an increase of the conductivity activation energy from 10 meV to 54meV for increasing sulphurization time from 10min to 60min. The solar cells were built with the following structure: SLG/Mo/CZTS/CdS/i-ZnO/ZnO:Al/Ni:Al grid. Several ac response equivalent circuit models were tested to fit impedance measurements. The best results were used to extract the device series and shunt resistances and capacitances. Absorber layer's electronic properties were also determined using the Mott–Schottky method. The results show a decrease of the average acceptor doping density and built-in voltage, from 2.0 1017 cm−3 to 6.5 1015 cm−3 and from 0.71 V to 0.51 V, respectively, with increasing sulphurization time. These results also show an increase of the depletion region width from approximately 90 nm–250 nm.

Cu2ZnSnS4 absorber layers obtained through sulphurization of metallic precursors: Graphite box versus sulphur flux

In this work we employed a hybrid method, combining RF-magnetron sputtering with evaporation, for the deposition of tailor made metallic precursors, with varying number of Zn/Sn/Cu (ZTC) periods and compared two approaches to sulphurization. Two series of samples with 1×, 2× and 4× ZTC periods have been prepared. One series of precursors was sulphurized in a tubular furnace directly exposed to a sulphur vapour and N2+5% H2 flux at a pressure of 5.0×10+4 Pa. A second series of identical precursors was sulphurized in the same furnace but inside a graphite box where sulphur pellets have been evaporated again in the presence of N2+5% H2 and at the same pressure as for the sulphur flux experiments. The morphological and chemical analyses revealed a small grain structure but good average composition for all three films sulphurized in the graphite box. As for the three films sulphurized in sulphur flux grain growth was seen with the increase of the number of ZTC periods whilst, in terms of composition, they were slightly Zn poor. The films' crystal structure showed that Cu2ZnSnS4 is the dominant phase. However, in the case of the sulphur flux films SnS2 was also detected. Photoluminescence spectroscopy studies showed an asymmetric broad band emission whichoccurs in the range of 1–1.5 eV. Clearly the radiative recombination efficiency is higher in the series of samples sulphurized in sulphur flux. We have found that sulphurization in sulphur flux leads to better film morphology than when the process is carried out in a graphite box in similar thermodynamic conditions. Solar cells have been prepared and characterized showing a correlation between improved film morphology and cell performance. The best cells achieved an efficiency of 2.4%.

Precursors’ order effect on the properties of sulfurized Cu2ZnSnS4 thin films

A dc magnetron sputtering-based method to grow high-quality Cu2ZnSnS4 (CZTS) thin films, to be used as an absorber layer in solar cells, is being developed. This method combines dc sputtering of metallic precursors with sulfurization in S vapour and with post-growth KCN treatment for removal of possible undesired Cu2−xS phases. In this work, we report the results of a study of the effects of changing the precursors’ deposition order on the final CZTS films’ morphological and structural properties. The effect of KCN treatment on the optical properties was also analysed through diffuse reflectance measurements. Morphological, compositional and structural analyses of the various stages of the growth have been performed using stylus profilometry, SEM/EDS analysis, XRD and Raman Spectroscopy. Diffuse reflectance studies have been done in order to estimate the band gap energy of the CZTS films. We tested two different deposition orders for the copper precursor, namely Mo/Zn/Cu/Sn and Mo/Zn/Sn/Cu. The stylus profilometry analysis shows high average surface roughness in the ranges 300–550 nm and 230–250 nm before and after KCN treatment, respectively. All XRD spectra show preferential growth orientation along (1 1 2) at 28.45◦. Raman spectroscopy shows main peaks at 338 cm−1 and 287 cm−1 which are attributed to Cu2ZnSnS4. These measurements also confirm the effectiveness of KCN treatment in removing Cu2−xS phases. From the analysis of the diffuse reflectance measurements the band gap energy for both precursors’ sequences is estimated to be close to 1.43 eV. The KCN-treated films show a better defined absorption edge; however, the band gap values are not significantly affected. Hot point probe measurements confirmed that CZTS had p-type semiconductor behaviour and C–V analysis was used to estimate the majority carrier density giving a value of 3.3 × 1018 cm−3.

