D2D communication resource allocation method based on joint optimization framework under dense users

By using the D3QN and DDPG methods of the joint optimization framework in the D2D communication environment, the problem of interference impact in high-density D2D communication is solved, adaptive resource allocation and power control are realized, delay and throughput are balanced, and D2D and cellular communications are improved. performance.

CN119071928AActive Publication Date: 2024-12-03CHANGCHUN UNIV OF SCI & TECH

Patent Information

Application Number
CN202411281414.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-13
Publication Date
2024-12-03
Estimated Expiration
2044-09-13

AI Technical Summary

Technical Problem

In a high-density D2D communication environment, mutual interference between devices causes the communication quality and transmission time to be affected, and existing DRL-based resource allocation and power control are difficult to effectively improve D2D and cellular communication performance when the delay requirements are low.

Method used

Using the D2D communication resource allocation method based on the joint optimization framework, by establishing the MDP decision process of D3QN and DDPG, designing an incremental reward mechanism and a deep reinforcement learning experience pool, performing iterative learning of D2D communication resource allocation and transmission power control, and output optimally Policy to optimize user channel selection and transmit power allocation.

Benefits of technology

It realizes adaptive control of power and independent selection of resources under low latency, gradually approaching the optimal solution, balancing user delay and throughput, ensuring normal communication of cellular users and maximizing system throughput.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119071928A_ABST
    Figure CN119071928A_ABST
Patent Text Reader

Abstract

The invention belongs to the technical field of communication, and particularly relates to a D2D communication resource allocation method based on a joint optimization framework under dense users, which comprises the following steps: S1, a D2D communication resource allocation data acquisition part and a D3QN and DDPG joint D2D communication resource allocation MDP decision process are established; s2, designing a progressive reward mechanism; and S3, constructing an action selection mechanism combined with D3QN and DDPG optimization. By adopting the D3QN and DDPG combined D2D communication resource allocation and transmitting power control method, each D2D user transmitting end can adaptively control the power and independently select the resource according to the D2D delay requirement. A progressive reward mechanism is adopted, so that the algorithm gradually approaches the optimal solution in the optimization process, the problems of difficulty in initial exploration and slow strategy convergence are solved, and the relationship between high user delay and low throughput is balanced in time; according to the method, normal communication of cellular users can be ensured, and the system throughput can be maximized under the condition of realizing balance of time delay and throughput.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to a D2D communication resource allocation method based on a joint optimization framework under dense user conditions. Background Art

[0002] The rapid development of mobile communication network technology has brought higher speeds, lower latency, larger connections and higher spectrum efficiency, while also raising users' expectations and triggering their growing demand for wireless networks. The mutual influence of the two has given rise to a series of innovative communication models.

[0003] Among them, device to device (D2D) communication, as an emerging communication mode, has been widely studied and applied. It is widely used in the fields of Internet of Things, social networks, emergency communications, etc. Although D2D communication brings many potential benefits, in a high-density D2D communication environment, the communication quality and transmission time may be seriously affected due to mutual interference between devices. At the same time, it also greatly increases the difficulty of network interference management within the system. Therefore, it is still worth further studying DRL-based resource allocation and power control, especially when the delay requirement is very low, to improve the performance of D2D and cellular communications. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the deficiencies of the prior art, the present invention provides a D2D communication resource allocation method based on a joint optimization framework under dense user conditions, which solves the problems raised in the above background technology.

[0006] (II) Technical solution

[0007] In order to achieve the above-mentioned purpose, the present invention specifically adopts the following technical solutions:

[0008] The D2D communication resource allocation method based on the joint optimization framework under dense user conditions includes the following steps:

[0009] S1: D2D communication resource allocation data collection part and establishing the MDP decision process of D2D communication resource allocation jointly with D3QN and DDPG;

[0010] S2: Design a progressive reward mechanism;

[0011] S3: Construct an action selection mechanism that combines D3QN and DDPG optimization;

[0012] S4: Design a deep reinforcement learning experience pool including positive and negative sample classification and priority experience replay to carry out the D2D communication resource allocation data training part;

[0013] S5: Based on the designed D2D communication system model in a single-cell dense user scenario, the joint D3QN and DDPG optimization method is used to perform 10,000 iterations of learning and output the optimal result for the D2D communication resource allocation and transmission power control data interaction part;

[0014] S6: Output the optimal strategy after iterative learning, that is, user channel selection and transmission power allocation in D2D communication in a single-cell dense user scenario.

