A novel medium- and long-term load forecasting method based on sensitivity analysis of multi meteorological indicators

Support Vector Machine (SVM) is a precise and fast method for the prediction of short-term electrical load and the similar day method is a simple and direct method for load forecasting. This paper tries to combine SVM model and similar day method for next day load forecasting. The proposed method forecasts the load of next day using SVM. Then, the load curve of a similar day is selected to correct the curve forecasted by SVM, which can avoid the appearance of large forecasting error effectively. Corresponding software was developed and used to forecast the next day load in a practical power system, and the final forecasting result is accurate and reliable.

The traditional method for power load forecasting is susceptible to various factors, including holidays, seasonal variations, weather conditions, and more. These factors make it challenging to ensure the accuracy of forecasting results. Additionally, there is a limitation in extracting meaningful physical signs from power data, which ultimately reduces prediction accuracy. This paper aims to address these issues by introducing a novel approach called VCAG (Variable Mode Decomposition-Convolutional Neural Network-Attention Mechanism-Gated Recurrent Unit) for combined power load forecasting. In this approach, we integrate Variable Mode Decomposition (VMD) with Convolutional Neural Network (CNN). VMD is employed to decompose power load data, extracting valuable time-frequency features from each component. These features then serve as input for the CNN. Subsequently, an attention mechanism is applied to give importance to specific features generated by the CNN, enhancing the weight of crucial information. Finally, the weighted features are fed into a Gated Recurrent Unit (GRU) network for time series modeling, ultimately yielding accurate load forecasting results.To validate the effectiveness of our proposed model, we conducted experiments using two publicly available datasets. The results of these experiments demonstrate that our VCAG method achieves high accuracy and stability in power load forecasting, effectively overcoming the limitations associated with traditional forecasting techniques. As a result, this approach holds significant promise for broad applications in the field of power load forecasting.

Artificial Neural Network (ANN) is a learning method that can be used for prediction and classification. In this study, ANN back-propagation is implemented to predict the closing price of the S&P 500 stock exchange using historical data. Historical data consisting of five variables, namely open, high, low, close, and volume. The historical data are taken from finance.yahoo.com which stores historical data of daily stock prices up to 65 years earlier. The data is designed based on daily prediction scenarios of the closing stock price of the S&P 500 stock exchange. Using the scenario an application prototype using R and Java software has been successfully built. The prototype is dynamic during select the data set (10, 50, 100, 500 past data) to get the best stock closing prediction for the next day. The selection of the best stock closing prediction uses the MAPE (Mean Average Percentage Error) criterion which is in contrast to the prediction accuracy level. The smaller the MAPE value the better the predicted result. Based on the implementation results, the average MAPE for daily forecast for 1 month in April 2017 was 0.2307 indicating that the average daily prediction accuracy rate for 1 month was 99.77%. Our prototype application can make prediction automatically every day, every time when connected to the internet.

A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids

An integrated genetic algorithm (GA)/fuzzy system (FS), tabu search (TS) and neural fuzzy network (NFN) method for load forecasting is presented in this paper. A fuzzy hyper-rectangular composite neural networks (FHRCNNs) was used for the initial load forecasting. Then we used CGAFS and TS to find the optimal solution of the parameters of the FHRCNNs, instead of backpropagation (BP)(including parameters such as synaptic weights, biases, membership functions, sensitivity factor in membership functions and adjustable synaptic weights). First the CGAFS generates a set of feasible solution parameters and then puts the solution into the TS. The CGAKS has good global optimal search capabilities, but poor local optimal search capabilities. The TS method on the other hand has good local optimal search capabilities. We combined both methods to try and obtain both advantages, and in doing so eliminate the drawback of the traditional ANN training by BP. Finally, we used the (GAFSTS-NFN) to see if we could improve the quality of the solution, and if we actually could reduce the error of load forecasting. The proposed CGAFS-TS load forecasting scheme was tested using data obtain from a sample study, including one year, one week and 24-hours time periods. The results demonstrated the accuracy of the proposed load forecasting scheme.

