The invention proposes an SDN network DDoS attack detection method based on an optimized BP neural network. The method achieves the more complete extraction of six feature values, correlated with DDoS, in a lower flow table of an SDN network environment: source IP address acceleration GSIP, flow survival time change ADF, opposite flow ratio PPF, port acceleration GSP, a flow table item speed RFE,and a flow matching success rat RFM. Through the setting of a triggering threshold value, the method reduces the load of the SDN network, and employs a particle swarm optimization algorithm for optimizing the BP neural network, selects the mean square error of the BP neural network as a fitness function of the particle swarm optimization algorithm, selects the value with the best fitness as the threshold and weight of the BP neural network, avoids the conditions that the slow solving speed of the optimal solution of the BP neural network causes a locally optimal solution, and improves the detection precision.

SDN network DDoS attack detection method based on optimized BP neural network

The invention provides a novel reservoir evaluation method and device based on logging data. The novel reservoir evaluation method based on the logging data comprises the steps that step 1, data selection and data preprocessing are conducted; step 2, predicting the porosity and the permeability of the non-coring section by adopting the preprocessed data; step 3, utilizing the predicted porosity and permeability to identify the interlayer; and step 4, synthesizing comprehensive parameters for reservoir evaluation. According to the new reservoir evaluation method and device based on the loggingdata, on one hand, evaluation on a reservoir can be quantified, and on the other hand, inaccurate reservoir evaluation caused by adoption of a single parameter can be avoided; An effective reservoir evaluation parameter is formulated by utilizing logging data, rock core experimental data are fully utilized, and the credibility is enhanced.

novel reservoir evaluation method based on logging data

The invention discloses a neural network-based abnormal-traffic detection method and system. The method and the system are used to optimize an abnormal-traffic identification model. The method provided by the invention includes: collecting network traffic data, and selecting main feature attributes through an information gain method; setting neuron numbers of an input layer, a hidden layer and anoutput layer of a neural network model according to the main feature attributes; training the neural network model, and calculating and judging whether a mean square error value is less than a minimumerror; when the same is less than the preset error value, using weight values and thresholds of the neural network model as inputs of an artificial bee colony algorithm, and using the error value asa fitness function; obtaining updated food sources through a particle swarm optimization algorithm after a certain solution reaches a searching upper-limit; using updated source information as new weight values and thresholds, and carrying out retraining; and then identifying abnormal traffic. The method can guarantee late convergence speed while global optimization is carried out, improve optimization efficiency, and guarantee accuracy of abnormal-traffic detection.

Neural network-based abnormal-traffic detection method and system

The embodiment of the invention discloses a method and equipment for selecting a CDN (Content Delivery Network) node, relates to the field of communications, and realizes selection of CDN nodes with relatively high service efficiency from edge CDN nodes and external CDN nodes. The specific solution comprises: receiving, by an MEC server, a DNS (Domain Name Service) request including a domain nameand sent by a terminal; when a stored domain name set includes the domain name, judging whether appointed load rates of the edge CDN nodes in an edge CDN node set meet a preset condition or not; and if the appointed load rate of each edge CDN node does not meet the preset conditions, sending the DNS request and a first comprehensive load rate to a global load balancer corresponding to the DNS request, receiving an indication message sent by the global load balancer, determining a target CDN node according to the indication message, and sending an IP (Internet Protocol) address of the target CDN node to the terminal. The embodiment of the invention is used in the process of selecting the CDN node for the terminal.

Method and device for selecting CDN (Content Delivery Network) node

The embodiment of the invention relates to an authentication method and system, a method for accessing a terminal to a network, a central authentication system, an edge authentication system and a terminal. The method comprises the following steps of responding to the received access request, obtaining a token of a terminal and an identifier of the terminal carried by the access request, extracting tokens corresponding to the identifiers from a preset database, judging whether the extracted token is consistent with the token of the terminal or not; if yes, generating a new token; obtaining a uniform resource locator of an edge authentication system to which the terminal belongs, sending the new token and the uniform resource locator to the terminal; and sending the new token and the identifier to the edge authentication system, so that the technical problem of long authentication time in the prior art is avoided, the authentication pressure of the central authentication system is reduced, the load of the central authentication system is reduced, the operation efficiency of the central authentication system is improved, and the technical effect of saving time is realized.