[0015] Furthermore, in the S1, when performing the D2D communication resource allocation data collection part, all D2D pairs in the environment are regarded as an intelligent agent, and each intelligent agent completes a resource allocation according to the current strategy. When all intelligent agents complete resource allocation or reach the set interaction upper limit, the first data collection is completed. Next, the cellular D2D communication network environment is initialized and interacts with the environment again until the strategy of the intelligent agent converges or reaches a predetermined number of training times, and then data collection is stopped;

[0016] In the above S1, in the MDP decision process of establishing the D2D communication resource allocation of the joint D3QN and DDPG, it is necessary to establish the MDP model of the D2D communication network scenario in the cellular network single cell dense user scenario, which specifically includes the following contents:

[0017] State space: CUE's instantaneous channel information Ht, DUE's instantaneous channel information Gt, neighbor user's subchannel selection Nt-1 in the previous time slot, interference situation It-1 of each subchannel in the previous time slot, transmission time Tt that meets the delay constraint, and the remaining load Lt sent by DUE;

[0018] Action space definition:

[0019] in represents resource block allocation, the number of resource blocks is equal to the number of cellular users in the environment, represents all possible transmission powers that the agent can take;

[0020] Reward function: system throughput, delay constraints, and interference of cellular users.

[0021] Furthermore, the progressive reward function in S2 is set as follows:

[0022]

[0023] Where R c [m] and R d [n] represents the throughput of cellular user m and D2D user n, respectively. cellis the total amount of interference of cellular users in the current state, λ is the adjustment parameter, T t is the transmission time, and β is the weight parameter used to balance the relationship between system throughput and delay.

[0024] Furthermore, the S3 needs to initialize the experience pool in the joint optimization network, set the sample buffer area to store the current state, current action, current reward and the state at the next moment obtained by the interaction between the agent and the environment; initialize the joint action selection optimization model, including the network parameters of D3QN and DDPG; and specifically include the following contents:

[0025] Based on the dual action selection mechanism setting in the joint optimization network:

[0026] Improved greedy strategy definition:

[0027]

[0028] Where T now represents the current round number, ε final represents the exploration rate after stabilization, T final Indicates the number of rounds when the exploration rate is stable;

[0029] Action definition in the dual action selection mechanism:

[0030]

[0031] in represents the optimal subchannel selection, represents the optimal transmit power under the current delay constraint;

[0032] D3QN is used to select the optimal user sub-channel allocation scheme Using DDPG to select the best transmit power

[0033] Furthermore, the deep reinforcement learning experience pool in S4 includes positive and negative sample classification and priority experience playback, wherein the specific content of positive and negative sample classification is: in the process of interaction between the agent and the environment, the D2D reused successfully is used as a positive sample, and the reused failed is used as a negative sample, and then a certain proportion of non-uniform sampling is used to form a "minimum" sample, and finally the repeated "minimum" samples in the experience pool are removed;

[0034] The specific content of the priority experience replay is as follows: For the experience replay part of DRL training, the traditional experience replay is improved by random sampling, and a priority is introduced, which is called random priority experience replay. A higher sampling probability is given to experiences with higher priorities. Therefore, the time difference error is used to measure the priority of the sample, which is expressed as follows:

[0035]

[0036] Therefore, the number of samples for DRL training is defined as I, and the empirical priority of the i-th sample is:

[0037]

[0038] Rank(i) refers to the position of the i-th sample in the experience pool. When sampling, in order not to directly select the sample with the highest ranking, a random factor η is introduced, that is, a truncated Gaussian distribution is used to generate random numbers. This can ensure that low-priority experience also has a certain learning opportunity while maintaining a higher sampling probability for high-priority experience, thereby increasing the diversity of training, avoiding overfitting, and improving training effects.