Crop yield varies spatially and temporally due to several limiting factors, including soil type, nutrient availability, water availability, weather, and crop varieties. It is difficult to quantify the severity of these limiting factors on crop yield as well as the spatial variation of crop yield before harvest. Remotely sensed aerial images can be used to improve estimates of mid-season crop yields. However, the success of such approaches is typically dependent on the image classification technique used. In this article, we develop an automated self-organizing map (SOM) neural image classification technique and evaluate it with respect to the widely used ISODATA clustering method using visual assessment of preservation of image texture. We also develop hybrid SOM-back-propagation neural network (BPNN) models to predict crop yield from the Oakes Irrigation Test Area (OITA) research sites at Oakes, North Dakota. We used the SOM image classification technique to classify the composite visible and near-infrared (NIR) band aerial images from several parts of the OITA research site. SOM cluster centroids from individual grid images were used as inputs to the BPNN yield prediction models created for the years 1997, 1998, 1999, 2000, and 2001. The models using individual red, green, and NIR band digital data provided average corn yield prediction accuracies of more than 80% for every year, except for the NIR model in 1998 (45%). Individual year models were validated with individual band training and testing datasets from the other four years. Models using the green band dataset provided better validation results. Average corn yield prediction accuracies ranged from 55% to a maximum of 96%. Average corn yield prediction accuracies of validated models using the red band and NIR band datasets ranged from 33% to a maximum of 94% and from 36% to a maximum of 95%, respectively. This article establishes the use of hybrid SOM-BPNN modeling techniques to predict corn yield from aerial images at mid-crop season.

Genomic selection and high-throughput phenotyping (HTP) are promising tools to accelerate breeding gains for high-yielding and climate-resilient wheat varieties. Hence, our objective was to evaluate them for predicting grain yield (GY) in drought-stressed (DS) and late-sown heat-stressed (HS) environments of the International maize and wheat improvement center’s elite yield trial nurseries. We observed that the average genomic prediction accuracies using fivefold cross-validations were 0.50 and 0.51 in the DS and HS environments, respectively. However, when a different nursery/year was used to predict another nursery/year, the average genomic prediction accuracies in the DS and HS environments decreased to 0.18 and 0.23, respectively. While genomic predictions clearly outperformed pedigree-based predictions across nurseries, they were similar to pedigree-based predictions within nurseries due to small family sizes. In populations with some full-sibs in the training population, the genomic and pedigree-based prediction accuracies were on average 0.27 and 0.35 higher than the accuracies in populations with only one progeny per cross, indicating the importance of genetic relatedness between the training and validation populations for good predictions. We also evaluated the item-based collaborative filtering approach for multivariate prediction of GY using the green normalized difference vegetation index from HTP. This approach proved to be the best strategy for across-nursery predictions, with average accuracies of 0.56 and 0.62 in the DS and HS environments, respectively. We conclude that GY is a challenging trait for across-year predictions, but GS and HTP can be integrated in increasing the size of populations screened and evaluating unphenotyped large nurseries for stress–resilience within years.

Short-term load forecasting plays a vital role for the power system’s safe operation and production arrangements. This paper regards electric load forecasting as a nonlinear time series prediction problem, and establishes the electric load autoregressive prediction model (ARX Model) based on historical load data, approaching ARX model parameters with RBF neural network, estimating model parameters with using a Structured Nonlinear Parameters Optimization Method (SNPOM), proposing cycle prediction method for short-term electric load forecasting. Experimental results show that the method has higher prediction accuracy for short-term electric load forecasting. Keywords: Short-term load forecasting; time series; RBF-ARX model; cycle forecasting; structured nonlinear parameter optimization method

Electricity becoming more and more important for the development of a secure & sustainable energy system. Electricity Demand growth is likely to be anemic. With the rising complexity of energy systems, new ways to use engineering experience and data collecting to increase load forecasting accurately are needed. With the recent advancements in the field of machine learning to leverage big data sets and draw inferences from a vast data set. The electrical load is predicted by using a variety of research strategies, including deterministic and stochastic procedures. This manuscript intends to estimate load demand by utilizing various stochastic methods for Short-Term Load Forecasting (STLF). The dataset is trained using various regression techniques which include a Decision tree, Support Vector machines (SVM), and Ensembles. The performance of the finest regression methodology is analyzed over parameters like RMSE (root mean square error), MSE (mean square error) and, R-squared, MAE (mean absolute error) & training time. The most effective technique is determined by feeding the best machine learning algorithm to various regression learners over data cross-validation of 5 folds and 7 folds. MATLAB platforms are used to implement the methods.