A study of ternary Cu2SnS3 and Cu3SnS4 thin films prepared by sulfurizing stacked metal precursors

Thin films of Cu2SnS3 and Cu3SnS4 were grown by sulfurization of dc magnetron sputtered Sn–Cu metallic precursors in a S2 atmosphere. Different maximum sulfurization temperatures were tested which allowed the study of the Cu2SnS3 phase changes. For a temperature of 350 ◦C the films were composed of tetragonal (I -42m) Cu2SnS3. The films sulfurized at a maximum temperature of 400 ◦C presented a cubic (F-43m) Cu2SnS3 phase. On increasing the temperature up to 520 ◦C, the Sn content of the layer decreased and orthorhombic (Pmn21) Cu3SnS4 was formed. The phase identification and structural analysis were performed using x-ray diffraction (XRD) and electron backscattered diffraction (EBSD) analysis. Raman scattering analysis was also performed and a comparison with XRD and EBSD data allowed the assignment of peaks at 336 and 351 cm−1 for tetragonal Cu2SnS3, 303 and 355 cm−1 for cubic Cu2SnS3, and 318, 348 and 295 cm−1 for the Cu3SnS4 phase. Compositional analysis was done using energy dispersive spectroscopy and induced coupled plasma analysis. Scanning electron microscopy was used to study the morphology of the layers. Transmittance and reflectance measurements permitted the estimation of absorbance and band gap. These ternary compounds present a high absorbance value close to 104 cm−1. The estimated band gap energy was 1.35 eV for tetragonal (I -42m) Cu2SnS3, 0.96 eV for cubic (F-43m) Cu2SnS3 and 1.60 eV for orthorhombic (Pmn21) Cu3SnS4. A hot point probe was used for the determination of semiconductor conductivity type. The results show that all the samples are p-type semiconductors. A four-point probe was used to obtain the resistivity of these samples. The resistivities for tetragonal Cu2SnS3, cubic Cu2SnS3 and orthorhombic (Pmn21) Cu3SnS4 are 4.59 × 10−2 cm, 1.26 × 10−2 cm, 7.40 × 10−4 cm, respectively.

CuxSnSx+1 (x = 2, 3) thin films grown by sulfurization of metallic precursors deposited by dc magnetron sputtering

We report the results of the growth of Cu-Sn-S ternary chalcogenide compounds by sulfurization of dc magnetron sputtered metallic precursors. Tetragonal Cu2SnS3 forms for a maximum sulfurization temperature of 350 ºC. Cubic Cu2SnS3 is obtained at sulfurization temperatures above 400 ºC. These results are supported by XRD analysis and Raman spectroscopy measurements. The latter analysis shows peaks at 336 cm-1, 351 cm-1 for tetragonal Cu2SnS3, and 303 cm-1, 355 cm-1 for cubic Cu2SnS3. Optical analysis shows that this phase change lowers the band gap from 1.35 eV to 0.98 eV. At higher sulfurization temperatures increased loss of Sn is expected in the sulphide form. As a consequence, higher Cu content ternary compounds like Cu3SnS4 grow. In these conditions, XRD and Raman analysis only detected orthorhombic (Pmn21) phase (petrukite). This compound has Raman peaks at 318 cm-1, 348 cm-1 and 295 cm-1. For a sulfurization temperature of 450 ºC the samples present a multi-phase structure mainly composed by cubic Cu2SnS3 and orthorhombic (Pmn21) Cu3SnS4. For higher temperatures, the samples are single phase and constituted by orthorhombic (Pmn21) Cu3SnS4. Transmittance and reflectance measurements were used to estimate a band gap of 1.60 eV. For comparison we also include the results for Cu2ZnSnS4 obtained using similar growth conditions.

Assessment of the potential of tin sulphide thin films prepared by sulphurization of metallic precursors as cell absorbers

In this work, SnxSy thin films have been grown on soda-lime glass substrates by sulphurization of metallic precursors in a nitrogen plus sulphur vapour atmosphere. Different sulphurization temperatures were tested, ranging from 300 °C to 520 °C. The resulting phases were structurally investigated by X-Ray Diffraction and Raman spectroscopy. Composition was studied using Energy Dispersive Spectroscopy being then correlated with the sulphurization temperature. Optical measurements were performed to obtain transmittance and reflectance spectra, from which the energy band gaps, were estimated. The values obtained were 1.17 eV for the indirect transition and for the direct transition the values varied from 1.26 eV to 1.57 eV. Electrical characterization using Hot Point Probe showed that all samples were p-type semiconductors. Solar cells were built using the structure: SLG/Mo/SnxSy/CdS/ZnO:Ga and the best result for solar cell efficiency was 0.17%.