[0039] Furthermore, in the data interaction part of S5, in each unit time "t", the agent obtains the state from the simulation environment and transmits it to the joint optimization network, calculates the Q value function through the joint optimization network and outputs the corresponding action selection, which is the optimal action obtained after processing by the dual network model, that is, the optimal subchannel selection and optimal power selection of D2D;

[0040] The specific process in S5 is as follows:

[0041] S5.1: Initializing D2D communication method parameters and network parameters, including the following steps:

[0042] S5.1.1: Initialize the sample capacity of the experience pool, store the state (user's channel gain), action (subchannel allocation and transmit power control), reward (system throughput and interference and delay constraints), and next moment state (user's channel gain) obtained by the interaction of intelligent agents in the D2D communication environment under a single cell into the experience pool;

[0043] S5.1.2: Initialize the joint action selection optimization model of the intelligent agent, including the network model and parameters of the subchannel selection unit - D3QN; the policy network, Q network model and parameters of the transmission power control unit - DDPG;

[0044] S5.1.3: Initialize the system model in a single-cell dense user scenario, set the base station to be located at the center of the cell, and set the cellular users and D2D users to be randomly distributed in the cell;

[0045] S5.2: Running the joint D3QN and DDPG method to iteratively learn and output a D2D communication resource allocation strategy in a single cell; including the following steps:

[0046] S5.2.1: Use the state (s), action (a), and reward (r) obtained by the interaction between the agent and the environment to construct the MDP decision process, calculate the link gain when users are reused in the system, the signal-to-interference-to-noise ratio of the user, and use Shannon's theorem and function constraints to output the system throughput;

[0047] S5.2.2: Input the current action selection, reward value, and updated state into the experience pool as a sample;

[0048] S5.2.3: Input the small batch samples in the experience pool into the DDPG network and the D3QN network respectively, calculate and update the policy network parameters and target network parameters of DDPG, calculate and update the state value function and action value function parameters of D3QN, and output the user's subchannel selection and transmission power.

[0049] (III) Beneficial effects

[0050] Compared with the prior art, the present invention provides a D2D communication resource allocation method based on a joint optimization framework under dense user conditions, which has the following beneficial effects:

[0051] The present invention adopts D3QN and DDPG to jointly allocate D2D communication resources and control transmission power. According to the D2D delay requirements, each D2D user transmitter can adaptively control power and independently select resources. And a progressive reward mechanism is adopted to make the algorithm gradually approach the optimal solution during the optimization process, solve the problems of difficult initial exploration and slow strategy convergence, and timely balance the relationship between high user delay and low throughput; the present invention can not only ensure the normal communication of cellular users, but also maximize the system throughput while achieving a balance between delay and throughput. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flow chart for realizing the present invention;

[0053] Figure 2 It is a system model diagram of the present invention;

[0054] Figure 3 This is a network structure diagram of the joint optimization method of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example

[0057] like Figure 1-3 As shown, a D2D communication resource allocation method based on a joint optimization framework under dense user conditions proposed in an embodiment of the present invention includes the following steps:

[0058] S1: D2D communication resource allocation data collection part and establishing the MDP decision process of D2D communication resource allocation jointly with D3QN and DDPG;

[0059] S2: Design a progressive reward mechanism;

[0060] S3: Construct an action selection mechanism that combines D3QN and DDPG optimization;

[0061] S4: Design a deep reinforcement learning experience pool including positive and negative sample classification and priority experience replay to carry out the D2D communication resource allocation data training part;

[0062] S5: Based on the designed D2D communication system model in a single-cell dense user scenario, the joint D3QN and DDPG optimization method is used to perform 10,000 iterations of learning and output the optimal result for the D2D communication resource allocation and transmission power control data interaction part;

[0063] S6: Output the optimal strategy after iterative learning, that is, user channel selection and transmission power allocation in D2D communication in a single-cell dense user scenario.

