Explore the vast range of titles available.

The transformation of the energy system towards volatile renewable generation, increases the need to manage decentralized flexibilities more efficiently. For this, precise forecasting of uncontrollable electrical load is key. Although there is an abundance of studies presenting innovative individual methods for load forecasting, comprehensive comparisons of popular methods are hard to come across.In this paper, eight methods for day-ahead forecasts of supermarket, school and residential electrical load on the level of individual buildings are compared. The compared algorithms came from machine learning and statistics and a median ensemble combining the individual forecasts was used.In our examination, nearly all the studied methods improved forecasting accuracy compared to the naïve seasonal benchmark approach. The forecast error could be reduced by up to 35% compared to the benchmark. From the individual methods, the neural networks achieved the best results for the school and supermarket buildings, whereas the k-nearest-neighbor regression had the lowest forecasting error for households. The median ensemble narrowly yielded a lower forecast error than all individual methods for the residential and school category and was only outperformed by a neural network for the supermarket data. However, this slight increase in performance came at the cost of a significantly increased computation time. Overall, identifying a single best method remains a challenge specific to the forecasting task.

In the energy-planning sector, the precise prediction of electrical load is a critical matter for the functional operation of power systems and the efficient management of markets. Numerous forecasting platforms have been proposed in the literature to tackle this issue. This paper introduces an effective framework, coded in Python, that can forecast future electrical load based on hourly or daily load inputs. The framework utilizes a recurrent neural network model, consisting of two simpleRNN layers and a dense layer, and adopts the Adam optimizer and tanh loss function during the training process. Depending on the size of the input dataset, the proposed system can handle both short-term and medium-term load-forecasting categories. The network was extensively tested using multiple datasets, and the results were found to be highly promising. All variations of the network were able to capture the underlying patterns and achieved a small test error in terms of root mean square error and mean absolute error. Notably, the proposed framework outperformed more complex neural networks, with a root mean square error of 0.033, indicating a high degree of accuracy in predicting future load, due to its ability to capture data patterns and trends.

The growing demand for consumer-end electrical load is driving the need for smarter management of power sector utilities. In today’s technologically advanced society, efficient energy usage is critical, leaving no room for waste. To prevent both electricity shortage and wastage, electrical load forecasting becomes the most convenient way out. However, the conventional and probabilistic methods are less adaptive to the acute, micro, and unusual changes in the demand trend. With the recent development of artificial intelligence (AI), machine learning (ML) has become the most popular choice due to its higher accuracy based on time-, demand-, and trend-based feature extractions. Thus, we propose an Extreme Gradient Boosting (XGBoost) regression-based model—PredXGBR-1, which employs short-term lag features to predict hourly load demand. The novelty of PredXGBR-1 lies in its focus on short-term lag autocorrelations to enhance adaptability to micro-trends and demand fluctuations. Validation across five datasets, representing electrical load in the eastern and western USA over a 20-year period, shows that PredXGBR-1 outperforms a long-term feature-based XGBoost model, PredXGBR-2, and state-of-the-art recurrent neural network (RNN) and long short-term memory (LSTM) models. Specifically, PredXGBR-1 achieves an mean absolute percentage error (MAPE) between 0.98 and 1.2% and an R2 value of 0.99, significantly surpassing PredXGBR-2’s R2 of 0.61 and delivering up to 86.8% improvement in MAPE compared to LSTM models. These results confirm the superior performance of PredXGBR-1 in accurately forecasting short-term load demand.

The article focuses on the findings of endurance tests on thrust bearings. In addition to the mechanical load (axial load: 10 ≤ C0/P ≤ 19, lubrication gap: 0.33 µm ≤ h0 ≤ 1.23 µm), these bearings are also exposed to electrical loads (voltage: 20 Vpp ≤ U0 ≤ 60 Vpp, frequency 5 kHz and 20 kHz), such as those generated by modern frequency converters. In a previous study, the focus was on the chemical change in the lubricant and the resulting wear particles. In contrast, this article focuses on the changes occurring in the metallic contact partners. Therefore, the changes in the surface topography are analysed using Abbott–Firestone curves. These findings show that tests with an additional electrical load lead to a significant reduction in roughness peaks. A correlation to acceleration measurements is performed. Moreover, it is shown that the electrical load possibly has an effect on the light load hardness. An increase in the occurring wear could not be detected during the test series. Also, a comparison with mechanical reference tests is made. The article finally provides an overview of different measurement values and their sensitivity to additional electrical loads in roller bearings.

Management and efficient operations in critical infrastructures such as smart grids take huge advantage of accurate power load forecasting, which, due to its non‐linear nature, remains a challenging task. Recently, deep learning has emerged in the machine learning field achieving impressive performance in a vast range of tasks, from image classification to machine translation. Applications of deep learning models to the electric load forecasting problem are gaining interest among researchers as well as the industry, but a comprehensive and sound comparison among different—also traditional—architectures is not yet available in the literature. This work aims at filling the gap by reviewing and experimentally evaluating four real world datasets on the most recent trends in electric load forecasting, by contrasting deep learning architectures on short‐term forecast (one‐day‐ahead prediction). Specifically, the focus is on feedforward and recurrent neural networks, sequence‐to‐sequence models and temporal convolutional neural networks along with architectural variants, which are known in the signal processing community but are novel to the load forecasting one.

