10 results about "Network utility" patented technology

The invention discloses an Internet of Things routing method based on a graph neural network and reinforcement learning, and relates to the technical field of Internet of Things communication. The method comprises the following steps: firstly, constructing a network logic topology and a state model containing parameters such as bandwidth and time delay; based on the time random walk sequence, using an LSTM auto-encoder to extract node time evolution characteristics, migrating a weight initialization Node2vec model to extract static structure characteristics, and generating space-time fused node representation; then, neighbor message updating features are aggregated through a graph neural network, and global states are spliced to construct reinforcement learning input; and finally, designing a differentiated reward function for different service types sensitive to time delay or throughput, and optimizing next hop selection by using a deep reinforcement learning agent to maximize network utility as a target. According to the method, the topology dynamic change can be accurately sensed, multi-service differentiated scheduling is realized, the network throughput and robustness are remarkably improved, and the transmission delay is reduced.

The invention discloses a proportional fair scheduling method based on a block chain. The method comprises the steps that a user and an operator complete identity authentication and registration through a registration contract; a user periodically uploads channel state information and bandwidth requirements through a state reporting contract; the scheduling contract calculates the scheduling priority of each user according to a proportional fairness principle, determines a to-be-scheduled user for each operator, and completes the updating of the historical throughput of the user; and the settlement contract generates a bill according to the scheduling result and carries out chaining for evidence storage. The invention further discloses a cross-network joint scheduling performance evaluation method in the multi-operator collaborative environment, and a mathematical characterization model of the long-term average throughput of the user and the network utility is constructed. According to the method, automatic scheduling is realized by using the intelligent contract, and the scheduling operation is recorded on the chain in a tampering-free manner, so that the whole scheduling process is open, transparent, safe and credible, cross-network resource aggregation and cooperative scheduling in a multi-operator environment are realized, and the utilization efficiency of spectrum resources and the overall performance of the network are effectively improved.

This invention discloses a robust resource scheduling method and related apparatus for UAV-assisted cellular networks, comprising: 1) initializing the basic parameters of the UAV-assisted cellular network and sampling uncertain channel state information between the UAV and ground users to obtain uncertain channel state information samples; 2) constructing a polyhedral model with a high-probability region based on the uncertain channel state information samples; 3) constructing a two-stage robust optimization model, wherein the first stage is the main problem MP and the second stage is the subproblem SP; 4) linearizing the subproblem SP to obtain a mixed-integer linear programming problem SP. MILP 5) Design a solution to the mixed-integer linear programming problem SP. MILP The branch and bound algorithm; 6) Control the drone users and base station users according to the optimal transmit power of the drone users and base station users. This method and related devices can effectively improve the reliability and network utility of the drone-assisted network.

The invention discloses a satellite-ground communication network user association method based on multi-agent deep reinforcement learning. The method comprises the following steps: establishing a cache auxiliary satellite-ground fusion network system; by taking realization of network utility maximization in a cache replacement period as an optimization target, and by taking limitation of base stations or low earth orbit satellites used by users, an upper limit of the service quantity of the base stations and an upper limit of the service quantity of the low earth orbit satellites as constraint conditions, constructing an optimization problem P0 for maximizing the network utility; converting an optimization problem P0 for maximizing network utility into a partially observable Markov process, and constructing a neural network structure framework for decentralized execution and centralized training; and based on a neural network structure framework, selecting optimal user association distribution by adopting a multi-agent deep learning strategy based on a value decomposition network. According to the method, high-energy-efficiency low-delay high-quality service is taken as a core target, and a multi-agent deep reinforcement learning algorithm is designed to solve the problem of user association.

The application relates to a wireless network congestion control optimization method based on a heavy ball method, which comprises the following steps: initialization, selection of system parameters and iteration step length; emptying all queues at the initial state; initial value assignment of weights; iteration, start of calculation of the difference of the weight parameters, determination of a service rate for each link by a scheduling module to obtain a service rate vector; congestion control, determination of an integer random variable for each data flow, wherein the random variable needs to meet the constraint of queue stability; update of the queue length and update of the weight parameters by using the heavy ball method; and finally, return to the iteration start point until the algorithm converges. The application realizes the maximization of network utility under the constraint of queue stability by introducing the heavy ball method based on momentum, effectively reduces the queue delay, and achieves the effect of improving the communication quality by reliable resource allocation and routing scheduling when the devices accessing the data link network are continuously increased.

