A hybrid approach for energy management systems in grid tied microgrids using Kepler optimization algorithm and motif-based heterogeneous graph attention network

In this paper, we propose an autonomic management framework (ASGrid) to address the requirements of emerging large-scale applications in hybrid grid and sensor network systems. To the best of our knowledge, we are the first who proposed the autonomic sensor grid system concept in a holistic manner targeted at non-trivial large applications. To bridge the gap between the physical world and the digital world and facilitate information analysis and decision making, ASGrid is designed to smooth the integration of sensor networks and grid systems and efficiently use both on demand. Under the blueprint of ASGrid, we present several building blocks that fulfill the following major features: (1) Self-configuration through content-based aggregation and associative rendezvous mechanisms; (2) Self-optimization through utility-based sensor selection and model-driven hierarchical sensing task scheduling; (3) Self-protection through ActiveKey dynamic key management and S3Trust trust management mechanisms. Experimental and simulation results on these aspects are presented.

Network embedding (graph embedding) has become the focus of studying graph structure in recent years. In addition to the research on homogeneous networks and heterogeneous networks, there are also some methods to attempt to solve the problem of dynamic network embedding. However, in dynamic networks, there is no research method specifically for heterogeneous networks. Therefore, this paper proposes a heterogeneous dynamic graph attention network (HDGAN), which attempts to use the attention mechanism to take the heterogeneity and dynamics of the network into account at the same time, so as to better learn network embedding. Our method is based on three levels of attention, namely structural-level attention, semantic-level attention and time-level attention. Structural-level attention pays attention to the network structure itself, and obtains the representation of structural-level nodes by learning the attention coefficients of neighbor nodes. Semantic-level attention integrates semantic information into the representation of nodes by learning the optimal weighted combination of different meta-paths. Time-level attention is based on the time decay effect, and the time feature is introduced into the node representation by neighborhood formation sequence. Through the above three levels of attention mechanism, the final network embedding can be obtained.Through experiments on two real-world heterogeneous dynamic networks, our models have the best results, proving the effectiveness of the HDGAN model.

Since ten years, the Grid systems are hot research topics. Recently, the Grid systems open towards the management of heterogeneous and distributed data on a large-scale environment. The Grid data management raises new problems and presents real challenges: (i) resource discovery and allocation, (ii) query processing and optimization, (iii) monitoring services, (iv) replication and caching, (v) cost models, (vi) autonomic data management, and (vii) security. The main characteristics offered by these systems are: large scale (e.g. high numbers of data sources, and computing resources) and dynamicity of nodes (unstable system). The synergy and convergence of interests between Grid systems and agent systems have been clearly pointed out. To address some of the above problems, a complementary approach (with respect to web services and P2P techniques) based on mobile agents deserves to be explored. In this talk, we draw up a synthetic state of the art of using mobile agents to solve some fundamental problems of data management in grid systems (e.g. resource discovery and allocation, distributed query and optimization, monitoring services for query optimization, cost models). We point out the advantages of mobile agents and how they can help for decentralized control, and scaling.

A relation-aware heterogeneous graph convolutional network for relationship prediction

Social media has developed rapidly because of its easy spread and access characteristics, but it provides a platform for the spread of rumors. Recent rumor detection methods generally seek clues from the rich graphical structure representation in the social context. However, they often ignore the interactive information generated during the spread of rumors, which would lose some inherent structural features. In this paper, we propose a Heterogeneous Graph Attention Network with Bi-directional information propagation mechanism for rumor detection. We establish a heterogeneous graph to represent a social network for modeling users and tweets and the interaction between them. We explore a bi-directional information propagation mechanism to simulate the spreading mode of rumors in the heterogeneous social network, in which the structural features scattered in the graph are captured by modeling the spreading process of rumors and aggregating information from neighboring nodes. We also use the graph attention network to encode heterogeneous graphs and extract the features of users and tweets to perform detection. Our experimental results on three representative datasets have demonstrated our method has better detection performance compared with other methods.