We propose an enhanced multiple branch predictor using per-primary address branch histories. Using this scheme, the interferences among different branches are reduced, enhancing the average prediction accuracy. Also, since the branches predicted each cycle do not suffer from successive dependencies, predictions are generated in parallel. This scheme results in higher average branch prediction accuracy than the previous global history scheme under the same implementation cost. For two branch predictions, the prediction accuracy of integer benchmarks varies between 92.0 and 96.9 percent. For floating point benchmarks including nasa7, the accuracy is between 94.8 and 95.8 percent.KeywordsPrediction AccuracySecondary BranchBranch PredictionTertiary BranchHistory RegisterThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

With the requirements of the power load predicting accuracy becoming higher and higher, and the actual power load is also a complex nonlinear system limited by various uncertain factors. Given only considering the influence of a single model on the load forecasting, the predicting accuracy is absolutely not high under the comprehensive effects of multiple factors. Ensuring to make the electrical model satisfy the requirements, there is access to improving the accuracy of load predicting results through analysis of the relationship between load and multiple factors in power load forecasting. This paper combines the rough set theory with information fusion, firstly a decision table of attributes is established on the basis of historical datum, for the purpose of simplifying the attribute index in mining to obtain important information. Following step is to rank the importance of the factors influencing the load according to the degree of effect, with grouping these sorted factors into attributes combination and using the same kind of load forecasting method to predict each combination's own results, and finally all groups of the predicting results are integrated by fusion, where then final predicting result can be obtained. The results of the algorithmic example show that groups of predicting results integrated based on information fusion theory are better than the results got through any casual single attribute combination. And fusion results are a combined action of a variety of related factors, enhancing the favorable trend, where at the same time it has reduced the uncertainty brought by multiple factor comprehensive effect. Based on information fusion the predicting results are helpful to reduce the prediction error, which is feasible and effective. With the explosive growth on the amount of in today's information age, the wave of data is coming, fast and furious. The era of big proposes a new challenge for the development in electricity industry. With the advance of electricity industry, intelligence, automation and interaction will bring many datum casing electrical big generation. Due to the numerous index of power load forecasting, different goals of all kinds of power load forecasting, even with the same kind of theory, the forecast model to predict no matter from the form, content or effect also vary widely. The load in the medium and long-term prediction of power system is greatly influenced by economy, society and meteorology factors and other uncertainties, etc. How to extract the key factor from multiple factors and reduce the results' uncertainty arising from the comprehensive effect of multiple factors, and improving the precision has been becoming a serious problem to be solved. Aiming at these problems, the paper based on the literature (8) proposing medium-and long- term load forecasting based on partial least squares regression analysis, an more optimized and advanced method is put forward to improve accuracy of prediction. The rough set theory and information fusion are introduced into the model, which respectively advance pre-processing and optimize the integration of multiple sets of results after prediction, in order to reduce uncertainty caused by varieties factors affecting and improve accuracy of forecasting results. II. THE ROUGH SET THEORY In the era of big data, on account of the characteristics on grid volume, which is large amount, variety type, and more speed, the traditional attribute simplified methods have been unable to complete the pre-processing on electrical big data. To this end the paper proposes a method on power big simplified processing based on cloud computing technology. The rough set theory which offers a new way for mining, is a new mathematical tool to deal with uncertain and imprecise problems. In this paper, rough sets method is used in power load forecasting to analyze the dependence of load on each factor and the importance of various properties in condition attribute set. In the decision system R={U, A}, the rough set divides A(attribute) into two categories C and D, where C is condition attribute, D is decision attribute, and U is domain. The ternary collection R={U,C,D} is known as a decision-making system. An important application of rough set in the analysis is to find the dependence among attributes from a known decision system R={U,C,D}. The dependency is defined as follows.

