Cluster Operator Research Articles

Distributed Unmanned Aerial Vehicle Cluster Testing Method Based on Deep Reinforcement Learning

In the process of the collaborative work of Unmanned Aerial Vehicle (UAV) clusters, the cluster communication node test is often carried out by a single-node test, which leads to poor topology and robustness of the overall network system, an imbalanced communication network load, and high complexity of the communication test, which seriously affects the diversified needs of current users and the efficiency of large-scale task processing. To solve this problem, a distributed method for UAV cluster testing, called UTDR (distributed UAV cluster Testing method by using Deep Reinforcement learning), based on the Deep Deterministic Policy Gradient (DDPG) is proposed in this work. The system management node is used to monitor the status of the UAV testing task execution node and bandwidth resources. By taking advantage of the method of continuous interaction between the agent and the environment, the future state of the node after processing the current task to be assigned is predicted and evaluated from the perspective of interpretability, so as to achieve the effectiveness and stability of the UAV cluster testing task collaborative execution. The experimental results show that our proposed method can ensure the stable operation of the UAV cluster, accurately predict the future state, and reduce the load degree and bandwidth resource consumption of the large-scale test task network system.

Optimal configuration of shared energy storage system in microgrid cluster: Economic analysis and planning for hybrid self-built and leased modes

Applying shared energy storage within a microgrid cluster offers innovative insights for enhancing energy management efficiency. This investigation tackles the financial constraint investors face with a limited budget for shared energy storage configuration, conducting a thorough economic analysis of a hybrid model that integrates self-built and leased energy storage modes. It also underscores the significance of energy sharing among microgrids. Departing from conventional single-mode planning approaches, this study explores the synergistic benefits of the self-built and leased modes, focusing on their distinct advantages regarding upfront investment costs and lifecycle returns. Specifically, a step-cost decrement model is established, accurately depicting the economies of scale characteristics of the self-built energy storage mode. Based on this, a shared energy storage system model that integrates self-built and leased modes is proposed. Subsequently, a robust optimization model is formulated for configuring shared energy storage within a microgrid cluster, incorporating considerations of inter-microgrid energy sharing, seasonal variations in net load curves, and associated volatility. The column-and-constraint generation algorithm and strong duality theory are employed to solve the constructed model in two stages. Six distinct scenarios are designed to validate the effectiveness of the method and model proposed in this paper while also assessing the impact of investment budget and uncertain parameters on shared energy storage planning for a microgrid cluster. The results show that the proposed shared energy storage planning model significantly improves the economics of energy storage investment and system operation, even under budgetary constraints. It also reduces the dependency of a microgrid cluster on both shared energy storage and distribution grid when compared to models relying solely on self-built or leased mode. This study can guide investors and microgrid cluster operators in planning and implementing shared energy storage.

An "ultimate" coupled cluster method based entirely on T2.

Electronic structure methods built around double-electron excitations have a rich history in quantum chemistry. However, it seems to be the case that such methods are only suitable in particular situations and are not naturally equipped to simultaneously handle the variety of electron correlations that might be present in chemical systems. To this end, the current work seeks a computationally efficient, low-rank, "ultimate" coupled cluster method based exclusively on T2 and its products that can effectively emulate more "complete" methods that explicitly consider higher-rank, T2m, operators. We introduce a hierarchy of methods designed to systematically account for higher, even order cluster operators, such as T4, T6, …, T2m, by invoking tenets of the factorization theorem of many-body perturbation theory (MBPT) and expectation-value coupled cluster theory. It is shown that each member within this methodological hierarchy is defined such that both the wavefunction and energy are correct through some order in MBPT and can be extended up to arbitrarily high orders in T2. The efficacy of such approximations are determined by studying the potential energy surface of several closed and open-shell molecules. We find that the proposed hierarchy of augmented T2 methods essentially reduces to standard CCD for problems where dynamic electron correlations dominate but offer improvements in situations where non-dynamic and static correlations become relevant. A notable highlight of this work is that the cheapest methods in this hierarchy-which are correct through fifth-order in MBPT-consistently emulate the behavior of the O(N10) CCDQ method, yet only require a O(N6) algorithm by virtue of factorized intermediates.

