Transformer Oil Dissolved Gas Concentration Prediction Based on Genetic Algorithm and Improved Gray Verhulst Model

In this article, an improved grey prediction model is proposed to address low-accuracy prediction issue of grey forecasting model. The first step is using a trigonometric function to transform the original data sequence to smooth the data, which is called smoothness of grey prediction model, and then a grey support vector machine model by integrating the improved grey model with support vector machine is introduced. At the initial stage of the model, trigonometric functions and accumulation generation operation can be used to preprocess the data, which enhances the smoothness of the data and reduces the associated randomness. In addition, support vector machine is implemented to establish a prediction model for the pre-processed data and select the optimal model parameters via genetic algorithms. Finally, the data are restored through the ‘regressive generate’ operation to obtain the forecasting data. To prove that the grey support vector machine model is superior to the other models, the battery life data from the Center for Advanced Life Cycle Engineering are selected, and the presented model is used to predict the remaining useful life of the battery. The predicted result is compared to that of grey model and support vector machines. For a more intuitive comparison of the three models, this article quantifies the root mean square errors for these three different models in the case of different ratio of training samples and prediction samples. The results show that the effect of grey support vector machine model is optimal, and the corresponding root mean square error is only 3.18%.

<abstract> <p>Fractional order imply the idea of "in between", the grey model generated by fractional accumulation has better prediction and adaptability than that generated by first-order accumulation. General grey model of the differential equation of the left is a cumulative function derivative of time, in order to improve the adaptability of the model and prediction ability, general fractional order differential equation model is presented. In this paper, on the basis of the derivation of time $ t $ extensions to the derivation of $ {t^u} $, added a variable coefficient, and through the integral differential equation and tectonic background value. We establish an optimized fractional order cumulative grey model with variable parameters, i.e., optimized fractional order accumulated grey model (FOGM (1, 1)). By using the Particle swarm optimization (PSO) algorithm, we search for the order and variable parameters of the optimal fractional order. Then we apply the proposed model to predict the total energy consumption of Jiangsu province and the consumption level of Chinese residents. The results indicate that the proposed model has high fitting and prediction accuracy compared to other classical grey prediction models, such as grey model (GM (1, 1)), non-homogeneous grey model (NGM (1, 1)) and fractional order accumulated grey model (FGM (1, 1)). It also validates that the proposed model is a practical and promising model for forecasting the energy consumption as well as the consumption level of Chinese residents.</p> </abstract>

Population forecasting plays a significant role in determining demography, economics, and agriculture policies for developing countries. In this study, we employ the five different grey prediction models to estimate the population of Türkiye until 2050 using the 2007 to 2022 address-based data. These models are given as the grey standard (GM (1,1)), grey time-varying dynamic (GM (1,1) t), grey Gompertz (GGM), grey Verhulst (GVM), and grey exponential (EXGM (1,1). The comparison of grey models is evaluated by mean absolute percentage error (MAPE), regression coefficient (R2), variance ratio (C), and probability of error (P). The GGM and GM (1,1) t are identified as the most suitable models for predicting the period 2007-2022. For the future population forecasts from 2023 to 2050, the five models are compared with the projection values of the Turkish Statistical Institute published in 2018. The GGM is determined to be the most compatible based on the MAPE value of 0.68116 and the C value of 0.05218, and the Grey Verhulst model is provided the most compatible R2 value of 0.99818. According to the GGM, the population of Türkiye is projected to reach 105,948,975 by 2050, 106,877,632 based on the GM (1,1) t, and 102,591,471 based on the GVM.

The grey Riccati model (GRM) is a generalization of the grey Verhulst model (GVM). Both the GRM and GVM generally perform well in simulating and forecasting the raw sequences with a bell-shaped or single peak feature. Although there are several methods to solve the Riccati differential equation, the existing time response functions of the GRM are generally complicated. In order to reduce the computational complexity of the time response function, this study attempts to transform the Riccati equation into a Bernoulli equation with the help of a known particular solution. Then, a unified time response function of the GRM is obtained by the proposed methodology. The simulation results demonstrate that the proposed unified grey Riccati model performs the same as the grey generalized Verhulst model (a kind of grey Riccati model) and is better than the traditional grey Verhulst model. The fact also reveals that the newly developed grey Riccati model is reasonable and effective.

Traffic flow prediction is crucial in transportation management and optimizing control strategies and infrastructure planning. However, traditional prediction methods often need help handling traffic data's inherent uncertainty and complexity. This paper explores the application of Grey prediction models as a promising approach for efficient traffic flow prediction. Grey prediction models, rooted in Grey systems theory, offer a robust framework for modelling systems with incomplete and uncertain information. The paper provides a comprehensive overview of Grey prediction models, including the Grey Verhulst, Grey-Markov, and Grey differential equation models. It discusses the process of data collection, pre-processing, and model application in traffic flow prediction. Case studies and experimental results demonstrate the effectiveness of Grey prediction models in accurately forecasting traffic flow patterns. Despite challenges such as data sparsity and model complexity, Grey prediction models offer significant advantages over traditional methods, including improved prediction accuracy and adaptability to dynamic traffic conditions. The paper concludes with recommendations for practitioners and researchers interested in leveraging Grey prediction models for efficient traffic management.

