Improved Giza pyramids construction algorithm for Modify the deep neural network-based method for energy demand forecasting

Neural network based optimization approach for energy demand prediction in smart grid

ARIMA forecasting of primary energy demand by fuel in Turkey

Throughout the history of the oil and gas industry, forecasts have been made of energy supply, future rates of production, energy demand and of oil prices. These forecasts are used for a wide variety of purposes including the oil industry itself, financial institutions, public policy planners, nations, and groups of nations (OPEC). Most forecasts are incorrect after only a few years, but they are often updated without a fundamental under-standing of why the earlier predictions were in error. This leads to painful disruptions and redirections not only within the oil industry but also in public policy debates and decisions on a national and global scale. This paper reviews some of the more significant forecasts of energy supply, demand, and oil prices made in the last 25 years, and identifies the basic premises used and why they led to incorrect forecasts. Usually the premises have been too narrowly based. A broader basis is proposed, which includes continuing changes in technology, national goals, public attitudes and environmental concerns. Extrapolation of past trends is a poor basis for forecasts. Hence, a broader understanding of the changing world is essential and must be incorporated meaningfully into forecasts.

Accurate energy demand prediction is crucial for efficient grid management and resource optimization, particularly across multiple countries with varying consumption patterns. However, real-world energy demand data often contains outliers that can distort forecasting accuracy. This study evaluates the impact of five outlier detection techniques—Z-Score, density- based spatial clustering of applications with noise (DBSCAN), isolation forest (IF), local outlier factor (LOF), and one-class support vector machine (SVM)—on the performance of three time-series forecasting models: long short-term memory (LSTM) networks, convolutional neural network (CNN) Autoencoders, and LSTM with attention mechanisms. The models are tested using energy demand data from four European countries— Germany, France, Spain, and Italy—derived from real-time consumption records. A comparative analysis based on root mean squared error (RMSE) demonstrates that incorporating outlier detection significantly enhances model robustness, reducing forecasting errors caused by anomalous data. The findings emphasize the importance of selecting appropriate outlier detection strategies to improve the accuracy and reliability of energy demand forecasting. This research provides valuable insights into the trade-offs involved in outlier removal, with implications for policy and operational practices in energy management.

Energy is an indispensable material resource for human production and life. It is a powerful engine and an important guarantee for human survival, economic and social sustainable development and world change. The economy is developing rapidly, the demand for energy continues to grow, energy consumption has increased sharply in a short period, and the security of energy supply and demand has also shown a severe trend. Predicting energy demand is especially important. However, due to the many influencing factors and the lack of energy data, the energy demand prediction has great uncertainty in the prediction results. Because of the above problems, this paper proposes an energy big data demand prediction model based on a fuzzy rough set model. Firstly, according to the data, the factors affecting the energy demand are determined, and the fuzzy C-means clustering algorithm is used to discretize the data according to the characteristics of the fuzzy rough set. Then the decision table is established and the attribute importance is calculated, and then the neighborhood rough set is used for attribute reduction. Then extract the correlation rules to establish a prediction model. Compare the prediction model proposed in this paper with the existing gray prediction method and energy elasticity coefficient method. The results show that this method can more scientifically predict the changes in energy big data demand. Finally, based on the experimental results, the corresponding strategies for optimizing the energy structure are proposed to provide reference for the optimization and development of energy demand.

The article presents a method of energy demand forecasting by using thermodynamic analysis of processes in the energy consumption sphere. Energy demand of a branch is determined on the base of modeling the energy consumption of an individual process by its material and energy balances. It makes it possible to take into account improvement of existing processes, change of technologies and introduction of energy conservation measures when the specific energy consumption for the product is determined for short- and mid-term forecasting. It is suggested to apply forecasting of energy and exergy efficiencies of technologies by long-term forecasting of energy demand. The complete energy balance method and concepts of the chemical energy and exergy of feedstock, ideal and idealized analogues of real processes, minimum necessary and limiting energy and work consumption are used.