The cross-lingual text classification task remains a long-standing challenge that aims to train a classifier on high-resource source languages and apply it to classify texts in low-resource target languages, bridging linguistic gaps while maintaining accuracy. Most existing methods achieve exceptional performance by relying on multilingual pretrained language models to transfer knowledge across languages. However, little attention has been paid to factors beyond semantic similarity, which leads to the degradation of classification performance in the target languages. This study proposes a novel framework, a heterogeneous graph neural network with multi-view contrastive learning for cross-lingual text classification, which integrates a heterogeneous graph architecture with multi-view contrastive learning for the cross-lingual text classification task. This study constructs a heterogeneous graph to capture both syntactic and semantic knowledge by connecting document and word nodes using different types of edges, including Part-of-Speech tagging, dependency, similarity, and translation edges. A Graph Attention Network is applied to aggregate information from neighboring nodes. Furthermore, this study devises a multi-view contrastive learning strategy to enhance model performance by pulling positive examples closer together and pushing negative examples further apart. Extensive experiments show that the framework outperforms the previous state-of-the-art model, achieving improvements of 2.20% in accuracy and 1.96% in F1-score on the XGLUE and Amazon Review datasets, respectively. These findings demonstrate that the proposed model makes a positive impact on the cross-lingual text classification task overall.

Dynamic heterogeneous graph representation learning with neighborhood type modeling

Exploring the potential long noncoding RNA (lncRNA)-disease associations (LDAs) plays a critical role for understanding disease etiology and pathogenesis. Given the high cost of biological experiments, developing a computational method is a practical necessity to effectively accelerate experimental screening process of candidate LDAs. However, under the high sparsity of LDA dataset, many computational models hardly exploit enough knowledge to learn comprehensive patterns of node representations. Moreover, although the metapath-based GNN has been recently introduced into LDA prediction, it discards intermediate nodes along the meta-path and results in information loss. This paper presents a new multi-view contrastive heterogeneous graph attention network (GAT) for lncRNA-disease association prediction, MCHNLDA for brevity. Specifically, MCHNLDA firstly leverages rich biological data sources of lncRNA, gene and disease to construct two-view graphs, feature structural graph of feature schema view and lncRNA-gene-disease heterogeneous graph of network topology view. Then, we design a cross-contrastive learning task to collaboratively guide graph embeddings of the two views without relying on any labels. In this way, we can pull closer the nodes of similar features and network topology, and push other nodes away. Furthermore, we propose a heterogeneous contextual GAT, where long short-term memory network is incorporated into attention mechanism to effectively capture sequential structure information along the meta-path. Extensive experimental comparisons against several state-of-the-art methods show the effectiveness of proposed framework.The code and data of proposed framework is freely available athttps://github.com/zhaoxs686/MCHNLDA.

Building up grid-connected Hybrid Renewable Energy Systems (HRES) is one of the major challenges of developing countries. This relies on the feasibility study and moreover on the optimization of the system built. This paper aims to provide a good framework for Energy Management Systems (EMS) strategies. It consists of PV/Battery/loads connected to the power grid. Hence, the Hybrid Micro Grid System (HMGS) obtained is subject to meteorological uncertainties due to shadowing of the solar panels. Two approaches have been applied in this work: heuristic method using State Machine Logic (State Flow Method) and Linear Programming. These methods have been implemented using MATLAB R2018a. A thorough discussion describes the results of the simulations using both methods for two meteorological conditions: clear and cloudy periods. Four scenarios are presented in accordance to the specifications above-mentioned. A real-time analysis is performed for a specific case study on a daily basis.

Micro grid is an epitome of a macro grid but works in low voltage comprising of various small-distributed energy resources (DERs), energy storage devices, and controllable loads being interfaced through fast acting power electronic devices. Combined heat and power (CHP) produced by DERs are utilized in the local market where Micro Grid operates either in island mode or in grid-connected mode. The CHP mode of operation makes the Micro Grid most efficient and economic. Like deregulation regime in Micro Grid market, multi agent generator providers may be considered to make the Micro Grid market competitive. The reason for competitive electricity market is to serve the consumers at a reduced price. The main purpose of this paper is to analyze and propose the pricing mechanism for Micro Grid energy in the competitive electricity market. Central controller of the Micro Grid (μcc) is the main brain behind all energy management system (EMS) activities, which includes participation in the bidding to settle marketclearing price (MCP). Two important market settlement techniques - Day-ahead and Real-time - have been discussed briefly in this paper. Uniform and Pay-as-bid pricing rules have been discussed separately for electricity pricing fixation in the context of Micro Grid. In this paper marketing strategies of some of the renewable DERs - mainly Photovoltaic (PV) and wind generator - have been considered. Wind power is now a potential candidate in non-conventional power generation family. Power available from wind and PV system cost high and is of intermittent in nature. Participation of these two renewable DERs along with Micro turbine, Diesel generator, fuel cells etc. in the bidding for market clearing price (MCP) make the market complex. This paper gives a brief guideline for marketing of PV and wind power. Consumers in the Micro Grid system are categorized as shed-able and non-shed-able according to their priority. How these loads affect demand curve have also been discussed. This paper presents a case study on price determination based on demand and supply side bidding strategies. The impacts of congestion management, market power, carbon taxation, price volatility, etc. on pricing have also been discussed in the context of Micro Grid.

