Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attack...Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attackers to obtain complete network information in realistic network scenarios,Reinforcement Learning(RL)is a promising solution to discover the optimal penetration path under incomplete information about the target network.Existing RL-based methods are challenged by the sizeable discrete action space,which leads to difficulties in the convergence.Moreover,most methods still rely on experts’knowledge.To address these issues,this paper proposes a penetration path planning method based on reinforcement learning with episodic memory.First,the penetration testing problem is formally described in terms of reinforcement learning.To speed up the training process without specific prior knowledge,the proposed algorithm introduces episodic memory to store experienced advantageous strategies for the first time.Furthermore,the method offers an exploration strategy based on episodic memory to guide the agents in learning.The design makes full use of historical experience to achieve the purpose of reducing blind exploration and improving planning efficiency.Ultimately,comparison experiments are carried out with the existing RL-based methods.The results reveal that the proposed method has better convergence performance.The running time is reduced by more than 20%.展开更多
Under the requirement of high-quality development, the research method of integrated model planning for offshore oil and gas exploration and development suitable for the western South China Sea is put forward. Based o...Under the requirement of high-quality development, the research method of integrated model planning for offshore oil and gas exploration and development suitable for the western South China Sea is put forward. Based on the new round of resource evaluation and exploration and development research in the western South China Sea, the in-depth research on underground oil and gas resources, surface development facilities, external factors and economic indexes are carried out to clarify the industrial layout of oil and gas development. The potential and prospect of oil and gas exploration and development were implemented, and the main external factors and corresponding measures affecting the planning were clarified in this paper. The economic evaluation model suitable for the region is established based on the analysis of internal rate of return, comprehensive barrel oil cost, critical price, financial net present value and other important indicators, and a set of planning and research methods suitable for the integration of exploration and development in the western South China Sea is finally formed. This method has been applied to the replacement reserve study of Weizhou X and Weizhou Y oil fields. It is found that the planned reserves and production are consistent with the actual ones, and good practical results have been achieved.展开更多
In order to realize the explorer autonomy, the software architecture of autonomous mission management system (AMMS) is given for the deep space explorer, and the autonomous mission planning system, the kernel part of ...In order to realize the explorer autonomy, the software architecture of autonomous mission management system (AMMS) is given for the deep space explorer, and the autonomous mission planning system, the kernel part of this architecture, is designed in detail. In order to describe the parallel activity, the state timeline is introduced to build the formal model of the planning system and based on this model, the temporal constraint satisfaction planning algorithm is proposed to produce the explorer’s activity sequence. With some key subsystems of the deep space explorer as examples, the autonomous mission planning simulation system is designed. The results show that this system can calculate the executable activity sequence with the given mission goals and initial state of the explorer.展开更多
The bidding blocks are distributed in different regions of China,There are seven blocks in W est China,and seven blocks in Northeast China,the other twelve blocks are from North and Central China.All the blocks are lo...The bidding blocks are distributed in different regions of China,There are seven blocks in W est China,and seven blocks in Northeast China,the other twelve blocks are from North and Central China.All the blocks are located in prospective sedimentary basins with different geological condi-tions,some are from oil produced basin such as Bohai Bay Basin which is a prolific basin,it's production accounts for 50%in total prodcuction of China.Based on estimation,the total potential resource of oil is 3.55 billion tons and gas is 800 billion cubic meters in bidding areas.As far as the exploratory objectives are concerned,there are Paleozoic.Mesozoic and Cenozoic strata,as well as continental clastic and marine一carbonate re-servoir.These provide more choices for foreign companies.In addition,most of bidding blocks are adjacent to transport lines,so communication and petroleum transportation are very convenient.展开更多
Path planning is a prevalent process that helps mobile robots find the most efficient pathway from the starting position to the goal position to avoid collisions with obstacles.In this paper,we propose a novel path pl...Path planning is a prevalent process that helps mobile robots find the most efficient pathway from the starting position to the goal position to avoid collisions with obstacles.In this paper,we propose a novel path planning algorithm-Intermediary RRT*-PSO-by utilizing the exploring speed advantages of Rapidly exploring Random Trees and using its solution to feed to a metaheuristic-based optimizer,Particle swarm optimization(PSO),for fine-tuning and enhancement.In Phase 1,the start and goal trees are initialized at the starting and goal positions,respectively,and the intermediary tree is initialized at a random unexplored region of the search space.The trees were grown until one met the other and then merged and re-initialized in other unexplored regions.If the start and goal trees merge,the first solution is found and passed through a minimization process to reduce unnecessary nodes.Phase 2 begins by feeding the minimized solution from Phase 1 as the global best particle of PSO to optimize the path.After simulating two special benchmark configurations and six practice configurations with special cases,the results of the study concluded that the proposed method is capable of handling small to large,simple to complex continuous environments,whereas it was very tedious for the previous method to achieve.展开更多
文摘Intelligent penetration testing is of great significance for the improvement of the security of information systems,and the critical issue is the planning of penetration test paths.In view of the difficulty for attackers to obtain complete network information in realistic network scenarios,Reinforcement Learning(RL)is a promising solution to discover the optimal penetration path under incomplete information about the target network.Existing RL-based methods are challenged by the sizeable discrete action space,which leads to difficulties in the convergence.Moreover,most methods still rely on experts’knowledge.To address these issues,this paper proposes a penetration path planning method based on reinforcement learning with episodic memory.First,the penetration testing problem is formally described in terms of reinforcement learning.To speed up the training process without specific prior knowledge,the proposed algorithm introduces episodic memory to store experienced advantageous strategies for the first time.Furthermore,the method offers an exploration strategy based on episodic memory to guide the agents in learning.The design makes full use of historical experience to achieve the purpose of reducing blind exploration and improving planning efficiency.Ultimately,comparison experiments are carried out with the existing RL-based methods.The results reveal that the proposed method has better convergence performance.The running time is reduced by more than 20%.