Introduction: Patients with non-ischemic DCM are at risk of life-threatening ventricular arrhythmias. Improved patient selection for ICD implantation is warranted. Deep neural networks (DNN) can discover complex ECG features without the need for hand-crafted feature extraction. This study aimed to distinguish patients at risk of arrhythmias and detect and visualize ECG characteristics that attribute to the DNN classification. Methods: We trained a DNN model on baseline raw ECG samples of adult patients with DCM for the composite outcome of sustained ventricular arrhythmia, (aborted) sudden cardiac death and appropriate ICD therapy in the University Medical Centre Utrecht. Gradient-Weighted Class Activation Mapping was used for visual interpretation of the network. DNN performance was validated both internally and in an external cohort from the Maastricht University Medical University Center. Results: 26.628 ECGs were used for pre-training the network. In total, 317 patients with DCM were included in the primary cohort with a median age of 52 years (IQR 42 - 61), median LVEF of 25% (IQR 20-33), NYHA II and III (32% and 25%). 233 patients were ICD recipients. Subsequently 84 patients reached the outcome (median follow-up duration of 3.96 years (IQR 1.94 - 7.00)). The DNN focused on subtle but predictive differences in the terminal QRS-segment, the T-wave, and the P-wave (figure). The AUC of the DNN was 0.70 in cross-validation. External validation was similar, with an AUC of 0.66. Conclusion: In this study we trained and validated a deep neural network for prediction of life-threatening arrhythmic events. Even though the discriminatory changes on ECG segments were very subtle, the trained DNN was able to predict life-threatening events, focusing on the terminal QRS-segment, the T-wave, and the P-wave. Future studies are warranted to elucidate the identified ECG abnormalities and understand their electrophysiological substrates for LTA prediction in DCM.

Automated image classification is an essential task of the computer vision field. The tagging of images into a set of predefined groups is referred to as image classification. The implementation of computer vision to automate image classification would be beneficial because manual image evaluation and identification can be time-consuming, particularly when there are many images of different classes. Deep learning approaches are proven to overperform existing machine learning techniques in many fields in recent years, and computer vision is one of the most notable examples. The very deep neural network (VDCNN) is a powerful deep learning model for image classification, and this paper examines it briefly using MNIST handwritten digit dataset. This dataset is used to prove the efficacy of very deep neural networks over other deep learning models. The proposed study aims to comprehend the very deep neural network architecture used to accomplish a handwritten digit recognition task. The feasibility of the proposed model is evaluated using mean accuracy, validation accuracy, and standard deviation. The study results of the very deep neural network model are compared to a convolutional neural network and convolutional neural network with batch normalization. According to the results of the comparison study, very deep neural networks achieve high accuracy of 99.1% for a handwritten dataset. The outcome of the proposed work is used to interpret how well a very deep neural network performs when compared to the other two models of deep neural networks. This proposed architecture may be used to automate the classification of handwritten digits dataset.

FPGAs have been rapidly adopted for acceleration of Deep Neural Networks (DNNs) with improved latency and energy efficiency compared to CPU and GPU-based implementations. High-level synthesis (HLS) is an effective design flow for DNNs due to improved productivity, debugging, and design space exploration ability. However, optimizing large neural networks under resource constraints for FPGAs is still a key challenge. In this paper, we present a series of effective design techniques for implementing DNNs on FPGAs with high performance and energy efficiency. These include the use of configurable DNN IPs, performance and resource modeling, resource allocation across DNN layers, and DNN reduction and re-training. We showcase several design solutions including Long-term Recurrent Convolution Network (LRCN) for video captioning, Inception module for FaceNet face recognition, as well as Long Short-Term Memory (LSTM) for sound recognition. These and other similar DNN solutions are ideal implementations to be deployed in vision or sound based IoT applications.

Sustainable energy systems are necessary to save the natural resources avoiding environmental impacts which would compromise the development of future generations. Delivering sustainable energy will require an increased efficiency of the generation process including the demand side. The architecture of the future energy supply can be characterized by a combination of conventional centralized power plants with an increasing number of distributed energy resources, including cogeneration and renewable energy systems. Thus efficient forecast tools are necessary predicting the energy demand for the operation and planning of power systems. The role of forecasting in deregulated energy markets is essential in key decision making, such as purchasing and generating electric power, load switching, and demand side management. This chapter describes the energy data analysis and the basics of the mathematical modeling of the energy demand. The forecast problem will be discussed in the context of energy management systems. Because of the large number of influence factors and their uncertainty it is impossible to build up an ‘exact’ physical model for the energy demand. Therefore the energy demand is calculated on the basis of statistical models describing the influence of climate factors and of operating conditions on the energy consumption. Additionally artificial intelligence tools are used. A large variety of mathematical methods and ideas have been used for energy demand forecasting (see Hahn et al., 2009, or Fischer, 2008). The quality of the demand forecast methods depends significantly on the availability of historical consumption data as well as on the knowledge about the main influence parameters on the energy consumption. These factors also determine the selection of the best suitable forecast tool. Generally there is no 'best' method. Therefore it is very important to proof the available energy data basis and the exact conditions for the application of the tool. Within this chapter the algorithm of the model building process will be discussed including the energy data treatment and the selection of suitable forecast methods. The modeling results will be interpreted by statistical tests. The focus of the investigation lies in the application of regression methods and of neural networks for the forecast of the power and heat demand for cogeneration systems. It will be shown that similar methods can be applied to both forecast tasks. The application of the described methods will be demonstrated by the heat and power demand forecast for a real district heating system containing different cogeneration units.

