An Improved Jump Spider Optimization for Network Traffic Identification Feature Selection

The massive influx of traffic on the Internet has made the composition of web traffic increasingly complex.Traditional port-based or protocol-based network traffic identification methods are no longer suitable for today’s complex and changing networks.Recently,machine learning has beenwidely applied to network traffic recognition.Still,high-dimensional features and redundant data in network traffic can lead to slow convergence problems and low identification accuracy of network traffic recognition algorithms.Taking advantage of the faster optimizationseeking capability of the jumping spider optimization algorithm(JSOA),this paper proposes a jumping spider optimization algorithmthat incorporates the harris hawk optimization(HHO)and small hole imaging(HHJSOA).We use it in network traffic identification feature selection.First,the method incorporates the HHO escape energy factor and the hard siege strategy to forma newsearch strategy for HHJSOA.This location update strategy enhances the search range of the optimal solution of HHJSOA.We use small hole imaging to update the inferior individual.Next,the feature selection problem is coded to propose a jumping spiders individual coding scheme.Multiple iterations of the HHJSOA algorithmfind the optimal individual used as the selected feature for KNN classification.Finally,we validate the classification accuracy and performance of the HHJSOA algorithm using the UNSW-NB15 dataset and KDD99 dataset.Experimental results show that compared with other algorithms for the UNSW-NB15 dataset,the improvement is at least 0.0705,0.00147,and 1 on the accuracy,fitness value,and the number of features.In addition,compared with other feature selectionmethods for the same datasets,the proposed algorithmhas faster convergence,better merit-seeking,and robustness.Therefore,HHJSOAcan improve the classification accuracy and solve the problem that the network traffic recognition algorithm needs to be faster to converge and easily fall into local optimum due to high-dimensional features.

Data Center Traffic Scheduling Strategy for Minimization Congestion and Quality of Service Guaranteeing

According to Cisco’s Internet Report 2020 white paper,there will be 29.3 billion connected devices worldwide by 2023,up from 18.4 billion in 2018.5G connections will generate nearly three times more traffic than 4G connections.While bringing a boom to the network,it also presents unprecedented challenges in terms of flow forwarding decisions.The path assignment mechanism used in traditional traffic schedulingmethods tends to cause local network congestion caused by the concentration of elephant flows,resulting in unbalanced network load and degraded quality of service.Using the centralized control of software-defined networks,this study proposes a data center traffic scheduling strategy for minimization congestion and quality of service guaranteeing(MCQG).The ideal transmission path is selected for data flows while considering the network congestion rate and quality of service.Different traffic scheduling strategies are used according to the characteristics of different service types in data centers.Reroute scheduling for elephant flows that tend to cause local congestion.The path evaluation function is formed by the maximum link utilization on the path,the number of elephant flows and the time delay,and the fast merit-seeking capability of the sparrow search algorithm is used to find the path with the lowest actual link overhead as the rerouting path for the elephant flows.It is used to reduce the possibility of local network congestion occurrence.Equal cost multi-path(ECMP)protocols with faster response time are used to schedulemouse flows with shorter duration.Used to guarantee the quality of service of the network.To achieve isolated transmission of various types of data streams.The experimental results show that the proposed strategy has higher throughput,better network load balancing,and better robustness compared to ECMP under different traffic models.In addition,because it can fully utilize the resources in the network,MCQG also outperforms another traffic scheduling strategy that does rerouting for elephant flows(namely Hedera).Compared withECMPandHedera,MCQGimproves average throughput by 11.73%and 4.29%,and normalized total throughput by 6.74%and 2.64%,respectively;MCQG improves link utilization by 23.25%and 15.07%;in addition,the average round-trip delay and packet loss rate fluctuate significantly less than the two compared strategies.

Soil respiration response to precipitation reduction in a grassland and a Mongolian pine plantation in semi-arid northeast China

Climate change is predicted to alter global precipitation regimes.However,the response of soil carbon and nitrogen cycles and soil microorganisms to precipitation reduction is poorly understood but is dependent on ecosystem type.To evaluate the impacts of reduced precipitation on soil respiration,soil inorganic nitrogen(i.e.,NH4^+–N and NO3^-–N),nitrogen mineralization,and soil microbial community composition,a precipitation manipulation experiment was initiated in a Mongolian pine plantation and a naturally restored grassland in semi-arid northeast China.Precipitation reduction led to decreases of soil respiration rates by 14 and 8%in 2014 and 2015 in the Mongolian pine plantation but no changes in the grassland.Soil inorganic nitrogen,ammonification and nitrification rate,and soil phospholipids fatty acids were not significantly changed by reduced precipitation but significantly differed between the two ecosystems and among growing seasons.Our results suggest that the impacts of precipitation reduction on soil respiration were different between the Mongolian pine plantation and the grassland,and that ecosystem type and growing season had more pronounced impacts on soil carbon and nitrogen cycles.