Reliability study is required for all the industrial applications to understand the behavior and functionality of device with respect to technological, environmental and operational issues. This paper aim to study and analyzed the exiting contribution related to MEMS resonator in order to explore the reliability issues. It also explored the reliability related to packaging, designing and functioning of MEMS resonator. It summarized the analysis of Environmental effect, design parameters, intermolecular forces, varying electrical load and vibrations etc. An approach and methodology for testing and simulation of MEMS resonator in view of reliability analysis is presented.

The increasing deployment of variable renewable energy sources (VRES) is changing the source regime in the electrical energy sector. However, VRES feed-in from wind turbines and photovoltaic systems is dependent on the weather and only partially predictable. As a result, existing energy sector models must be re-evaluated and adjusted as necessary. In long-term forecast models, the expansion of VRES must be taken into account so that future local overloads can be identified and measures taken. This paper focuses on one input factor for electrical energy models: the electrical load. We compare two different types to describe this, namely vertical grid load and total load. For the total load, an approach for a spatially-resolved electrical load model is developed and applied at the municipal level in Germany. This model provides detailed information about the load at a quarterly-hour resolution across 11,268 German municipalities. In municipalities with concentrations of energy-intensive industry, high loads are expected, which our simulation reproduces with a good degree of accuracy. Our results also show that municipalities with energy-intensive industry have a higher simulated electric load than neighboring municipalities that do not host energy-intensive industries. The underlying data was extracted from publically accessible sources and therefore the methodology introduced is also applicable to other countries.

Currently, deep learning methods have become prevalent in the field of electrical load forecasting. These approaches have shown a great potential to map complex nonlinear feature interactions. However, many existing electrical load forecasting models based solely on deep learning suffer from various limitations including the inability to perceive and integrate multi-scale features, the absence of continuous information of electrical load series and capturing fine-grained and hidden temporal pattern of electrical load series. In order to address these issues, in this paper we propose an improved model based on neural ordinary differential equations (NODEs), which possesses the ability of adaptive fusion, multi-scale feature perception, and representation. This model strengthens the effective decomposition of multi-scale features with the NODE-series block and enhances the multi-scale feature extraction and fusion ability with the NODE-split block. The experimental results show that the proposed model outperforms five baseline models and three block ablation experiments prove the necessity of the blocks.

In deep drilling applications, such as those for geothermal energy, there are many challenges, such as those related to efficient operation of the drilling fluid (mud) pumping system. Legacy drilling rigs often use paired, parallel-connected independent-excitation direct-current (DC) motors for mud pumps, that are supplied by a single power converter. This configuration results in electrical power imbalance, thus reducing its efficiency. This paper investigates this power imbalance issue in such legacy DC mud pump drive systems and offers an innovative solution in the form of a closed-loop control system for electrical load balancing. The paper first analyzes the drilling fluid circulation and electrical drive layout to develop an analytical model that can be used for electrical load balancing and related energy efficiency improvements. Based on this analysis, a feedback control system (so-called “current mirror” control system) is designed to balance the electrical load (i.e., armature currents) of parallel-connected DC machines by adjusting the excitation current of one of the DC machines, thus mitigating the power imbalance of the electrical drive. The proposed control system effectiveness has been validated, first through simulations, followed by experimental testing on a deep drilling rig during commissioning and field tests. The results demonstrate the practical viability of the proposed “current mirror” control system that can effectively and rather quickly equalize the armature currents of both DC machines in a parallel-connected electrical drive, and thus balance both the electrical and mechanical load of individual DC machines under realistic operating conditions of the mud pump electrical drive.

Forecasting of load is essential for operating power systems. India recently witnessed one of the worst power crisis with the highest ever power demand of 207 GW on April 29, 2022. The demand in the month of May and June 2022 was estimated to reach 215 GW. The peak demand this year 2023, according to the electricity ministry, is predicted to be around 230 GW from April to June. The inability to meet certain fundamental issues as power can take a toll on any country’s economy. Proper prediction helps in proper decision making and planning. The main objective of this paper is to predict day ahead electrical load demand for Assam. Statistical and Machine Learning Algorithms has been studied. The study has been carried out using real-time data for the years 2016, 2017 and 2018. The paper presents a detailed analysis of the different hyper parameters of the deep learning models and their effect is seen on the learning efficiency. A novel stacked forecasting model is proposed using neural networks as base learners and CatBoost as the meta-learner. The performance of the proposed model has been evaluated and compared with individual models in terms of training time and accuracy using different error metrics namely MAE, MSE, RMSE, MAPE and R 2 score. A comparison of the proposed prediction model with the prediction models available in literature has been presented. The conclusion states that both the statistical and machine learning algorithms used in this study act as useful tools for daily load forecasting with considerable accuracy; yet machine learning algorithm outperforms the statistical methods. The entire work has been done in Google Colaboratory using Python as the programming language.