文摘Under the requirement of high-quality development, the research method of integrated model planning for offshore oil and gas exploration and development suitable for the western South China Sea is put forward. Based on the new round of resource evaluation and exploration and development research in the western South China Sea, the in-depth research on underground oil and gas resources, surface development facilities, external factors and economic indexes are carried out to clarify the industrial layout of oil and gas development. The potential and prospect of oil and gas exploration and development were implemented, and the main external factors and corresponding measures affecting the planning were clarified in this paper. The economic evaluation model suitable for the region is established based on the analysis of internal rate of return, comprehensive barrel oil cost, critical price, financial net present value and other important indicators, and a set of planning and research methods suitable for the integration of exploration and development in the western South China Sea is finally formed. This method has been applied to the replacement reserve study of Weizhou X and Weizhou Y oil fields. It is found that the planned reserves and production are consistent with the actual ones, and good practical results have been achieved.
文摘In order to realize the explorer autonomy, the software architecture of autonomous mission management system (AMMS) is given for the deep space explorer, and the autonomous mission planning system, the kernel part of this architecture, is designed in detail. In order to describe the parallel activity, the state timeline is introduced to build the formal model of the planning system and based on this model, the temporal constraint satisfaction planning algorithm is proposed to produce the explorer’s activity sequence. With some key subsystems of the deep space explorer as examples, the autonomous mission planning simulation system is designed. The results show that this system can calculate the executable activity sequence with the given mission goals and initial state of the explorer.
文摘The bidding blocks are distributed in different regions of China,There are seven blocks in W est China,and seven blocks in Northeast China,the other twelve blocks are from North and Central China.All the blocks are located in prospective sedimentary basins with different geological condi-tions,some are from oil produced basin such as Bohai Bay Basin which is a prolific basin,it's production accounts for 50%in total prodcuction of China.Based on estimation,the total potential resource of oil is 3.55 billion tons and gas is 800 billion cubic meters in bidding areas.As far as the exploratory objectives are concerned,there are Paleozoic.Mesozoic and Cenozoic strata,as well as continental clastic and marine一carbonate re-servoir.These provide more choices for foreign companies.In addition,most of bidding blocks are adjacent to transport lines,so communication and petroleum transportation are very convenient.
基金funded by International University,VNU-HCM under Grant Number T2021-02-IEM.
文摘Path planning is a prevalent process that helps mobile robots find the most efficient pathway from the starting position to the goal position to avoid collisions with obstacles.In this paper,we propose a novel path planning algorithm-Intermediary RRT*-PSO-by utilizing the exploring speed advantages of Rapidly exploring Random Trees and using its solution to feed to a metaheuristic-based optimizer,Particle swarm optimization(PSO),for fine-tuning and enhancement.In Phase 1,the start and goal trees are initialized at the starting and goal positions,respectively,and the intermediary tree is initialized at a random unexplored region of the search space.The trees were grown until one met the other and then merged and re-initialized in other unexplored regions.If the start and goal trees merge,the first solution is found and passed through a minimization process to reduce unnecessary nodes.Phase 2 begins by feeding the minimized solution from Phase 1 as the global best particle of PSO to optimize the path.After simulating two special benchmark configurations and six practice configurations with special cases,the results of the study concluded that the proposed method is capable of handling small to large,simple to complex continuous environments,whereas it was very tedious for the previous method to achieve.
