Fig 9 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
It is important to achieve an efficient home energy management system (HEMS) because of its role in promoting energy saving and emission reduction for end-users. Two critical issues in an efficient HEMS are identification of user behavior and energy management strategy. However, current HEMS methods usually assume perfect knowledge of user behavior...
Context in source publication
Context 1
... prove its superior performance, it is also compared with the load disaggregation with attention model (LDWA) [8], which is a more advanced model built on SGN using attention technique. Figure 9 shows the behavior correlation graph of the 12 households obtained when the experiments are performed on the latest data. The thicker edges in the graph represent the greater weights. ...
Similar publications
The widespread adoption of electric vehicles (EVs) is crucial for reducing carbon emissions and combating
climate change. However, the efficiency of EV battery charging systems remains a critical challenge, with issues such
as long charging times, energy inefficiency, and battery degradation. This paper explores the application of artificial
int...
![Fig. 1. ARES energy storage shuttle train [5]](publication/376941555/figure/fig1/AS:11431281214914703@1703858617273/ARES-energy-storage-shuttle-train-5_Q320.jpg)
![Fig. 2. Optimization of timetables [55]](publication/376941555/figure/fig2/AS:11431281214914704@1703858617403/Optimization-of-timetables-55_Q320.jpg)
The article focuses on the problem of energy intensity in rail vehicles and analyzes current technologies aimed at reducing it. The author discusses innovations and strategies aimed at increasing energy efficiency in rail transportation. He also outlines the challenges of reducing energy consumption in this sector and future development prospects....
Smart street lighting system is one of the technologies that support green environmental related works. Thanks to the technology advancement, this branch of street lighting can benefit from the implementation of new solutions that will help organizations around the word to better manage the electricity consumption and develop a strong smart city. I...
The growth of the Internet of Things (IoT) has brought about the need for effi-cient energy management in buildings. This challenge has led to the development of various energy management systems that utilize different approaches. In this article, a fuzzy logic-based approach is proposed for energy management in IoT-enabled buildings. The system ut...
The requirement for integration of power plants due to the cyclical rise in electrical energy consumption is due to fluctuating load demand with the current grid systems. This integration necessitates effective allocating loads to the power plants for a minimum grid-tied transmission line cost while meeting network constraints. In this paper, we fo...
Citations
... As machine learning models get better at predicting load patterns, microgrid performance and efficiency will only improveespecially as microgrids start to take the form of electric vehicle charging stations. Several models (i.e., CNN, [4], k-NN [10], RNN, SVM [10]) and ANN's ( [14]) have been demonstrated to improve load optimization for microgrid stations.The integration of machine learning models to microgrid operations can pave the way towards sustainable, energy-efficient practices. With the power of making data-driven decisions, microgrid operators can lower energy wastage and have better resource management while giving a seamless experience to the end user. ...
... As machine learning models get better at predicting load patterns, microgrid performance and efficiency will only improveespecially as microgrids start to take the form of electric vehicle charging stations. Several models (i.e., CNN, [4], k-NN [10], RNN, SVM [10]) and ANN's ( [14]) have been demonstrated to improve load optimization for microgrid stations.The integration of machine learning models to microgrid operations can pave the way towards sustainable, energy-efficient practices. With the power of making data-driven decisions, microgrid operators can lower energy wastage and have better resource management while giving a seamless experience to the end user. ...
... On the contrary side, deadband manipulate entails establishing a threshold over which corrective movements are undertaken. These advanced techniques goal to beautify the adaptability of energy structures to the variety provided with the help of renewable resources [4]. Recent studies have examined the use of these sophisticated control techniques within the framework of incorporated wind and solar power infrastructure. ...
This study studies frequency manipulation approaches inside an integrated wind and solar energy machine, focused at the dynamic conduct of System A. Through complete simulation analyses making use of PSCAD/EMTDC software program, two superb manage strategies are evaluated: a notch clean out and deadband manipulate. Real wind velocity and photovoltaic output information from Pollachi wind and solarn plant, increase the realism of the simulations. Comparative evaluations, given in Tables five and six, show that the deadband manage mechanism exceeds the notch filter in suppressing frequency variations and decreasing High Voltage Direct Current (HVDC) line energy go with the flow oscillations. The deadband control, by means of actively inhibiting any frequency additions beyond a specified threshold, demonstrates increased flexibility and effectiveness. Results reveal that this strategy delivers a slightly enhanced overall performance in preserving machine frequency balance as compared to the notch clear out. These results contribute to the improvement of frequency management approaches in integrated renewable power architectures, providing vital insights for boosting balance and efficiency. The versatility and robust overall performance of the deadband manage mechanism showcase it as a potential alternative for actual-world programs, enabling dependable and resilient operation in strong structures including wind and sun
... It is not the only strategy for buying low and selling high. Making intelligent trading decisions involves a thorough awareness of market dynamics as well as acute insights, which may be difficult to determine from these criteria [3,4]. As a result of globalization and technological advancements, the number of assets available for trading on the stock market has expanded tremendously. ...
