Short term load forecasting using interval type-2 fuzzy logic systems

Accurate Short Term Load Forecasting (STLF) is essential for a variety of decision making processes. However, forecasting accuracy may drop due to presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. This paper proposes the application of Interval Type-2 Fuzzy Logic Systems (IT2 FLSs) for the problem of STLF. IT2 FLSs, with extra degrees of freedom, are an excellent tool for handling prevailing uncertainties and improving the prediction accuracy. Experiments conducted with real datasets show that IT2 FLS models appropriately approximate future load demands with an acceptable accuracy. Furthermore, they demonstrate an encouraging degree of accuracy superior to feedforward neural networks used in this study.

Interval type-2 fuzzy logic systems for load forecasting : a comparative study

Accurate short term load forecasting (STLF) is essential for a variety of decision-making processes. However, forecasting accuracy can drop due to the presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. This paper proposes the application of Interval Type-2 Fuzzy Logic Systems (IT2 FLSs) for the problem of STLF. IT2 FLSs, with additional degrees of freedom, are an excellent tool for handling uncertainties and improving the prediction accuracy. Experiments conducted with real datasets show that IT2 FLS models precisely approximate future load demands with an acceptable accuracy. Furthermore, they demonstrate an encouraging degree of accuracy superior to feedforward neural networks and traditional type-1 Takagi-Sugeno-Kang (TSK) FLSs.

Prediction interval construction using interval type-2 fuzzy logic systems

This study proposes a novel non-parametric method for construction of prediction intervals (PIs) using interval type-2 Takagi-Sugeno-Kang fuzzy logic systems (IT2 TSK FLSs). The key idea in the proposed method is to treat the left and right end points of the type-reduced set as the lower and upper bounds of a PI. This allows us to construct PIs without making any special assumption about the data distribution. A new training algorithm is developed to satisfy conditions imposed by the associated confidence level on PIs. Proper adjustment of premise and consequent parameters of IT2 TSK FLSs is performed through the minimization of a PI-based objective function, rather than traditional error-based cost functions. This new cost function covers both validity and informativeness aspects of PIs. A metaheuristic method is applied for minimization of the non-linear non-differentiable cost function. Quantitative measures are applied for assessing the quality of PIs constructed using IT2 TSK FLSs. The demonstrated results for four benchmark case studies with homogenous and heterogeneous noise clearly show the proposed method is capable of generating high quality PIs useful for decision-making.

Study protocol for "Moving bright, eating smart"- a phase 2 clinical trial on the acceptability and feasibility of a diet and physical activity intervention to prevent recurrence in colorectal cancer survivors

Background: Colorectal cancer is the second most common cancer and cancer-killer in Hong Kong with an alarming increasing incidence in recent years. The latest World Cancer Research Fund report concluded that foods low in fibre, and high in red and processed meat cause colorectal cancer whereas physical activity protects against
colon cancer. Yet, the influence of these lifestyle factors on cancer outcome is largely unknown even though cancer survivors are eager for lifestyle modifications. Observational studies suggested that low intake of a Western-pattern diet and high physical activity level reduced colorectal cancer mortality. The Theory of Planned
Behaviour and the Health Action Process Approach have guided the design of intervention models targeting a wide range of health-related behaviours.
Methods/design: We aim to demonstrate the feasibility of two behavioural interventions intended to improve colorectal cancer outcome and which are designed to increase physical activity level and reduce consumption of a Western-pattern diet. This three year study will be a multicentre, randomised controlled trial in a 2x2 factorial
design comparing the “Moving Bright, Eating Smart” (physical activity and diet) programme against usual care. Subjects will be recruited over a 12-month period, undertake intervention for 12 months and followed up for a further 12 months. Baseline, interim and three post-intervention assessments will be conducted. Two hundred and twenty-two colorectal cancer patients who completed curative treatment without evidence of recurrence will be recruited into the study. Primary outcome measure will be whether physical activity and dietary targets are met at the end of the 12-month intervention. Secondary outcome measures include the magnitude and
mechanism of behavioural change, the degree and determinants of compliance, and the additional health benefits and side effects of the intervention.
Discussion: The results of this study will establish the feasibility of targeting the two behaviours (diet and physical activity) and demonstrate the magnitude of behaviour change. The information will facilitate the design of a further larger phase III randomised controlled trial with colorectal cancer outcome as the study endpoint to determine whether this intervention model would reduce colorectal cancer recurrence and mortality.

A new neural network-based type reduction algorithm for interval type-2 fuzzy logic systems

This paper introduces a new type reduction (TR) algorithm for interval type-2 fuzzy logic systems (IT2 FLSs). Flexibility and adaptiveness are the key features of the proposed non-parametric algorithm. Lower and upper firing strengths of rules as well as their consequent coefficients are fed into a neural network (NN). NN output is a crisp value that corresponds to the defuzzified output of IT2 FLSs. The NN type reducer is trained through minimization of an error-based cost function with the purpose of improving modelling and forecasting performance of IT2 FLS models. Simulation results indicate that application of the proposed TR algorithm greatly enhances modelling and forecasting performance of IT2 FLS models. This benefit is achieved in no cost, as the computational requirement of the proposed algorithm is less than or at most equivalent to traditional TR algorithms.

Security protocols for EPC class-1 Gen-2 RFID multi-tag systems

The objective of the research is to develop security protocols for EPC C1G2 RFID Passive Tags in the areas of ownership transfer and grouping proof.