Topology-aware fault diagnosis for microgrid clusters with diverse scenarios generated by digital twins

Microgrid clusters, characterized by their dynamically changing topologies and flexible operational modes ranging from grid-tied to autonomous functioning, present significant challenges for conventional protective measures. To address these complexities, this paper proposes a novel topology-aware fault diagnosis approach that integrates Message Passing Neural Networks (MPNNs) with a Graph-Lasso-based topology identification method. Our framework is designed to enhance the precision and adaptability of fault diagnosis in microgrid clusters, which are crucial for maintaining system stability. The proposed model demonstrates over 99% accuracy in fault localization and over 97% in fault type recognition, even under varying topological conditions and data loss scenarios. Through the application of digital twin technology, the framework not only improves the diagnostic capabilities but also supports the intelligent operation and maintenance of microgrid clusters, thereby contributing to the overall reliability and quality of their electrical systems.

Research on AUV Multi-Node Networking Communication Based on Underwater Electric Field CSMA/CA Channel.

To address the issues of high attenuation, weak reception signal, and channel blockage in the current electric field communication of underwater robots, research on autonomous underwater vehicle (AUV) multi-node networking communication based on underwater electric field Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) channel was conducted. This article, first through simulation, finds that the Optimized Link State Routing (OLSR) protocol has a smaller routing packet delay time and higher reliability compared to the Ad Hoc On-Demand Distance Vector (AODV) protocol on underwater electric field CSMA/CA channels. Then, a 2FSK underwater electric field communication system was established, and dynamic communication experiments were carried out between two AUV nodes. The experimental results showed that within a range of 0 to 3.5 m, this system can achieve underwater dynamic electric field communication with a bit error rate of 0 to 0.628%. Finally, to avoid channel blockage during underwater AUV multi-node communication, this article proposes a dynamic backoff method for AUV multi-node communication based on CSMA/CA. This system can achieve dynamic multi-node communication of underwater electric fields with an error rate ranging from 0 to 0.96%. The research results have engineering application prospects for underwater cluster operations.

Finite-order method to calculate approximate density matrices in the Fock-space multireference coupled cluster theory

An efficient approach to calculate approximate pure-state and transition reduced density matrices in the framework of the multireference relativistic Fock-space coupled cluster (FS CC) theory is proposed. The method is based on the effective operator formalism and consists of the direct substitution of the FS CC Ansatz for a wave operator into the effective operator expression with the subsequent truncation of expansion at the terms quadratic in cluster amplitudes. The final density matrix is defined by active-space density matrices of different ranks ‘dressed’ with contributions from cluster operators. The method gives a connected expression for pure-state density matrices, provided that the intermediate normalisation condition is fulfilled. Moreover, under some additional assumptions, the connectivity can also be ensured for calculated transition property matrix elements and natural transition spinors. The developed technique allows for fast and accurate calculations of one-particle reduced density matrices for a wide range of electronic states. A pilot application of the new technique to construct averaged atomic natural orbital (ANO) basis sets for fully relativistic electronic structure calculations is presented.

Triple Electron Attachments with a New Intermediate-Hamiltonian Fock-Space Coupled-Cluster Method.

The implementation of a new intermediate-Hamiltonian Fock-space coupled-cluster (IHFSCC) scheme for the (3,0) sector of the Fock space is reported. In this IHFSCC approach, the three-body contributions in the cluster operator S(3,0) corresponding to the (3,0) sector of the Fock space are considered, while S(1,0) and S(2,0) at the (1,0) and (2,0) level only include one- and two-body operators. By introducing a suitable partition of the wave operator, the intermediate Hamiltonian, which only depends on the two-body operator of S(1,0), is obtained. S(2,0) and S(3,0) are not required within this new IHFSCC scheme, and a large reference space can be possibly employed. The performance of this (3,0) IHFSCC method in calculating triple ionization potentials and excitation energies for atoms and cations with a ground p3 configuration as well as adiabatic excitation energies for some molecules is investigated. The effect of the number of active virtual orbitals and three different types of orbitals, i.e., reference orbitals, restricted open-shell Hartree-Fock orbitals (ROHF) of the target systems, and canonicalized ROHF orbitals, on IHFSCC results, is also studied. Our calculations indicate that reasonable results can be achieved with this (3,0) IHFSCC method when a minimal reference space is employed. Further increasing the number of active orbitals does not necessarily improve the results. In addition, the IHFSCC results using canonicalized ROHF orbitals generally agree well with reference values, and they are not very sensitive to the number of active orbitals compared with results using the reference orbitals. The new (3,0) IHFSCC method can be applied to open-shell systems with three unpaired electrons with reasonable accuracy at a relatively low computational cost.