Decomposition of Mongolian pine litter in the presence of understory species in semi-arid northeast China

The effects of understory plant litter on domi- nant tree litter decomposition are not well documented especially in semi-arid forests. In this study, we used a microcosm experiment to examine the effects of two understory species （Artemisia scoparia and Setaria viridis） litter on the mass loss and N release of Mongolian pine （Pinus sylvestris var. mongolica） litter in Keerqin Sandy Lands, northeast China, and identified the influencing mechanism from the chemical quality of decomposing litter. Four litter combinations were set up： one monocul- ture of Mongolian pine and three mixtures of Mongolian pine and one or two understory species in equal mass proportions of each species. Total C, total N, lignin, cel- lulose and polyphenol concentrations, and mass loss of pine litter were analyzed at days 84 and 182 of incubation.The chemistry of pine litter not only changed with the stages of decomposition, but was also strongly influenced by the presence of understory species during decomposition. Both understory species promoted mass loss of pine litter at 84 days, while only the simultaneous presence of two understory species promoted mass loss of pine litter at 182 days. Mass loss of pine litter was negatively correlated with initial ratios of C/N, lignin/N and polyphenol/N of litter combinations during the entire incubation period; at 182 days it was negatively correlated with polyphenol concentration and ratios of C/N and polyphenol/N of litter combinations at 84 days of incubation. Nitrogen release of pine litter was promoted in the presence of understory species. Nitrogen release at 84 days was negatively correlated with initial N concentration; at 182 days it was negatively correlated with initial polyphenol concentration of litter combinations and positively correlated with lignin concentration of litter com- binations at 84 days of incubation. Our results suggest that the presence ofunderstory species causes substantial changes in chemical components of pine litter that can exert strong influences on subsequent decomposition of pine litter.

Ultrahigh electrochemical performance in mixed-valence Cu_(1.85)Sebased anode for supercapacitors

Mixed-valence is an effective way to achieve high electrochemical performance of anodes for supercapacitor.However,inordinate mixed valence with more structural defects leads to structural instability.The development of mixed valence electrodes that can maintain a stable structure during the defect formation process is the key to resolving this problem.Cu_(2-x)Se with mixed-valence is a potential candidate,the stable monoclinic structure of Cu2Se can be transformed into another stable cubic structure(x>0.15).Herein,Cu_(1.85)Se anode with mixed valence reveals the ultrahigh specific capacity of 247.8 mA·h/g at 2 A/g.Furthermore,the introduction of multi-walled carbon nanotubes(MWCNTs)into Cu1.85Se further improves the specific capacity(435 mA·h/g at 2 A/g).XRD shows that the introduction of MWCNTs can improve the reversibility via chemical interactions and accelerate the electron transfer in the Cu1.85Se/MWCNTs.Notably,the assembled symmetric supercapacitor(SC)device expresses a high energy density of 41.4 W·h/kg,and the capacity remains 83%even after 8000 charge/discharge cycles.This research demonstrates the great potential of developing high specific capacity anode materials for superior performance supercapacitor.

In-situ growth of flexible 3D hollow tubular Cu_(2)S nanorods on Cu foam for high electrochemical performance supercapacitor

For pursing high-performance supercapacitors,both of the design strategy and structural characteristic of electrode materials are crucial.Herein,we report the in-situ growth of flexible self-assembled 3D hollow tubular Cu_(2)S nanorods on Cu foam substrate(Cu_(2)S@Cu).The Cu substrate is simultaneously acted as a copper source and a collector,which reduces the contact resistance.Moreover,the highly ordered 3D unique structure increases the redox reactive sites and enhances the ion transmission effectively,resulting in greatly improved electrochemical performance.Based on the Cu_(2)S@Cu electrode,the supercapacitor exhibits high areal capacitance of 1000 mF cm^(-2) at a current density of 2 mA cm^(-2),and great cycle stability,maintaining 96.9% capacitance after 10,000 cycles.Furthermore,the supercapacitor also shows an excellent flexibility with no significant decrease in the twisting or bending state.The capacity retention rates are 99.8% and 86.1%,respectively,and finally recover to 99.3%,confirming its great potential in practical application for portable electronic devices.