Making determinations in the ever-changing world of stock trading has frequently involved a complicated interaction between information and experience. With so many companies to choose from, investors frequently find it difficult to identify profitable options. The transformational potential of artificial intelligence (AI) to improve and streamline stock trading decisions is explored in this study. Support Vector Machines (SVM), Principal Component Analysis (PCA), and Neural Networks (NN) are three different approaches that are combined in this study to create a strong stock recommendation system that is compatible with investor strategies and risk tolerance. To improve computational efficiency, traders with similar tastes were grouped together using hierarchical clustering. The results showed promise. The NN model demonstrated a training accuracy of 94.8%, whilst the SVM model displayed an accuracy of 92.3%. The fact that PCA was able to capture all of the dataset's variation with just five main components demonstrated its superiority. Moreover, an evaluation of Value-at-Risk and Expected Returns for the suggested portfolios revealed the intrinsic trade-off between possible benefits and related hazards. This study essentially highlights the enormous potential of AI to transform stock trading by providing accurate recommendations that maximize profitability while blending in with investor profiles.
... 所提的框架包括三层两阶段， 如图 2 所示。 "三 层"即物理实体层、拓扑映射层及智能体交互层； "两阶段"即离线训练阶段、在线应用阶段。两阶 段详细阐述了三层之间的交互关系。下面分别对框 架中的内容进行详细介绍。 "物理实体层"即某工业园区型 IES，其具有 高能耗、多能互补、热电联供、安全可靠的特点，是 推进能源转型和可持续发展的重要手段之一 [24][25][26] ，如 图 2 中第一层所示； "物理实体层"将 IES 真实系统 映射为有权无向拓扑图 [27][28] ...
With the dual-carbon goals, the intensified coupling of heterogeneous energy sources is driving integrated energy system (IES) topology to evolve towards greater complexity and flexibility. However, the existing optimal scheduling methods do not sufficiently consider the knowledge of non-European network topology and its heterogeneous power flow constraints. To address this issue, this paper proposes an optimal dispatch method based on graph reinforcement learning. First, by guaranteeing diverse node states, the heterogeneous energy network topology connections are converted into network graph models using graph theory. Second, a state-action-reward framework based on real graph mapping is established, and the graph reinforcement learning method is employed to learn the non-Euclidean knowledge and heterogeneous flow constraints brought by the graph model, thus achieving safe and optimal scheduling of IES. Finally, the real data of an industrial park is used for simulation verification. Compared with the traditional method, the proposed method effectively alleviates the node voltage over-limit problem. The results indicate that the proposed method can achieve optimal dispatch of IES while considering the actual topology operation state information and heterogeneous flow safety.
... It is not the only strategy for buying low and selling high. Making intelligent trading decisions involves a thorough awareness of market dynamics as well as acute insights, which may be difficult to determine from these criteria [3,4]. As a result of globalization and technological advancements, the number of assets available for trading on the stock market has expanded tremendously. ...
Making determinations in the ever-changing world of stock trading has frequently involved a complicated interaction between information and experience. With so many companies to choose from, investors frequently find it difficult to identify profitable options. The transformational potential of artificial intelligence (AI) to improve and streamline stock trading decisions is explored in this study. Support Vector Machines (SVM), Principal Component Analysis (PCA), and Neural Networks (NN) are three different approaches that are combined in this study to create a strong stock recommendation system that is compatible with investor strategies and risk tolerance. To improve computational efficiency, traders with similar tastes were grouped together using hierarchical clustering. The results showed promise. The NN model demonstrated a training accuracy of 94.8%, whilst the SVM model displayed an accuracy of 92.3%. The fact that PCA was able to capture all of the dataset's variation with just five main components demonstrated its superiority. Moreover, an evaluation of Value-at-Risk and Expected Returns for the suggested portfolios revealed the intrinsic trade-off between possible benefits and related hazards. This study essentially highlights the enormous potential of AI to transform stock trading by providing accurate recommendations that maximize profitability while blending in with investor profiles.
