In the training process of manipulator path planning algorithm， the training efficiency of manipulator path planning is low due to the huge action space and state space leading to sparse rewards， and it becomes challenging to evaluate the value of both states and actions given the immense number of states and actions. To address the above problems， a robotic manipulator planning algorithm based on SAC （Soft Actor-Critic） reinforcement learning was proposed. The learning efficiency was improved by incorporating the demonstrated path into the reward function so that the manipulator imitated the demonstrated path during reinforcement learning， and the SAC algorithm was used to make the training of the manipulator path planning algorithm faster and more stable. The proposed algorithm and Deep Deterministic Policy Gradient （DDPG） algorithm were used to plan 10 paths respectively， and the average distances between paths planned by the proposed algorithm and the DDPG algorithm and the reference paths were 0.8 cm and 1.9 cm respectively. The experimental results show that the path imitation mechanism can improve the training efficiency， and the proposed algorithm can better explore the environment and make the planned paths more reasonable than DDPG algorithm.

Resource load prediction with high accuracy can provide a basis for real-time task scheduling， thus reducing energy consumption. However， most prediction models for time series of resource load make short-term or long-term prediction by extracting the long-time series dependence characteristics of time series and neglecting the short-time series dependence characteristics of time series. In order to make a better long-term prediction of resource load， a new edge computing resource load prediction model based on long-short time series feature fusion was proposed. Firstly， the Gram Angle Field （GAF） was used to transform time series into image format data， so as to extract features by Convolutional Neural Network （CNN）. Then， the CNN was used to extract spatial features and short-term data features， the Long Short-Term Memory （LSTM） network was used to extract the long-term time series dependent features of time series. Finally， the extracted long-term and short-term time series dependent features were fused through dual-channel to realize long-term resource load prediction. Experimental results show that， the Mean Absolute Error （MAE）， Root Mean Square Error （RMSE） and R-squared（R²） of the proposed model for CPU resource load prediction in Alibaba cloud clustering tracking dataset are 3.823， 5.274， and 0.815 8 respectively. Compared with the single-channel CNN and LSTM models， dual-channel CNN+LSTM and ConvLSTM+LSTM models， and resource load prediction models such as LSTM Encoder-Decoder （LSTM-ED） and XGBoost， the proposed model can provide higher prediction accuracy.

In order to realize the rapid analysis of massive real-time data, a Distributed Real-time Data Analysis System (DRDAS) was designed, which resolved the collection, storage and real-time analysis for mass concurrent data. And according to the operation principle of Spark Streaming, a dynamic sampling K-means parallel algorithm was proposed, which could quickly and efficiently detect all kinds of DDoS (Distributed Denial of Service) attacks. The experimental results show that the DRDAS has good scalability, fault tolerance and real-time processing ability, and along with new K-means parallel algorithm, the DRDAS can real-time detect various DDoS attacks, and shorten the detecting time of attacks.

Focusing on the issue that division is complex and needs a large delay to compute, a kind of method for designing the unit of high-performance double precision floating point divider based on Goldschmidt's algorithm was proposed and it supported IEEE-754 standard. Firstly, it was analyzed that how to compute division using Goldschmidt's algorithm and the error produced during iterative operation. Then, the method for controlling error was proposed. Secondly, bipartite reciprocal tables were adopted to calculate initial value of iteration with area saving, and parallel multipliers were adopted in the iterative unit for accelerating. Lastly, the executed station was divided reasonably and it made floating point divider supporting pipeline execution with state machine controlling. So, the speed of divider was improved. The experimental results show that the double precision floating point divider adopted 14-bit iterative initial value pipeline structure, its synthesis cell area is 84902.2618 μm², the running frequency is up to 2.2 GHz with 40 nm technology. Compared with 8-bit iterative initial value pipeline structure, computing speed is increased by 32.73% and area is increased by 5.05%. The delay of a double precision floating division instruction is 12 cycles, and it is decreased to 3 cycles in pipeline execution. Compared with the divider based on SRT algorithm implemented in other processers, data throughput is improved by 3-7 times. Compared with the divider based on Goldschmidt's algorithm implemented in other processers, data throughput is improved by 2-3 times.

