针对电力行业碳排放量预测问题,在传统人工蜂群算法中引入遗传学习策略进行改进,提出一种基于进化人工蜂群算法优化的随机森林回归预测模型。首先在可拓展随机性环境影响评估模型(stochastic imacts by regression on population afflue...针对电力行业碳排放量预测问题,在传统人工蜂群算法中引入遗传学习策略进行改进,提出一种基于进化人工蜂群算法优化的随机森林回归预测模型。首先在可拓展随机性环境影响评估模型(stochastic imacts by regression on population affluence and technlogy,STIRPAT)模型基础上确定电力行业碳排放量影响因素,将其作为预测模型的输入自变量,继而利用进化人工蜂群算法优化随机森林回归模型,从而避免模型参数主观设置不合理对预测精度的不利影响,最后运用参数优化后的模型对电力行业碳排放量进行预测。实际测算数据验证结果表明,该模型可以准确反映电力行业未来碳排放趋势,并且与其他预测模型相比,预测精度更高、优势更加明显,能够为节能减排政策制定提供参考借鉴。展开更多
Due to large size and different popularity for different part of the video, most proxy caches for streaming medias cache only a part of the video. Thus, an accurate understanding on the internal popularity distributio...Due to large size and different popularity for different part of the video, most proxy caches for streaming medias cache only a part of the video. Thus, an accurate understanding on the internal popularity distribution of media objects in streaming applications is very important for the development of efficient cache mechanisms. This letter shows that the internal popularity of popular streaming media obeys a k-transformed Zipf-like distribution through analyzing two 6-month long traces recorded at different streaming video servers of an entertainment video-on-demand provider. This empirical model can be used to design an efficient cach- ing algorithm.展开更多
文摘针对电力行业碳排放量预测问题,在传统人工蜂群算法中引入遗传学习策略进行改进,提出一种基于进化人工蜂群算法优化的随机森林回归预测模型。首先在可拓展随机性环境影响评估模型(stochastic imacts by regression on population affluence and technlogy,STIRPAT)模型基础上确定电力行业碳排放量影响因素,将其作为预测模型的输入自变量,继而利用进化人工蜂群算法优化随机森林回归模型,从而避免模型参数主观设置不合理对预测精度的不利影响,最后运用参数优化后的模型对电力行业碳排放量进行预测。实际测算数据验证结果表明,该模型可以准确反映电力行业未来碳排放趋势,并且与其他预测模型相比,预测精度更高、优势更加明显,能够为节能减排政策制定提供参考借鉴。
基金Supported by the National Natural Science Foundation of China (No.60302004), the Australian Research Council (Grant LX0240468) and Natural Science Foun-dation of Hubei, China (No.2005ABA264).
文摘Due to large size and different popularity for different part of the video, most proxy caches for streaming medias cache only a part of the video. Thus, an accurate understanding on the internal popularity distribution of media objects in streaming applications is very important for the development of efficient cache mechanisms. This letter shows that the internal popularity of popular streaming media obeys a k-transformed Zipf-like distribution through analyzing two 6-month long traces recorded at different streaming video servers of an entertainment video-on-demand provider. This empirical model can be used to design an efficient cach- ing algorithm.