Smart metering is a quite new topic that has grown in importance all over the world and it appears to be a remedy for rising prices of electricity. Forecasting electricity usage is an important task to provide intelligence to the smart gird. Accurate forecasting will enable a utility provider to plan the resources and also to take control actions to balance the electricity supply and demand. The customers will benefit from metering solutions through greater understanding of their own energy consumption and future projections, allowing them to better manage costs of their usage. In this proof of concept paper, our contribution is twofold: (1) we deal with short term electricity load forecasting for 24 hours ahead, not on the aggregate but on the individual household level what fits into the stream of Residential Power Load Forecasting (RPLF) methods; (2) we utilized a set of household behavioral data which significantly improved the forecasts accuracy.

Genomic selection (GS) uses genome-wide molecular marker data to predict the genetic value of selection candidates in breeding programs. In plant breeding, the ability to produce large numbers of progeny per cross allows GS to be conducted within each family. However, this approach requires phenotypes of lines from each cross before conducting GS. This will prolong the selection cycle and may result in lower gains per year than approaches that estimate marker-effects with multiple families from previous selection cycles. In this study, phenotypic selection (PS), conventional marker-assisted selection (MAS), and GS prediction accuracy were compared for 13 agronomic traits in a population of 374 winter wheat (Triticum aestivum L.) advanced-cycle breeding lines. A cross-validation approach that trained and validated prediction accuracy across years was used to evaluate effects of model selection, training population size, and marker density in the presence of genotype × environment interactions (G×E). The average prediction accuracies using GS were 28% greater than with MAS and were 95% as accurate as PS. For net merit, the average accuracy across six selection indices for GS was 14% greater than for PS. These results provide empirical evidence that multifamily GS could increase genetic gain per unit time and cost in plant breeding.

Cardiac arrhythmias reveal multiple morphologies in time-domain waveforms. Abnormal beats reflect the origin and the conduction path of the ectopic heart activation pulses, including supraventricular, junctional, and ventricular arrhythmias and conduction abnormalities. This paper proposes a method for automated screening of cardiac arrhythmias using the discrete fractional-order integration (DFOI) and the meta-learning-based intelligent classifier. The DFOI process with the specific fractional order is used to extract the QRS features with the finite computations. It can deal with the irregular time-varying signals. The meta-learning-based intelligent classifier is used to identify the abnormal classes, consisting of a primary multilayer network and several agent networks. Since abnormal QRS complexes are multi-waveforms such as ventricular premature contraction, the classifier needs to retrain with new training patterns for meeting new condition in clinical applications. Thus, this model possesses the learning-to-optimization capability for retraining generalized regression neural network using the particle swarm optimization algorithm. Using incremental new training patterns, each inducer is used to track the past learning experiences through several agent networks. This pattern scheme can gradually enhance the accuracy by refining the optimal parameters of each sub-estimator for pattern recognition. Using the arrhythmia database of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database, the proposed intelligent classifier demonstrated greater efficiency and promising results in average accuracy, positive predictivity, and true negative rate for recognizing electrocardiography signals.

New era has begun two decades ago in the most power sectors of the globe. As electricity itself shifted from being a commodity only to a competitive trading market instrument, forecasting of power load and prices started to be another important factor. With the introduction of liberal power markets, independent players like producers, operators, traders became an important factors of liberalized power markets. New era in this secotr also increased competition among companies and countries. Thus, as new players came into scene, electricity became to be a tradable product and similar to another commodities needs to account, forecast plan of electiricity brought new challenges. With its obstacles, new atmosphere of electiricity repormation brought benefits such as lower price to end users and more utilized energy systems among the countries. Different forecasting models have been developed in order to forsee future operations. Moreover, popular modelts from economics, such as game theories, cournot model, Bertrand model, nash equilibrium plays a big role in electricity price forecasting. Simulation modelts are another methods heavily used by producers, operators and power traders in market. Additionally, statistical models, such as moving averages, Root Mean Square Error, Mean Absolute Error, mean Absolute Percentage Error, Theil's inequality coefficient are frequesntly used to determine price movements of electiricity. As its broadly used in several different industries, Time Series models using historical information and adding updated information helps to model future movement of prices. This article discusses the several methods of price forecasting of electricity in liberal power markets as high volatility of the market raises a big risk for all participants. Forecasting models explains time series analysis and briefly discusses about autoregressive, moving average, autoregressive moving average, and seasonal autoregressive moving average models. Moreover, the article illustrates examples from electricity price and load forecasts and their comparisons with actual results from trades in Turkish electricity market.