Job mobility prediction is an emerging research topic that can benefit both organizations and talents in various ways, such as job recommendation, talent recruitment, and career planning. Nevertheless, most existing studies only focus on modeling the individual-level career trajectories of talents, while the impact of macro-level job transition relationships (e.g., talent flow among companies and job positions) has been largely neglected. To this end, in this paper we propose an enhanced approach to job mobility prediction based on a heterogeneous company-position network constructed from the massive career trajectory data. Specifically, we design an Attentive heterogeneous graph embedding for sequential prediction (Ahead) framework to predict the next career move of talents, which contains two components, namely an attentive heterogeneous graph embedding (AHGN) model and a Dual-GRU model for career path mining. In particular, the AHGN model is used to learn the comprehensive representation for company and position on the heterogeneous network, in which two kinds of aggregators are employed to aggregate the information from external and internal neighbors for a node. Afterwards, a novel type-attention mechanism is designed to automatically fuse the information of the two aggregators for updating node representations. Moreover, the Dual-GRU model is devised to model the parallel sequences that appear in pair, which can be used to capture the sequential interactive information between companies and positions. Finally, we conduct extensive experiments on a real-world dataset for evaluating our Ahead framework. The experimental results clearly validate the effectiveness of our approach compared with the state-of-the-art baselines in terms of job mobility prediction.

Detecting collusive spammers with heterogeneous graph attention network

HGHAN: Hacker group identification based on heterogeneous graph attention network

Real-world graphs or networks are usually heterogeneous, involving multiple types of nodes and relationships. Heterogeneous graph neural networks (HGNNs) can effectively handle these diverse nodes and edges, capturing heterogeneous information within the graph, thus exhibiting outstanding performance. However, most methods of HGNNs usually involve complex structural designs, leading to problems such as high memory usage, long inference time, and extensive consumption of computing resources. These limitations pose certain challenges for the practical application of HGNNs, especially for resource-constrained devices. To mitigate this issue, we propose the Spiking Heterogeneous Graph Attention Networks (SpikingHAN), which incorporates the brain-inspired and energy-saving properties of Spiking Neural Networks (SNNs) into heterogeneous graph learning to reduce the computing cost without compromising the performance. Specifically, SpikingHAN aggregates metapath-based neighbor information using a single-layer graph convolution with shared parameters. It then employs a semantic-level attention mechanism to capture the importance of different meta-paths and performs semantic aggregation. Finally, it encodes the heterogeneous information into a spike sequence through SNNs, simulating bioinformatic processing to derive a binarized 1-bit representation of the heterogeneous graph. Comprehensive experimental results from three real-world heterogeneous graph datasets show that SpikingHAN delivers competitive node classification performance. It achieves this with fewer parameters, quicker inference, reduced memory usage, and lower energy consumption.

Aiming at the transmission of heterogeneous data in heterogeneous networks, a topology optimization algorithm of heterogeneous wireless sensor networks based on local tree reconstruction is proposed, which can achieve better data transmission in the heterogeneous networks. First, the algorithm divides the nodes of the network into different layers by their hops and chooses different numbers of nodes as relay nodes in different layers. Second, the nodes are set with different initial energies in different layers. Because the packets of different nodes have different sizes, we adopt the corresponding data aggregation coefficients according to the actual data requirements of the network in data transmission. Finally, the lifetime of the network is prolonged by real-time updating of the topology of the tree during the data transmission. The simulations indicate that after the aforementioned three steps, the proposed algorithm prolongs the lifetime of the heterogeneous networks and improves the nodes utilization effectively.