Energy has been one of the most important topics of political and social discussion in recent decades. A significant proportion of the country’s revenues is derived from energy resources, making it one of the most important and strategic macro policy and sustainable development areas. Energy demand modeling is one of the essential strategies for better managing the energy sector and developing appropriate policies to increase productivity. With the increasing global demand for energy, it is necessary to develop intelligent forecasting methods and algorithms. Different economic and non-economic indicators can be used to estimate the energy demand, including linear and non-linear statistical methods, mathematics, and simulation models. This non-linear relationship between these indicators and energy demand has led researchers to search for intelligent solutions, such as artificial neural networks for non-linear modeling and prediction. The purpose of this study was to use a deep neural network with fuzzy wavelets to predict energy demand in Iran. For the training of the presented components, a hybrid training method incorporating both an inline PSO and a gradient-based algorithm is presented. The provided technique predicts energy consumption in Tehran, Mashhad, Ahvaz, and Urmia from 2010 to 2021. This study shows that the presented method provides high-performance prediction at a lower level of complexity.

Price prognostication has become progressively relevant to producers and shoppers within the new competitive wattage markets. Both for spot markets and long term contractors, value forecasts square measure necessary to develop bidding ways. In this paper, Genetic Algorithm based Neural network (GANN) approach is used to forecast short term hourly electricity price and the results are compared with Aritificial Neural Network(ANN). The recommended method is studied on the PJM electricity market. The results achieved through the simulation illustrates that the proposed model offers exact and improved results.

Deep neural networks (DNNs) are tremendously applied in artificial intelligence field. While the performance of DNNs is continuously improved by more complicated and deeper structures, the feasibility of deployment on embedded system remains as a critical problem. Neuromorphic system designs based on resistive random-access memory (ReRAM) provide an opportunity for power-efficient DNN employment. However, it encounters the challenge of limited programming resolution. A quantized training method is proposed in this paper to enhance the performance of neuromorphic systems based on ReRAM. Different from previous methods in which a dedicated regularization term is used in loss function to constrain parameter distribution, our quantized training method deals with training and quantization at the same time to alleviate the impact of limited parameter precision. Models with discrete parameters obtained after training can be directly mapped onto ReRAM devices. We implement experiments on image recognition tasks using multi-layer perceptron (MLP) and convolution neural network (CNN). The results verify that the quantized training method can approximate the accuracy of full-precision training, e.g., a two-layer MLP based on binary ReRAM only decreases the classification accuracy by 0.25% for MNIST dataset. In addition, we carefully investigate and present the importance of layer size under the ReRAM's low programming resolution, the different parameter resolution demands for convolution layer and fully connected layer, and system robustness to ReRAM variations after quantized training. The codes are available at https://github.com/qingyangqing/quantized-rram-net.

Forecasting energy demand in China and India: Using single-linear, hybrid-linear, and non-linear time series forecast techniques

Gait recognition is a noncontact biometric procedure that determines the identity or health status of a person by analyzing his or her walking posture and habits, including skeletal and joint movements. The most remarkable feature of this method is the possibility of conducting recognition without demanding much cooperation from participants. Therefore, this recognition technique has attracted much attention from scholars. Additionally, because of the rapid development of graphics processing unit technology, related hardware and computation performance, the applications of deep-learning technology are considerably enhanced. The objective of this study was to apply a deep neural network (DNN), which employs deep-learning technology, to achieve gait-based automatic pedestrian detection and recognition. In contrast to using wearable devices to precisely capture skeletal and joint movements, pedestrian color-image sequences were used as input in this study. Subsequently, a pretraining convolutional neural network (CNN) was employed to capture pedestrian location and extract pedestrian dense optical flow to serve as concrete low-level feature inputs. Then, a finely-tuned DNN based on the wide residual network was employed to extract high-level abstract features. In addition, to overcome the difficulty of obtaining local temporal features by using a 2D CNN, part of the 3D convolutional structure was introduced into the CNN. This design enabled use of limited memory to acquire more effective features and enhance the DNN performance. The experimental results show that the proposed method has exceptional performance for pedestrian detection and recognition.