Next-day electricity-price forecasting using a hybrid network

The paper proposes a novel method of forecasting short-term electricity price based on a two-stage hybrid network of self-organised map (SOM) and support-vector machine (SVM). In the first stage, a SOM network is applied to cluster the input-data set into several subsets in an unsupervised manner. Then, a group of SVMs is used to fit the training data of each subset in the second stage in a supervised way. With the trained network, one can predict straightforwardly the next-day hourly electricity prices. To confirm its effectiveness, the proposed model has been trained and tested on the data of historical energy prices from the New England electricity market.     

Preparation and photochromism of nanocomposite thin film based on polyoxometalate and polyethyleneglycol

A photochromic nanocomposite based on Keggin structure phosphomolybdic acid (PMoA) well dispersed in polyethyleneglycol (PEG) was fabricated. TEM image showed that PMoA nanoparticles with narrow size distribution were finely dispersed in polymer matrix. FT-IR results showed that the Keggin geometry of polyoxometalates was still preserved inside the composites and strong coulombic interaction was built between PMoA and polymer matrix. Under UV irradiation, the film was reduced photochemically to yield a blue species, which was in accordance with a charge-transfer mechanism.     

The hydration of slag,part 1: reaction models for alkali-activated slag

Reaction models are proposed to quantify the hydration products and to determine the composition of C–S–H from alkali-activated slags (AAS). Products of the slag hydration are first summarized from observations in literature. The main hydration products include C–S–H, hydrotalcite, hydrogarnet, AFm phases (C₄AH₁₃ and C₂ASH₈) and ettringite. Then, three stoichiometric reaction models are established correlating the mineral composition of slag (the glass part) with the hydration products. Using the proposed models, quantities of hydration products and composition of C–S–H are determined. The models are validated with a number of experimental investigations reported in literature, yielding good agreement, i.e., these models can successfully predict the hydration reaction of AAS. The models are furthermore applied to calculate the retained water in the hydration products of AAS in different hydration states and a general hydration equation of AAS is derived. As an illustration to one of the model applications, chemical shrinkage of the AAS cement paste in different hydration states are predicted. The chemical shrinkage of AAS is shown to be remarkably higher than OPC. Furthermore, phase distribution in the hardened AAS paste and the porosity are calculated.     

Preparation, sintering, and microstructures of strontium barium bismuth tantalate layered perovskite ceramics

The solid solutions of Ba-doped SrBi₂Ta₂O₉ layered perovskite ceramic powders have been successfully prepared via a two-step process using BiTaO₄ as a precursor. The lattice constants of the solid solutions monotonically increase with increasing barium-ion content. The sinterability of (Sr_1–xBa_x)Bi₂Ta₂O₉ powders is significantly improved by increasing the barium-ion content. When the specimens with high barium-ion contents are sintered at 1100°C, they thermally decompose to form rod-like grains and the matrix expands, leading to a lower density. The addition of barium ions to SrBi₂Ta₂O₉ also results in significant variation in the morphology of the sintered specimens and the occurrence of c-axis preferred orientation which is ascribed to the anisotropic growth of plate-like grains. The precise control of the barium-ion content as well as the sintering conditions is critical for obtaining densified barium-ion doped SrBi₂Ta₂O₉ ceramics with a pure, layered perovskite structure.