EEG classification with limited data: A deep clustering approach

In this paper, we propose a novel training strategy designed to prevent deep neural networks from overfitting when trained on a very limited number of samples. This approach enables the use of very deep networks in applications like EEG classification, where data collection is challenging, leading to significant overfitting issues. To address this issue, we introduce a classification network that leverages a deep clustering operation in its latent space. The network utilizes a set of dictionary elements as auxiliary inputs and learns to guide each input sample toward one of the clusters, each derived from a dictionary element. This process facilitates the grouping of samples from the same class within the same region of the latent space, thereby reducing the risk of complex class boundaries and overfitting. Additionally, we introduce two probabilistic models within our clustering approach to mitigate outlier issues and address augmentation challenges commonly encountered with EEG signals. Experimental evaluations on two widely recognized databases, EEG-ImageNet and BCIIV2a, demonstrate the effectiveness and superiority of our method compared to state-of-the-art approaches, achieving 97.9% accuracy on EEG-ImageNet and 84.1% accuracy on BCIIV2a.

Heat Transfer Performance and Operation Scheme of the Deeply Buried Pipe Energy Pile Group

This paper describes a study on the heat transfer properties of the deeply buried pipeline energy pile group, which is an efficient and convenient geothermal development technology. Through in situ experiments and a simulation algorithm, the research investigated the heat transmission characteristics of the deeply buried pipe energy pile group and optimized different intermittent operation schemes. The findings suggest that prolonged operation of the pile cluster intensifies heat buildup within the pile foundation, thereby adversely affecting the system’s overall heat exchange efficiency. Employing an intermittent operating mode can alleviate this heat accumulation phenomenon, thereby promoting sustained heat exchange performance of the piles over time. To evaluate the comprehensive thermal interaction and energy efficiency ratio of the energy pile heat exchange system, various intermittent operation strategies were compared in the study. Among them, the intermittent operational scheme with a ratio of n = 5 was found to be optimal, with the total average heat transfer rate of the pile set only 0.51% lower than that of the continuous operational mode, but the overall energy efficiency ratio improved by 19.6%. The intermittent operational mode proposed in this study can achieve the goal of saving energy and efficiently extracting geothermal resources, providing theoretical guidance for the extraction and utilization of subsurface geothermal power by energy piles.

Impact of Gale Weather Events on Wind Power Generation

Abstract Due to the influence of global warming, extreme wind weather occurs frequently, especially in extreme weather such as typhoons and cold waves, problems such as wind turbine shutdown, cutting out, and sudden changes in power generation power will occur, which brings great challenges to wind power forecast and safe and stable operation of the power grid. At present, the research and analysis of strong wind weather mostly stay at the single fan level, and the causes of abnormal changes in wind power output are mostly analyzed from the physical level. However, with the large-scale access of wind power to the power grid, the impact of extreme weather on power grid operation is becoming more and more significant, and it is particularly important to study the impact of strong wind weather events on wind power cluster output. This paper summarizes various types of wind power generation weather events, then screens key meteorological factors affecting power generation under different wind weather conditions based on Gaussian search and grey correlation weighting, and finally analyzes the meteorological impact on the actual operation of wind farm stations and clusters under typhoons and cold waves respectively, aiming at the problem of huge deviations in wind power forecast caused by wind. The next research direction and suggestions are put forward.