[0064] In some embodiments, when performing the D2D communication resource allocation data collection part in S1, all D2D pairs in the environment are regarded as an intelligent agent, and each intelligent agent completes a resource allocation according to the current strategy. When all intelligent agents complete resource allocation or reach the set interaction upper limit, the first data collection is completed. Next, the cellular D2D communication network environment is initialized and interacts with the environment again until the strategy of the intelligent agent converges or reaches a predetermined number of training times, and then data collection is stopped;

[0065] In S1, in the process of establishing the MDP decision-making process of D2D communication resource allocation for joint D3QN and DDPG, it is necessary to establish the MDP model of the D2D communication network scenario in the cellular network single cell dense user scenario, which specifically includes the following contents:

[0066] State space: CUE's instantaneous channel information Ht, DUE's instantaneous channel information Gt, neighbor user's subchannel selection Nt-1 in the previous time slot, interference situation It-1 of each subchannel in the previous time slot, transmission time Tt that meets the delay constraint, and the remaining load Lt sent by DUE;

[0067] Action space definition:

[0068] in represents resource block allocation, the number of resource blocks is equal to the number of cellular users in the environment, represents all possible transmission powers that the agent can take;

[0069] Reward function: system throughput, delay constraints, and interference of cellular users.

[0070] In some embodiments, the progressive reward function in S2 is set as follows:

[0071]

[0072] Where R c [m] and R d [n] represents the throughput of cellular user m and D2D user n, respectively. cell is the total amount of interference of cellular users in the current state, λ is the adjustment parameter, T t is the transmission time, and β is the weight parameter used to balance the relationship between system throughput and delay.

[0073] In some embodiments, S3 needs to initialize the experience pool in the joint optimization network, set a sample buffer area to store the current state, current action, current reward and next moment state obtained by the interaction between the agent and the environment; initialize the joint action selection optimization model, including the network parameters of D3QN and DDPG; and specifically include the following contents:

[0074] Based on the dual action selection mechanism setting in the joint optimization network:

[0075] Improved greedy strategy definition:

[0076]

[0077] Where T now represents the current round number, ε final represents the exploration rate after stabilization, T final Indicates the number of rounds when the exploration rate is stable;

[0078] Action definition in the dual action selection mechanism:

[0079]

[0080] in represents the optimal subchannel selection, represents the optimal transmit power under the current delay constraint;

[0081] D3QN is used to select the optimal user sub-channel allocation scheme Using DDPG to select the best transmit power

[0082] In some embodiments, the deep reinforcement learning experience pool in S4 includes positive and negative sample classification and priority experience playback, wherein the specific content of positive and negative sample classification is: during the interaction between the agent and the environment, D2D reuse successfully is used as a positive sample, and reuse failed is used as a negative sample, and then a certain proportion of non-uniform sampling is used to form a "minimum" sample, and finally the repeated "minimum" samples in the experience pool are removed;

[0083] The specific content of the priority experience replay is as follows: For the experience replay part of DRL training, the traditional experience replay is improved by random sampling, and a priority is introduced, which is called random priority experience replay. A higher sampling probability is given to experiences with higher priorities. Therefore, the time difference error is used to measure the priority of the sample, which is expressed as follows:

[0084]

[0085] Therefore, the number of samples for DRL training is defined as I, and the empirical priority of the i-th sample is:

[0086]

[0087] Rank(i) refers to the position of the i-th sample in the experience pool. When sampling, in order not to directly select the sample with the highest ranking, a random factor η is introduced, that is, a truncated Gaussian distribution is used to generate random numbers. This can ensure that low-priority experience also has a certain learning opportunity while maintaining a higher sampling probability for high-priority experience, thereby increasing the diversity of training, avoiding overfitting, and improving training effects.

[0088] In some embodiments, in the data interaction part of S5, in each unit time "t", the agent obtains the state from the simulation environment and transmits it to the joint optimization network, calculates the Q value function through the joint optimization network and outputs the corresponding action selection, which is the optimal action obtained after processing by the dual network model, that is, the optimal sub-channel selection and optimal power selection of D2D;

[0089] The specific process in S5 is as follows:

[0090] S5.1: Initializing D2D communication method parameters and network parameters, including the following steps:

[0091] S5.1.1: Initialize the sample capacity of the experience pool, store the state (user's channel gain), action (subchannel allocation and transmit power control), reward (system throughput and interference and delay constraints), and next moment state (user's channel gain) obtained by the interaction of intelligent agents in the D2D communication environment under a single cell into the experience pool;

[0092] S5.1.2: Initialize the joint action selection optimization model of the intelligent agent, including the network model and parameters of the subchannel selection unit - D3QN; the policy network, Q network model and parameters of the transmission power control unit - DDPG;