Authentication method and system, and method for accessing terminal to network

The invention discloses an intrusion detection method and system of a BP algorithm based on artificial swarm optimization. The method comprises the following steps: forming a packet through a collected host log file and network data, preprocessing the packet to obtain feature vectors of the host log file and the network data, and converting the feature vectors into input values that can be identified by a BP neural network algorithm; initializing the BP neural network algorithm, using a weight Wij connecting an input layer and a hidden layer and a weight Wjk connecting the hidden layer and anoutput layer as optimization targets of the artificial swarm algorithm to initialize the parameters of the artificial swarm algorithm, and transmitting an optimal honey source to the BP neural networkalgorithm to replace the weight Wij connecting the input layer and the hidden layer and the weight Wjk connecting the hidden layer and the output layer; and making a corresponding response operationon the behavior of a user according to the output value of the BP neural network algorithm. By adoption of the intrusion detection method and system, the problems of low convergence rate, vulnerability to local minimum point and large calculation amount of the existing BP neural network.

Intrusion detection method and system of BP algorithm based on artificial swarm optimization

The invention provides an optimized authentication method and system for a network access request. The method comprises the following steps that a scheduling center issues a domain name initial configuration table to each edge node; each edge node obtains performance information of each service node; the service node sends an access request to each edge node; each edge node generates an optimal coverage record of the edge node and uploads encrypted data to the scheduling center; the scheduling center decrypts the encrypted data, and sends an authentication request carrying an identity to an authentication server; the authentication server feeds back equipment information corresponding to the identity to the edge node; and the edge node authenticates the access request passing the service node. According to the technical scheme provided by the invention, the authentication efficiency can be improved.

Optimized authentication method and system for network access request

The invention provides an optimization method and system for a network transmission link. The method comprises the steps that an edge node downloads back-to-the-source path information from a computing center, wherein the back-to-the-source path information is obtained by the computing center through computing according to feedback detection information of each node; the edge node receives a handshake request which is sent by a client and points to a target domain name and determines a back-to-the-source path for transmitting the handshake request based on the handshake request and the back-to-the-source path information; when the edge node establishes connection with an adjacent node in the back-to-the-source path unsuccessfully, the edge node reselects the back-to-the-source path according to the back-to-the-source path information; and the edge node attempts to establish connection with the adjacent node in the reselected back-to-the-source path. According to the technical scheme provided by the invention, the transmission efficiency of data between the client of a user and a source station server can be improved.

Optimization method and system for network transmission link

The invention relates to a WEB station security detection method and device and a computer readable medium Large-scale WEB station security detection is provided Directional protection is realizedCorresponding security events can be timely processed The method comprises the following steps of obtaining a webpage file of a detected WEB station through a web crawler according to a breadth firstsearch policy, and analyzing the webpage file to obtain corresponding webpage source codes through utilization of a DOM (Document Object Model); carrying out whole station security state detection and webpage Trojan detection on the analyzed webpage source codes; and sending out alarm prompt to a user of the WEB station when a security state bad result or a webpage Trojan is detected According to the method, the device and the computer readable medium, the user is helped to know, track and analyze security states of the station in various time periods, so security protection policies and emphasis satisfying own demands can be customized, vested interests of the WEB station owner are protected, and moreover, rights and interests of a station visitor are indirectly protected

Li Wen

Papers

Intrusion detection method and system of BP algorithm based on artificial swarm optimization

Optimized authentication method and system for network access request

Optimization method and system for network transmission link

WEB station security detection method and device and computer readable medium