Decoupled ion conduction in poly(2-acrylamido-2-methyl-1-propane-sulfonic acid) homopolymers

As the focus on developing new polymer electrolytes continues to intensify in the area of alternative energy conversion and storage devices, the rational design of polyelectrolytes with high single ion transport rates has emerged as a primary strategy for enhancing device performance. Previously, we reported a series of sulfonate based copolymer ionomers based on using mixed bulky quaternary ammonium cations and sodium cations as the ionomer counterions. This led to improvements in the ionic conductivity and an apparent decoupling from the Tg of the ionomer. In this article, we have prepared a new series of ionomers based on the homopolymer of poly(2-acrylamido-2-methyl-1-propane-sulfonic acid) using differing sizes of the ammonium counter-cations. We observe a decreasing Tg with increasing the bulkiness of the quaternary ammonium cation, and an increasing degree of decoupling from Tg within these systems. Somewhat surprisingly, phase separation is observed in this homopolymer system, as evidenced from multiple impedance arcs, Raman mapping and SEM. The thermal properties, morphology and the effect of plasticizer on the transport properties in these ionomers are also presented. The addition of 10 wt% plasticizer increased the ionic conductivity between two and three orders of magnitudes leading to materials that may have applications in sodium based devices. This journal is

Robust nonlinear controller design for three-phase grid-connected photovoltaic systems under structured uncertainties

This paper presents a robust nonlinear controller design for a three-phase grid-connected photovoltaic (PV) system to control the current injected into the grid and the dc-link voltage for extracting maximum power from PV units. The controller is designed based on the partial feedback linearization approach, and the robustness of the proposed control scheme is ensured by considering structured uncertainties within the PV system model. An approach for modeling the uncertainties through the satisfaction of matching conditions is provided. The superiority of the proposed robust controller is demonstrated on a test system through simulation results under different system contingencies along with changes in atmospheric conditions. From the simulation results, it is evident that the robust controller provides excellent performance under various operating conditions. © 2014 IEEE.

EEG signal classification for BCI applications by wavelets and interval type-2 fuzzy logic systems

The nonlinear, noisy and outlier characteristics of electroencephalography (EEG) signals inspire the employment of fuzzy logic due to its power to handle uncertainty. This paper introduces an approach to classify motor imagery EEG signals using an interval type-2 fuzzy logic system (IT2FLS) in a combination with wavelet transformation. Wavelet coefficients are ranked based on the statistics of the receiver operating characteristic curve criterion. The most informative coefficients serve as inputs to the IT2FLS for the classification task. Two benchmark datasets, named Ia and Ib, downloaded from the brain-computer interface (BCI) competition II, are employed for the experiments. Classification performance is evaluated using accuracy, sensitivity, specificity and F-measure. Widely-used classifiers, including feedforward neural network, support vector machine, k-nearest neighbours, AdaBoost and adaptive neuro-fuzzy inference system, are also implemented for comparisons. The wavelet-IT2FLS method considerably dominates the comparable classifiers on both datasets, and outperforms the best performance on the Ia and Ib datasets reported in the BCI competition II by 1.40% and 2.27% respectively. The proposed approach yields great accuracy and requires low computational cost, which can be applied to a real-time BCI system for motor imagery data analysis.

The competition between metastable and equilibrium S (Al2CuMg) phase during the decomposition of AlCuMg alloys

Abstract The decomposition sequence of the supersaturated solid solution leading to the formation of the equilibrium S (Al2CuMg) phase in AlCuMg alloys has long been the subject of ambiguity and debate. Recent high-resolution synchrotron powder diffraction experiments have shown that the decomposition sequence does involve a metastable variant of the S phase (denoted S1), which has lattice parameters that are distinctly different to those of the equilibrium S phase (denoted S2). In this paper, the difference between these two phases is resolved using high-resolution synchrotron and neutron powder diffraction and atom probe tomography, and the transformation from S1 to S2 is characterised in detail by in situ synchrotron powder diffraction. The results of these experiments confirm that there are no significant differences between the crystal structures of S1 and S2, however, the powder diffraction and atom probe measurements both indicate that the S1 phase forms with a slight deficiency in Cu. The in situ isothermal aging experiments show that S1 forms rapidly, reaching its maximum concentration in only a few minutes at high temperatures, while complete conversion to the S2 phase can take thousands of hours at low temperature. The kinetics of S phase precipitation have been quantitatively analysed for the first time and it is shown that S1 phase forms with an average activation energy of 75 kJ/mol, which is much lower than the activation energy for Cu and Mg diffusion in an Al matrix (136 kJ/mol and 131 kJ/mol, respectively). The mechanism of the replacement of S1 with the equilibrium S2 phase is discussed.

Nonlinear backstepping controller design for sharing active and reactive power in three-phase grid-connected photovoltaic systems

In this paper, a nonlinear backstepping controller is designed for three-phase grid-connected solar photovoltaic (PV) systems to share active and reactive power. A cascaded control structure is considered for the purpose of sharing appropriate amount of power. In this cascaded control structure, the dc-link voltage controller is designed for balancing the power flow within the system and the current controller is designed to shape the grid current into a pure sinusoidal waveform. In order to balance the power flow, it is always essential to maintain a constant voltage across the dc-link capacitor for which an incremental conductance (IC) method is used in this paper. This approach also ensures the operation of solar PV arrays at the maximum power point (MPP) under rapidly changing atmospheric conditions. The proposed current controller is designed to guarantee the current injection into the grid in such a way that the system operates at a power factor other than unity which is essential for sharing active and reactive power. The performance of the proposed backstepping approach is verified on a three-phase grid-connected PV system under different atmospheric conditions. Simulation results show the effectiveness of the proposed control scheme in terms of achieving desired control objectives.