Research on the Historical Remain of the Bombard of Chongqing Ontological Model from the Perspective of Digital Humanities

Based on the perspective of digital humanities, taking the example of the historical remain of the bombard of Chongqing, this research explores the possibilities of digital communication of the historical remain of the bombard of Chongqing through specific methodssuch as multi-source clustering, resource indexing, knowledge reorganization, and interactive operations. The semantic ontology model can achieve a multidimensional stereoscopic description of the historical remain of the bombard of Chongqing with heterogeneous data from multiple sources. This facilitates the in-depth integration of related resources of relic objects, designing an ontology model that aligns with the unique characteristics of Chongqing's red culture. The study also discusses the technical and expansion paths of the ontology model for war relics, aiming to provide insights and references for the integration of digital resources and the digital preservation and dissemination of the historical remain of the bombard. To achieve the preservation of Chinese historical and cultural heritage.

Comparison of Signal to Noise Ratio of Colored and Gray Scale Image in Clustered Condition from the Contours of the Images with the Help of Different Image Filtering Method

As we know the image can be processed with the help of different types of coding for example mat-lab. Here in this paper we are primarily focusing on some common filtering methodologies [5]related to image contour in clustered conditions. For filtering purpose in this paper we have used three different filtering technologies such as prewitt [3], sobel [3], canny [3] filtering. But on the other hand we have used both colored [1] and non-colored [3] images for clustering operations. Our main aim in this paper to show variations of signal to noise ratios for the colored and non-colored contour images with and without filtering. As per my request study the discussion of results very carefully to realize the deeper meaning of the journal [4].

Coordinated Operation Strategy for Equitable Aggregation in Virtual Power Plant Clusters with Electric Heat Demand Response Considered

To tackle the variability of distributed renewable energy (DRE) and the timing differences in load demand, this paper perfects the integrated layout of “source-load-storage” energy control in virtual power plants (VPPs). Introducing a comprehensive control approach for VPPs of varying ownerships, and encompassing load aggregators (LAs), a robust and cost-efficient operation strategy is proposed for VPP clusters. Initially, the influence of real-time electricity prices on cluster energy utilization is taken into account. Flexible shared electricity prices are formulated cluster-wide, based on the buying and selling data reported by each VPP, and are distributed equitably across the cluster. Following this, a flexible supply and demand response mechanism is established. With the goal of minimizing operational costs, this strategy responds to demand (DR) on the end-user side, instituting shifts and reductions in electricity and heat loads based on electricity and heat load forecasting data. On the supply side, optimization strategies are developed for gas turbines, residual heat boilers, and ground-source heat pumps to restrict power output, thus achieving economical and low-carbon cluster operations. Finally, the efficacy of the proposed optimization strategy is demonstrated through tackling numerous scenario comparisons. The results showcase that the proposed strategy diminishes operational costs and carbon emissions within the cluster by 11.7% and 5.29%, respectively, correlating to the unoptimized scenario.

Underwater Multi-Channel MAC with Cognitive Acoustics for Distributed Underwater Acoustic Networks.

The advancement of underwater cognitive acoustic network (UCAN) technology aims to improve spectral efficiency and ensure coexistence with the underwater ecosystem. As the demand for short-term underwater applications operated under distributed topologies, like autonomous underwater vehicle cluster operations, continues to grow, this paper presents Underwater Multi-channel Medium Access Control with Cognitive Acoustics (UMMAC-CA) as a suitable channel access protocol for distributed UCANs. UMMAC-CA operates on a per-frame basis, similar to the Multi-channel Medium Access Control with Cognitive Radios (MMAC-CR) designed for distributed cognitive radio networks, but with notable differences. It employs a pre-determined data transmission matrix to allow all nodes to access the channel without contention, thus reducing the channel access overhead. In addition, to mitigate the communication failures caused by randomly occurring interferers, UMMAC-CA allocates at least 50% of frame time for interferer sensing. This is possible because of the fixed data transmission scheduling, which allows other nodes to sense for interferers simultaneously while a specific node is transmitting data. Simulation results demonstrate that UMMAC-CA outperforms MMAC-CR across various metrics, including those of the sensing time rate, controlling time rate, and throughput. In addition, except for in the case where the data transmission time coefficient equals 1, the message overhead performance of UMMAC-CA is also superior to that of MMAC-CR. These results underscore the suitability of UMMAC-CA for use in challenging underwater applications requiring multi-channel cognitive communication within a distributed network architecture.