Cu2ZnSnS4 solar cells prepared with sulphurized dc-sputtered stacked metallic precursors

In the present work we report the details of the preparation and characterization results of Cu2ZnSnS4 (CZTS) based solar cells. The CZTS absorber was obtained by sulphurization of dc magnetron sputtered Zn/Sn/Cu precursor layers. The morphology, composition and structure of the absorber layer were studied by scanning electron microscopy, energy dispersive spectroscopy, X-ray diffraction and Raman scattering. The majority carrier type was identified via a hot point probe analysis. The hole density, space charge region width and band gap energy were estimated from the external quantum efficiency measurements. A MoS2 layer that formed during the sulphurization process was also identified and analyzed in this work. The solar cells had the following structure: soda lime glass/Mo/CZTS/CdS/i-ZnO/ZnO:Al/Al grid. The best solar cell showed an opencircuit voltage of 345 mV, a short-circuit current density of 4.42 mA/cm2, a fill factor of 44.29% and an efficiency of 0.68% under illumination in simulated standard test conditions: AM 1.5 and 100 mW/cm2.

Mixed integer non linear programming and artificial neural network based approach to ancillary services dispatch in competitive electricity markets

Ancillary services represent a good business opportunity that must be considered by market players. This paper presents a new methodology for ancillary services market dispatch. The method considers the bids submitted to the market and includes a market clearing mechanism based on deterministic optimization. An Artificial Neural Network is used for day-ahead prediction of Regulation Down, regulation-up, Spin Reserve and Non-Spin Reserve requirements. Two test cases based on California Independent System Operator data concerning dispatch of Regulation Down, Regulation Up, Spin Reserve and Non-Spin Reserve services are included in this paper to illustrate the application of the proposed method: (1) dispatch considering simple bids; (2) dispatch considering complex bids.

Neural networks for condition monitoring of wind turbines gearbox

Wind energy is considered a hope in future as a clean and sustainable energy, as can be seen by the growing number of wind farms installed all over the world. With the huge proliferation of wind farms, as an alternative to the traditional fossil power generation, the economic issues dictate the necessity of monitoring systems to optimize the availability and profits. The relatively high cost of operation and maintenance associated to wind power is a major issue. Wind turbines are most of the time located in remote areas or offshore and these factors increase the referred operation and maintenance costs. Good maintenance strategies are needed to increase the health management of wind turbines. The objective of this paper is to show the application of neural networks to analyze all the wind turbine information to identify possible future failures, based on previous information of the turbine.

Multiple Linear Regression and Artificial Neural Networks to Predict Time and Efficiency of Soil Vapor Extraction

The prediction of the time and the efficiency of the remediation of contaminated soils using soil vapor extraction remain a difficult challenge to the scientific community and consultants. This work reports the development of multiple linear regression and artificial neural network models to predict the remediation time and efficiency of soil vapor extractions performed in soils contaminated separately with benzene, toluene, ethylbenzene, xylene, trichloroethylene, and perchloroethylene. The results demonstrated that the artificial neural network approach presents better performances when compared with multiple linear regression models. The artificial neural network model allowed an accurate prediction of remediation time and efficiency based on only soil and pollutants characteristics, and consequently allowing a simple and quick previous evaluation of the process viability.

Multilayer Perceptron Neural Networks Training Through Charged System Search and its Application for Non-Technical Losses Detection

The non-technical loss is not a problem with trivial solution or regional character and its minimization represents the guarantee of investments in product quality and maintenance of power systems, introduced by a competitive environment after the period of privatization in the national scene. In this paper, we show how to improve the training phase of a neural network-based classifier using a recently proposed meta-heuristic technique called Charged System Search, which is based on the interactions between electrically charged particles. The experiments were carried out in the context of non-technical loss in power distribution systems in a dataset obtained from a Brazilian electrical power company, and have demonstrated the robustness of the proposed technique against with several others natureinspired optimization techniques for training neural networks. Thus, it is possible to improve some applications on Smart Grids.

Metalearner based on Dynamic Neural Network for Strategic Bidding in electricity Markets

The restructuring of electricity markets, conducted to increase the competition in this sector, and decrease the electricity prices, brought with it an enormous increase in the complexity of the considered mechanisms. The electricity market became a complex and unpredictable environment, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. Software tools became, therefore, essential to provide simulation and decision support capabilities, in order to potentiate the involved players’ actions. This paper presents the development of a metalearner, applied to the decision support of electricity markets’ negotiation entities. The proposed metalearner executes a dynamic artificial neural network to create its own output, taking advantage on several learning algorithms implemented in ALBidS, an adaptive learning system that provides decision support to electricity markets’ players. The proposed metalearner considers different weights for each strategy, depending on its individual quality of performance. The results of the proposed method are studied and analyzed in scenarios based on real electricity markets’ data, using MASCEM - a multi-agent electricity market simulator that simulates market players’ operation in the market.