For the traditional player skill estimation algorithms based on probabilistic graphical model neglect the first-move advantage (or home play advantage) which affects estimation accuracy, a new method to model the first-move advantage was proposed. Based on the graphical model, the nodes of first-move advantage were introduced and added into player's skills. Then, according to the game results, true skills and first-move advantage of palyers were caculated by Bayesian learning method. Finally, predictions for the upcoming matches were made using those estimated results. Two real world datasets were used to compare the proposed method with the traditional model that neglect the first-move advantage. The result shows that the proposed method can improve average estimation accuracy noticeably.

To remove the noise of optical images while preserving its fine details, the extant object scale was upgraded to the decimal object scale for reflecting the size of local object structure more accurately, and a hybrid image filter which contains two parts was proposed. The first part was an adaptive Gaussian filter based on decimal object scale, the scale of the Gaussian kernel and the mask size of filtering were controlled adaptively by the decimal object scale. The second part was an adaptive median filter based on decimal object scale, and the impulse noise points which were selected adaptively by the decimal object scale were filtered. The weakness of the first part in suppressing the impulse noise was remedied by the second part. Both theory analysis and simulation results show that the presented method can suppress various point-like noise and it is superior to several traditional methods in preserving the fine details and signal to noise ratio.

For the purpose of energy conservation, a new routing algorithm named MH-TO was proposed based on the idea of the minimum hop routing. The new algorithm optimized the network topology through a power control method of half-match mechanism. Then a "tower model" was introduced to make that all nodes obtain minimum hop information. The packet was sent by the minimum hop path to the sink node when routing. According to the analysis and the simulation results, compared with the self-organized algorithm based on minimum hop, the new algorithm can save energy and balance energy consumption, which extends the life cycle of WSN.

In terms of Heterogeneous database synchronization demand, a synchronization solution was proposed based on the study of JMS message mechanism. This solution actualized asynchronously the synchronic data renewal by two parts: messages customization using XML language, database read-write using JNDI interface technology. The experimental results show that this new method effectively deals with the above problems.

RTS/CTS mechanism in 802.11 protocol can solve the hidden nodes problem in wireless networks. The vulnerabilities in RTS/CTS mechanism were analyzed. Due to the lack of authentication in RTS/CTS handshakes, attackers can launch denial of service attacks by continuously sending spurious RTS/CTS frames with large enough NAV values. Based on theoretical analysis, experiment was implemented in practical wireless networks using aircrack-ng developing toolkit. The experimental results show that it is feasible to launch denial of service attacks against RTS/CTS mechanism. This vulnerability can be utilized by attacker at any time and should be paid more attention.

Dealing with emergent disaster is a typical discrete event system. Based on the analyses of Discrete Event System Specification (DEVS) formalism, the DEVS simulation model of material supply in the emergent disaster was made. The simulation entities were analyzed. The simulation flow was designed. The structures of coupled model and main atomic models were given. And the simulation test of this model was completed in CD++. The reasonable simulation results were obtained. It laid the foundation for the development of simulation training on the services of emergent disaster.

Extraction method is one of the classical methods that achieve the minimum coverage in two-level logic synthesis. But as the output variables and the prime implicant grow up, both the long processing time and the resource requirement become the major problems to be resolved with the extraction method. To overcome these drawbacks, a new ameliorated algorithm for the coverage minimization was presented in this thesis on the basis of the extraction method theory, which was adapted to the processing of mass data. Based on the intersection iterative and the local search algorithm theory, two major phases in this algorithm were improved, including the extremal selecting and the branches processing. As a result, by using the existing computer resources, testing shows a promising result and the improved algorithm is superior to the others multi-output logic function optimizations.

Since confliction exists in rule database, non-conflict rule database is created at first. Based on Hierarchical Intelligent Cuttings algorithm and non-conflict function, a novel IP packet classification named HICNCH( the algorithm based on Hierarchical Intelligent Cuttings and Non-Collision Hash) is proposed. Also the least square method is proposed to improve the rule of cutting tree and cutting efficiency is improved greatly. Compared with other classic algorithm, our algorithm has lower time and space cost. The comprehensive performance has been improved a lot.