Community detection by influential nodes based on random walk distance

SummaryCommunity detection is a key feature that can be used to extract useful information from networks. In most studies, the same static algorithms are used on real‐time snapshots of the dynamic network. Such an action increases the calculations and the time taken for the clustering operation. The idea of community detection is based on the fact that communities are formed around a node that is more popular and influential. Therefore, in the proposed algorithm, first, several snapshots are received from the network, then for the first snapshot, the influence of each node is calculated using the influence function based on the random walk distance between nodes. Then by selecting k nodes with higher influence, network communities are formed and other nodes belong to the community with the most common edges. In the next step, the next snapshots will be received and then the communities will be updated. Then K nodes with higher influence are selected and their community is created if needed. The proposed method has been compared with state‐of‐the‐art algorithms, and the results show that proposed method has been able to have a suitable performance in the uniformity of communities and also the speed of community formation.

Delineating Source and Sink Zones of Trip Journeys in the Road Network Space

Source–sink zones refer to aggregated adjacent origins/destinations with homogeneous trip flow characteristics. Current relevant studies mostly detect source–sink zones based on outflow/inflow volumes without considering trip routes. Nevertheless, trip routes detail individuals’ journeys on road networks and give rise to relationships among human activities, road network structures, and land-use types. Therefore, this study developed a novel approach to delineate source–sink zones based on trip route aggregation on road networks. We first represented original trajectories using road segment sequences and applied the Latent Dirichlet Allocation (LDA) model to associate trajectories with route semantics. We then ran a hierarchical clustering operation to aggregate trajectories with similar route semantics. Finally, we adopted an adaptive multi-variable agglomeration strategy to associate the trajectory clusters with each traffic analysis zone to delineating source and sink zones, with a trajectory topic entropy defined as an indicator to analyze the dynamic impact between the road network and source–sink zones. We used taxi trajectories in Xiamen, China, to verify the effectiveness of the proposed method.

Polymorphic Clustering and Approximate Masking Framework for Fine-Grained Insect Image Classification

Insect diversity monitoring is crucial for biological pest control in agriculture and forestry. Modern monitoring of insect species relies heavily on fine-grained image classification models. Fine-grained image classification faces challenges such as small inter-class differences and large intra-class variances, which are even more pronounced in insect scenes where insect species often exhibit significant morphological differences across multiple life stages. To address these challenges, we introduce segmentation and clustering operations into the image classification task and design a novel network model training framework for fine-grained classification of insect images using multi-modality clustering and approximate mask methods, named PCAM-Frame. In the first stage of the framework, we adopt the Polymorphic Clustering Module, and segmentation and clustering operations are employed to distinguish various morphologies of insects at different life stages, allowing the model to differentiate between samples at different life stages during training. The second stage consists of a feature extraction network, called Basenet, which can be any mainstream network that performs well in fine-grained image classification tasks, aiming to provide pre-classification confidence for the next stage. In the third stage, we apply the Approximate Masking Module to mask the common attention regions of the most likely classes and continuously adjust the convergence direction of the model during training using a Deviation Loss function. We apply PCAM-Frame with multiple classification networks as the Basenet in the second stage and conduct extensive experiments on the Insecta dataset of iNaturalist 2017 and IP102 dataset, achieving improvements of 2.2% and 1.4%, respectively. Generalization experiments on other fine-grained image classification datasets such as CUB200-2011 and Stanford Dogs also demonstrate positive effects. These experiments validate the pertinence and effectiveness of our framework PCAM-Frame in fine-grained image classification tasks under complex conditions, particularly in insect scenes.

