Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devi...Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.展开更多
Rendezvous is a blind process establishing a communication link on a common channel between a pair of nodes in cognitive radio networks. We propose two guaranteed rendezvous algorithms for cognitive radio networks und...Rendezvous is a blind process establishing a communication link on a common channel between a pair of nodes in cognitive radio networks. We propose two guaranteed rendezvous algorithms for cognitive radio networks under both single-radio and multi-radio scenarios with an asynchronous setting. For single-radio scenario, each cycle length is a prime number associated with a channel hopping sequence.The rendezvous can be guaranteed as long as the IDs of the two nodes are different. For multi-radio scenario, we propose a cycle length and rotation based rendezvous algorithm. Each node generates a channel hopping sequence with only one cycle length. Then these radios of each nodes rotate on the generated sequence with different rotation numbers at each hopping cycle. The rendezvous between two nodes is guaranteed as long as they have different cycle lengths or the same cycle length with different number of rotations. We conduct simulations on three metrics and the results show that the proposed algorithms outperform the existing ones.展开更多
Conventional optical burst switching(OBS)technique adopts purely statistical multiplex mechanismso that the bursts collide with each other very easily.To address this problem,a novel proactive con-tention avoidance sc...Conventional optical burst switching(OBS)technique adopts purely statistical multiplex mechanismso that the bursts collide with each other very easily.To address this problem,a novel proactive con-tention avoidance scheme is proposed,which assigns dedicated wavelengths to each ingress node,then st-numbering algorithm is used to construct the traffic load balanced spanning trees .In this way,contentioncan be eliminated at ingress nodes,and the amount of bursts that could be accommodated by ingressnodes will be maximized.Further,those unused wavelengths left by traffic load balanced spanning treeare also organized as partial trees to carry bursts,thus the link utilization can be improved effectively.Simulation result shows that our scheme can improve the burst loss performance significantly without thewavelength converters or optical buffers comparing to other popular routing and wavelength assignment(RWA)algorithms.展开更多
文摘Load forecasting is of great significance to the development of new power systems.With the advancement of smart grids,the integration and distribution of distributed renewable energy sources and power electronics devices have made power load data increasingly complex and volatile.This places higher demands on the prediction and analysis of power loads.In order to improve the prediction accuracy of short-term power load,a CNN-BiLSTMTPA short-term power prediction model based on the Improved Whale Optimization Algorithm(IWOA)with mixed strategies was proposed.Firstly,the model combined the Convolutional Neural Network(CNN)with the Bidirectional Long Short-Term Memory Network(BiLSTM)to fully extract the spatio-temporal characteristics of the load data itself.Then,the Temporal Pattern Attention(TPA)mechanism was introduced into the CNN-BiLSTM model to automatically assign corresponding weights to the hidden states of the BiLSTM.This allowed the model to differentiate the importance of load sequences at different time intervals.At the same time,in order to solve the problem of the difficulties of selecting the parameters of the temporal model,and the poor global search ability of the whale algorithm,which is easy to fall into the local optimization,the whale algorithm(IWOA)was optimized by using the hybrid strategy of Tent chaos mapping and Levy flight strategy,so as to better search the parameters of the model.In this experiment,the real load data of a region in Zhejiang was taken as an example to analyze,and the prediction accuracy(R2)of the proposed method reached 98.83%.Compared with the prediction models such as BP,WOA-CNN-BiLSTM,SSA-CNN-BiLSTM,CNN-BiGRU-Attention,etc.,the experimental results showed that the model proposed in this study has a higher prediction accuracy.
基金supported in part by NSF under the grant CNS-1526152
文摘Rendezvous is a blind process establishing a communication link on a common channel between a pair of nodes in cognitive radio networks. We propose two guaranteed rendezvous algorithms for cognitive radio networks under both single-radio and multi-radio scenarios with an asynchronous setting. For single-radio scenario, each cycle length is a prime number associated with a channel hopping sequence.The rendezvous can be guaranteed as long as the IDs of the two nodes are different. For multi-radio scenario, we propose a cycle length and rotation based rendezvous algorithm. Each node generates a channel hopping sequence with only one cycle length. Then these radios of each nodes rotate on the generated sequence with different rotation numbers at each hopping cycle. The rendezvous between two nodes is guaranteed as long as they have different cycle lengths or the same cycle length with different number of rotations. We conduct simulations on three metrics and the results show that the proposed algorithms outperform the existing ones.
基金supported by the National Natural Science Foundation of China(No.60572050)the National High Technology Research and Development Programme of China(No.2008AA01Z211)
文摘Conventional optical burst switching(OBS)technique adopts purely statistical multiplex mechanismso that the bursts collide with each other very easily.To address this problem,a novel proactive con-tention avoidance scheme is proposed,which assigns dedicated wavelengths to each ingress node,then st-numbering algorithm is used to construct the traffic load balanced spanning trees .In this way,contentioncan be eliminated at ingress nodes,and the amount of bursts that could be accommodated by ingressnodes will be maximized.Further,those unused wavelengths left by traffic load balanced spanning treeare also organized as partial trees to carry bursts,thus the link utilization can be improved effectively.Simulation result shows that our scheme can improve the burst loss performance significantly without thewavelength converters or optical buffers comparing to other popular routing and wavelength assignment(RWA)algorithms.