Purpose – The purpose of this paper is to propose a novel approach to improve prediction accuracy of grey power models including GM(1, 1) and grey Verhulst model. Design/methodology/approach – The modified new models are proposed by optimizing the initial condition and model parameters. The new initial condition consists of the first item and the last item of a sequence generated by applying the first-order accumulative generation operator on the sequence of raw data. Findings – It is shown that the newly modified grey power model is an extension of the previous optimized GM(1, 1) and grey Verhulst model. And the optimized initial condition reflected the principle of new information priority. Practical implications – The result of a numerical example indicates that the modified grey model presented in this paper with better prediction performance. Originality/value – The new initial condition are derived by weighted combination of the first item and the last item. The coefficients of weight obtained by the least square method.

A fluctuation data grey model and its prediction of rainstorm days

Energy-efficient virtual machine placement in data centres via an accelerated Genetic Algorithm with improved fitness computation

A new prediction model presented in this paper is called the grey model with convolution integral, abbreviated as GMC(1, n). Additional n − 1 series can be introduced by the new model GMC(1, n) to improve the accuracy of prediction made by the existing grey model GM(1, 1). Improvements on the existing grey prediction model GM(1, n) are made to a large extent and the messages for a system can be inserted sufficiently. The relationship between input series and output series is constructed sufficiently by GMC(1, n) and high accuracy of indirect measurement or prediction for a dynamic system can be broadly anticipated. The relationship between the tensile strength and Brinell hardness number of a material is very intensive, but a definite explicit or implicit function to describe it does not exist. The property of a material is a grey system. It is more difficult to measure the tensile strength than the Brinell hardness number of a material especially for a higher temperature. The indirect measurement of the tensile strength of a material for a higher temperature can be made by GMC(1, n) with the Brinell hardness number of the material acting as a leading indicator. The results show that the accuracy of the indirect measurement of the tensile strength is satisfactory.

A novel grey-fuzzy regulator using genetic algorithms for a dc motor is presented in this paper. The grey system theory is employed to design a grey prediction model. After the grey model predicting the feedback errors of the motor speed, a compensated energy will be generated for the fuzzy controller. Appending the grey predictor to the feedback control system, then the fuzzy inference engine receives not only the current data but also the future information. Furthermore, the optimal parameter of the grey model is acquired via genetic algorithms. Computer simulation results show that the regulation performance of the motor speed and the control energy is improved.

The discrete grey model is increasingly used in various real-world forecasting problems, however, in the modeling procedure, neglecting the effect of the time power and requiring the integer-order accumulation impair the prediction performance to some extent. Considering this fact, this paper implements the fractional accumulating generation operator and time power term in the discrete grey polynomial model, and as a consequence, a generalized discrete grey polynomial model, namely GDGMP(1,1,N,α), is proposed. To further improve the prediction accuracy, a metaheuristic algorithm, namely the quantum genetic algorithm (QGA), is applied to determine the emerging coefficients. In the presence of alternate emerging coefficients, the GDGMP(1,1,N,α) model is compatible with other existing grey models. To demonstrate the effectiveness of the newly proposed model, this model is employed to forecast three real cases (i.e., natural gas consumption, electricity consumption, and elderly population) by comparing it with other benchmark models. The experimental results show that among these competitive models, the proposed model achieves the best prediction performance, and its MAPE (often referred to as the core indicator) for natural gas consumption, electricity consumption, and the elderly population achieves values of 6.05%, 3.22%, and 0.66%, respectively, which are all lower than those of the other models, indicating that the proposed model outperforms other benchmarks.

An optimized Nash nonlinear grey Bernoulli model based on particle swarm optimization and its application in prediction for the incidence of Hepatitis B in Xinjiang, China

Forecast of biofuel production and consumption in top CO2 emitting countries using a novel grey model

Gray box model and artificial neural network (ANN) model of central air-conditioning cold source system have been established with simulation data to predict system operation energy consumption and compare the prediction accuracy difference of models under variable training data. A hybrid model is proposed to combine gray box model and ANN model based on K-means cluster algorithm. The results show that ANN model has higher prediction accuracy than gray box model when the membership of model input variables to trained input data is greater than 0.4. Otherwise, the gray box model has higher energy consumption prediction accuracy. Compared with gray box model and ANN model, prediction accuracy of hybrid model increases 27.7% and 33.85% on average under different training data.

Grey and neural network prediction of suspended solids and chemical oxygen demand in hospital wastewater treatment plant effluent