DCFH: A dynamic clustering approach based on fire hawk optimizer in flying ad hoc networks

In flying ad hoc networks (FANETs), unmanned aerial vehicles (UAVs) communicate with each other without any fixed infrastructure. Because of frequent topological changes, instability of wireless communication, three-dimensional movement of UAVs, and limited resources, especially energy, FANETs deal with many challenges, especially the instability of UAV swarms. One solution to address these problems is clustering because it maintains network performance and increases scalability. In this paper, a dynamic clustering scheme based on fire hawk optimizer (DCFH) is proposed for FANETs. In DCFH, each cluster head calculates the period of hello messages in its cluster based on its velocity. Then, a fire hawk optimizer (FHO)-based dynamic clustering operation is carried out to determine the role of each UAV (cluster head (CH) or cluster member (CM)) in the network. To calculate the fitness value of each fire hawk, a fitness function is suggested based on four elements, namely the balance of energy consumption, the number of isolated clusters, the distribution of CHs, and the neighbor degree. To improve cluster stability, each CH manages the movement of its CMs and adjusts it based on its movement in the network. In the last phase, DCFH defines a greedy routing process to determine the next-hop node based on a score, which consists of distance between CHs, energy, and buffer capacity. Finally, DCFH is simulated using the network simulator version 2 (NS2), and its performance is compared with three methods, including the mobility-based weighted cluster routing scheme (MWCRSF), the dynamic clustering mechanism (DCM), and the Grey wolf optimization (GWO)-based clustering protocol. The simulation results show that DCFH well manages the number of clusters in the network. It improves the cluster construction time (about 55.51%), cluster lifetime (approximately 11.13%), energy consumption (about 15.16%), network lifetime (about 2.6%), throughput (approximately 3.9%), packet delivery rate (about 0.61%), and delay (approximately 14.29%). However, its overhead is approximately 8.72% more than MWCRSF.

Circular economy ideas in the practice of industrial ecosystems in Russia

The arrival of the new phenomenon “industrial ecosystem” to the field of production organisation makes investigating it particularly relevant. The paper focuses on describing its essence, indispensable structural elements, as well as delves into the practical significance allowing for the trends in Russia’s technological and ecological development. Methodologically, the paper is based on the concepts of industrial revolution, circular and digital economies. Methods of desk research and systematisation are used. According to the findings, the concept “industrial ecosystem” appeared within industrial ecology and represents a kind of a business ecosystem. In Kleiner’s systems concept, this type of ecosystem is considered as a total of an industrial cluster, a platform, a network, and an incubator. Comparative analysis of various forms of production organisation allows identifying industrial cluster as the most appropriate basis of the ecosystem. It is proved that the digital platform, the communication and logistics network, and the business incubator (technology park) are important for ensuring efficient operation of an industrial cluster. The paper validates the treatment of industrial ecosystems as a transitional form between natural (biological) and non-natural (business) ecosystems. The goal orientation of industrial ecosystem is handling both socioeconomic and environmental problems due to setting up closed-loop industrial cycles. The paper presents an original scheme of an ecosystem taking into account the principles of circular economy: industrial enterprise – circular industrial cluster – industrial ecosystem.

Optimal Planning of User-side Scaled Distributed Generation Based on Stackelberg Game

BACKGROUND: User-side distributed generation represented by distributed photovoltaic and distributed wind turbine has shown an expansion trend of decentralized construction and disordered access, which is difficult to satisfy the demand for large-scale exploitation and sustainable development of distributed generation under the low-carbon transformation vision of the power system.
 OBJECTIVES: To address the interest conflict and operation security problems caused by scaled distributed generation accessing the distribution network, this paper proposes the optimal planning method of user-side scaled distributed generation based on the Stackelberg game.
 METHODS: Firstly, a cluster planning and operation mode of distributed generation is established. Then, a prediction method for planning behavior of user-side distributed generation is proposed in order to predict whether users will adopt the self-build mode or the leasing site mode for distributed generation. Finally, in order to reveal the game relationship between the distribution network operator and the users in the allocation of distributed generation resources, a bi-level planning model for scaled distributed generation is established based on the Stackelberg game.
 RESULTS: The simulation results show that the revenue of the distribution network operator under the gaming model increases by 10.15% and 16.88% compared to the models of all users self-build distributed generation and all users leasing distributed generation site, respectively, while at the same time, individual users also realize different degrees of revenue increase.
 CONCLUSION: The case analysis validates the effectiveness of the proposed method in guiding the rational and efficient planning of user-side distributed generation.