[0093] S5.1.3: Initialize the system model in a single-cell dense user scenario, set the base station to be located at the center of the cell, and set the cellular users and D2D users to be randomly distributed in the cell;

[0094] S5.2: Running the joint D3QN and DDPG method to iteratively learn and output a D2D communication resource allocation strategy in a single cell; including the following steps:

[0095] S5.2.1: Use the state (s), action (a), and reward (r) obtained by the interaction between the agent and the environment to construct the MDP decision process, calculate the link gain when users are reused in the system, the signal-to-interference-to-noise ratio of the user, and use Shannon's theorem and function constraints to output the system throughput;

[0096] S5.2.2: Input the current action selection, reward value, and updated state into the experience pool as a sample;

[0097] S5.2.3: Input the small batch samples in the experience pool into the DDPG network and the D3QN network respectively, calculate and update the policy network parameters and target network parameters of DDPG, calculate and update the state value function and action value function parameters of D3QN, and output the user's subchannel selection and transmission power.

[0098] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A D2D communication resource allocation method based on a joint optimization framework under dense user conditions, characterized by: The following steps are involved: S1: D2D communication resource allocation data collection part and establishing the MDP decision process of D2D communication resource allocation jointly with D3QN and DDPG; S2: Design a progressive reward mechanism; S3: Construct an action selection mechanism that combines D3QN and DDPG optimization; S4: Design a deep reinforcement learning experience pool including positive and negative sample classification and priority experience replay to carry out the D2D communication resource allocation data training part; S5: Based on the designed D2D communication system model in a single-cell dense user scenario, the joint D3QN and DDPG optimization method is used to perform 10,000 iterations of learning and output the optimal result for the D2D communication resource allocation and transmission power control data interaction part; S6: Output the optimal strategy after iterative learning, that is, user channel selection and transmission power allocation in D2D communication in a single-cell dense user scenario.

2. The D2D communication resource allocation method based on a joint optimization framework under dense user conditions according to claim 1 is characterized by: In the D2D communication resource allocation data collection part in S1, all D2D pairs in the environment are regarded as an intelligent agent, and each intelligent agent completes a resource allocation according to the current strategy. When all intelligent agents complete resource allocation or reach the set interaction upper limit, the first data collection is completed. Next, the cellular D2D communication network environment is initialized and interacts with the environment again until the strategy of the intelligent agent converges or reaches a predetermined number of training times, and then data collection is stopped; In the above S1, in the MDP decision process of establishing the D2D communication resource allocation of the joint D3QN and DDPG, it is necessary to establish the MDP model of the D2D communication network scenario in the cellular network single cell dense user scenario, which specifically includes the following contents: State space: CUE's instantaneous channel information Ht, DUE's instantaneous channel information Gt, neighbor user's subchannel selection Nt-1 in the previous time slot, interference situation It-1 of each subchannel in the previous time slot, transmission time Tt that meets the delay constraint, and the remaining load Lt sent by DUE; Action space definition: in represents resource block allocation, the number of resource blocks is equal to the number of cellular users in the environment, represents all possible transmission powers that the agent can take; Reward function: system throughput, delay constraints, and interference of cellular users.

3. The D2D communication resource allocation method based on a joint optimization framework under dense user conditions according to claim 2 is characterized in that: The progressive reward function in S2 is set as follows: Where R c [m] and R d [n] represents the throughput of cellular user m and D2D user n, respectively. cell is the total amount of interference of cellular users in the current state, λ is the adjustment parameter, T t is the transmission time, and β is the weight parameter used to balance the relationship between system throughput and delay.