The invention discloses a zero-forcing transmitting and receiving beam forming joint optimization method, device and equipment based on an original decomposition method and a medium, and belongs to the field of wireless communication networks, and the method comprises the following steps: constructing a zero-forcing transmitting and receiving beam forming joint optimization model of all transmitters and receivers in a multi-user multiple-input multiple-output wireless communication network, the zero-forcing transmit-receive beamforming joint optimization model comprises a network utility objective function, transmit-receive beamforming power constraint and zero interference constraint; and decomposing the zero-forcing transmit-receive beamforming joint optimization model based on an original decomposition method, designing an original decomposition algorithm based on a parallel continuous convex approximation algorithm, and carrying out parallel iteration to update transmit-receive beamforming until a preset iteration termination condition is satisfied, thereby obtaining feasible transmit-receive beamforming of all links after optimization, the transmitting and receiving beamforming obtained by each iteration of the original decomposition algorithm is feasible.

The invention discloses a network utility optimization method for a multi-unmanned aerial vehicle cooperative mobile edge computing network, and belongs to the field of wireless communication. The implementation method of the invention comprises the following steps: constructing a multi-UAV collaborative MEC network architecture; respectively constructing a communication and calculation model, a network cost model and a network utility model by combining the unloading selection variable and the calculation selection variable; 2, constructing an optimization problem by taking maximization of the network utility model obtained in the step 1 as a target; the UPTSM algorithm decomposes an original optimization problem into two sub-problems, and the two sub-problems are converted into two bipartite graph matching problems; sequentially solving the two problems by adopting a Hungary algorithm to obtain an unloading selection variable and a calculation selection variable; the VC-WOA limits variables violating the task processing time limit to quickly search legal solutions, so that the network utility is improved to the greatest extent. According to the invention, by optimizing multi-UAV cooperative task scheduling and energy management, the cooperation efficiency can be improved, and fair task distribution is realized, so that the network income is maximized.

The application belongs to the technical field of general computing resource allocation, and particularly relates to a time-differentiated general computing resource allocation method, which comprises the following steps: constructing a time-differentiated ISCC system model, which comprises a base station, a mobile user and a sensing target; establishing a time-varying request model, a service cache model, a communication model, a computing model and a sensing model; taking the maximization of a network utility function as an objective, under the constraints of a time delay tolerance and a storage capacity, establishing a joint optimization problem comprising service caching, task offloading, spectrum resources, power resources and computing resources; converting the joint optimization problem into a partially observable Markov decision process, taking the base station as an agent, and defining a triple; and solving the problem by using a deep deterministic policy gradient algorithm based on LSTM; and the application uses an LSTM network to capture historical information, and the agent makes an optimal decision.

The application discloses a kind of multi-antenna unmanned plane communication network robust resource scheduling method and related device, comprising: the basic parameters of unmanned plane communication network are initialized, each ground user is arranged in ascending order according to the horizontal distance between ground user and unmanned plane ground projection point, according to channel gain difference, the user with unmanned plane ground projection point horizontal distance is close and the user with unmanned plane ground projection point horizontal distance is far away is paired;Determine high-probability confidence region;With the minimum unmanned plane total transmit power as target, construct the mathematical model P1 of joint optimization beam forming and power allocation;Solve the mathematical model P1, obtain unmanned plane robust beam forming and power allocation coefficient, according to unmanned plane robust beam forming and power allocation coefficient, multi-antenna unmanned plane communication network robust resource scheduling, the method and related device can effectively improve the reliability and network utility of multi-antenna unmanned plane network.

The invention discloses a network optimization method and a server, and relates to the technical field of network communication, and the method comprises the steps: obtaining a target network topological graph of a target network; wherein the target network is a content distribution network powered by green power. And then, according to the target network topological graph, performing problem positioning on the target network to obtain a network optimization problem. And then, solving a network optimization problem by using a gradient descent algorithm to obtain an optimal solution of the problem. And then, according to the optimal solution of the problem, determining a target request rate and a target cache allocation strategy. Wherein the target request rate and the target cache allocation strategy are used for maximizing the network utility of the target network. According to the embodiment of the invention, the effective consumption of green electricity can be realized while the network utility is maximized.