Edge-Cloud Co-Evolutionary Algorithms for Distributed Data-Driven Optimization Problems.

Surrogate-assisted evolutionary algorithms (EAs) have been proposed in recent years to solve data-driven optimization problems. Most existing surrogate-assisted EAs are for centralized optimization and do not take into account the challenges brought by the distribution of data at the edge of networks in the era of the Internet of Things. To this end, we propose edge-cloud co-EAs (ECCoEAs) to solve distributed data-driven optimization problems, where data are collected by edge servers. Specifically, we first propose a distributed framework of ECCoEAs, which consists of a communication mechanism, edge model management, and cloud model management. This communication mechanism is to avoid deadlock during the collaboration of edge servers and the cloud server. In edge model management, the edge models are trained based on local historical data and data composed of new solutions generated by co-evolutionary and their real evaluation values. In cloud model management, the black-box prediction functions received from edge models are used to find promising solutions to guide the edge model management. Moreover, two ECCoEAs are implemented, which proves the generality of the framework. To verify the performance of algorithms for distributed data-driven optimization problems, we design a novel benchmark test suite. The performance on the benchmarks and practical distributed clustering problems shows the effectiveness of ECCoEAs.

[Influence of different slope position and profile in Disporopsis pernyi forest land on soil microbial biomass and enzyme activity in southwest Karst mountain of China ].

Soil microbial biomass and enzyme activity are important parameters to evaluate the quality of the soil environment. The goal of this study was to determine the influence of different slope position and section in Disporopsis pernyi forest land on the soil microbial biomass and enzyme activity in southwest Karst Mountain. In this study, we chose the Dip forest land at Yunfo village Chengdong town Liangping country Chongqing Province as the study object, to analyze the influence of three different slope positions [Up Slope(US), Middle Slope(MS), Below Slope(BS)] and two different sections-upper layer(0-15 cm) and bottom layer(15-30 cm) on the soil microbial biomass carbon (SMBC), soil microbial biomass nitrogen (SMBN), microbial carbon entropy (qMBC), microbial nitrogen entropy (qMBN) , catalase(CAT), alkaline phosphatase (ALK), urease(URE), and invertase(INV). The results showed that the same trend (BS > MS > US) was found for SMBC, SMBN, qMBC, qMBN, CAT and INV of upper soil layer, while a different trend (BS > US > MS) was observed for ALK. In addition, another trend (MS > US > BS) was observed for URE. The same trend (BS > MS >US) was observed for SMBN, qMBN, CAT, ALK, URE and INV in bottom layer, but a different trend (MS > BS > US) was observed for SMBC and qMBC. The SMBC, SMBN, CAT, ALK, URE and INV manifested as upper > bottom with reduction of the section, while qMBC and qMBN showed the opposite trend. Correlation analysis indicated that there were significant (P <0.05) or highly significant (P < 0.01) positive correlations among SMBC in different slope position and section, soil enzyme activity and moisture. According to the two equations of regression analysis, SMBC tended to increase with the increasing CAT and ALK, while decreased with the increasing pH. Then SMBN tended to increase with the increasing URE and INV.

[Dynamics of microbes and enzyme activities during litter decomposition of Pinus massoniana forest in mid-subtropical area].

The dynamics of microbial quantity and enzyme activities during decomposition process of masson pine (Pinus massoniana) leaf litter, oak (Quercus aliena) leaf litter and their mixture (at natural mass ratio, 8: 2) were studied with litterbag method in the pinus forest typical vegetations of mid-subtropical Jinyun Mountain nature reserve. The results showed that the decomposition constant K of leaf litter ranked as follows: mixture (0.94) > oak (0.86) > masson pine (0.67). Microbial groups and enzyme activity exhibited some similar responses to the litter decomposition process. After 135 days, fungal and microbial quantities reached the maximum while bacterial and actinomycetic number reached the minimum, presumably due to the high-temperature environment. The correlative analysis showed that the cellulase and acid phosphatase activity had significant positive relationship with the dry weight remaining rate (P < 0.05), which played a key role for microbes in utilizing the substrates at early stages. Meanwhile, the polyphenol oxidase activity showed highly significant negative correlation with the dry weight remaining rate (P < 0.01) in pine litter and the mixed litter, which worked on further decay of recalcitrant compound at late stages. Through the whole process, the microbial quantity and polyphenol oxidase activity were generally in the order of oak litter > mixed litter > pine litter, while in most cases the oak litter showed the lowest acid phosphatase activity, the ranking of which had some differences with the order of the decomposition constant K, indicating that litter decomposition was the result of integrated action by microbe and many kinds of enzymes. The results suggested that differences in litter composition and seasonal climate strongly influenced the microbial communities and the ecosystem processes they mediate. When mixed with oak leaves in given stand, the pine litter had an accelerating decomposition rate, which might depend on the higher microbial quantity and polyphenol oxidase activity in the mixed litter.