4. The D2D communication resource allocation method based on a joint optimization framework under dense user conditions according to claim 3 is characterized by: In the S3, the experience pool in the joint optimization network needs to be initialized, and a sample buffer area needs to be set to store the current state, current action, current reward, and state at the next moment obtained by the interaction between the agent and the environment; the joint action selection optimization model needs to be initialized, including the network parameters of D3QN and DDPG; and specifically includes the following contents: Based on the dual action selection mechanism setting in the joint optimization network: Improved greedy strategy definition: Where T now represents the current round number, ε final represents the exploration rate after stabilization, T final Indicates the number of rounds when the exploration rate is stable; Action definition in the dual action selection mechanism: in represents the optimal subchannel selection, represents the optimal transmit power under the current delay constraint; D3QN is used to select the optimal user sub-channel allocation scheme Using DDPG to select the best transmit power 5. The D2D communication resource allocation method based on a joint optimization framework under dense user conditions according to claim 4 is characterized in that: The deep reinforcement learning experience pool in S4 includes positive and negative sample classification and priority experience playback, wherein the specific content of positive and negative sample classification is: in the process of interaction between the agent and the environment, the D2D reused successfully is used as a positive sample, and the reused failed is used as a negative sample, and then a certain proportion of non-uniform sampling is used to form a "minimum" sample, and finally the repeated "minimum" samples in the experience pool are removed; The specific content of the priority experience replay is as follows: For the experience replay part of DRL training, the traditional experience replay is improved by random sampling, and a priority is introduced, which is called random priority experience replay. A higher sampling probability is given to experiences with higher priorities. Therefore, the time difference error is used to measure the priority of the sample, which is expressed as follows: Therefore, the number of samples for DRL training is defined as I, and the empirical priority of the i-th sample is: Rank(i) refers to the position of the i-th sample in the experience pool. When sampling, in order not to directly select the sample with the highest ranking, a random factor η is introduced, that is, a truncated Gaussian distribution is used to generate random numbers. This can ensure that low-priority experience also has a certain learning opportunity while maintaining a higher sampling probability for high-priority experience, thereby increasing the diversity of training, avoiding overfitting, and improving training effects.

6. The D2D communication resource allocation method based on a joint optimization framework under dense user conditions according to claim 5 is characterized by: In the data interaction part of S5, in each unit time "t", the agent obtains the state from the simulation environment and transmits it to the joint optimization network, calculates the Q value function through the joint optimization network and outputs the corresponding action selection, which is the optimal action obtained after processing by the dual network model, that is, the optimal sub-channel selection and optimal power selection of D2D; The specific process in S5 is as follows: S5.1: Initializing D2D communication method parameters and network parameters, including the following steps: S5.1.1: Initialize the sample capacity of the experience pool, store the state (user's channel gain), action (subchannel allocation and transmit power control), reward (system throughput and interference and delay constraints), and next moment state (user's channel gain) obtained by the interaction of intelligent agents in the D2D communication environment under a single cell into the experience pool; S5.1.2: Initialize the joint action selection optimization model of the intelligent agent, including the network model and parameters of the subchannel selection unit - D3QN; the policy network, Q network model and parameters of the transmission power control unit - DDPG; S5.1.3: Initialize the system model in a single-cell dense user scenario, set the base station to be located at the center of the cell, and set the cellular users and D2D users to be randomly distributed in the cell; S5.2: Running the joint D3QN and DDPG method to iteratively learn and output a D2D communication resource allocation strategy in a single cell; including the following steps: S5.2.1: Use the state (s), action (a), and reward (r) obtained by the interaction between the agent and the environment to construct the MDP decision process, calculate the link gain when users are reused in the system, the signal-to-interference-to-noise ratio of the user, and use Shannon's theorem and function constraints to output the system throughput; S5.2.2: Input the current action selection, reward value, and updated state into the experience pool as a sample; S5.2.3: Input the small batch samples in the experience pool into the DDPG network and the D3QN network respectively, calculate and update the policy network parameters and target network parameters of DDPG, calculate and update the state value function and action value function parameters of D3QN, and output the user's subchannel selection and transmission power.

Citation Information

Patent Citations

  • A D2D user resource allocation method based on a deep reinforcement learning DDPG algorithm

    CN109862610A

  • D2D communication resource allocation method based on improved D3QN under multiple base stations

    CN116981090A

  • Multi-agent learning method for non-cellular network user scheduling and resource configuration

    CN117221925A

  • Resource allocation method and system for densely deploying NTN (Network Temporary Network) Internet of Things network

    CN118301771A

  • User packet and resource allocation method and apparatus in noma-MEC system

    WO2023179010A1

Cited By

  • Coherent detection spatial light cooperative transmission method based on local oscillator elastic light splitting

    CN119853815A

  • Resource configuration method and device of RF control system, storage medium and equipment

    CN120751503A

  • A resource configuration method and device of an RF control system, a storage medium and an equipment

    CN120751503B