Effects of constant light and dark conditions on the locomotor activity,body mass,and body temperature rhythms of Eurasian Tree Sparrows(Passer montanus)

Light is an essential environmental cue influencing the endogenous circadian clocks that regulate behavioral and physiological processes in animals.Despite extensive research on the circadian rhythms of avian behavior and physiology,the mechanisms by which they adapt and adjust to abnormal photoperiod conditions,such as artificial light,have yet to be fully elucidated.Here,the circadian rhythms of the body mass,activity,and core and peripheral body temperatures of the Eurasian Tree Sparrow(Passer montanus,ETS)-a diurnal passerine-were examined under three different lighting conditions:constant light(LL),constant darkness(DD),and normal light-dark cycles(LD).Our results showed that the activity,body mass,core,tarsometatarsus,and eye temperatures of the ETSs varied significantly with treatment,time,and the interaction between treatment and time;however,there was no significant change in body mass in response to the interaction between time and treatment.Under LD conditions,the ETSs exhibited significant circadian rhythms in activity and core,tarsometatarsus,and eye temperatures.Under LL conditions,only the core temperature exhibited significant rhythmicity.Under DD conditions,there were no significant circadian rhythms in activity,body mass,and eye temperature;however,the core and tarsometatarsus temperatures remained rhythmic.Our results indicate that the core body temperature rhythm of ETS is endogenous and can be maintained under abnormal photoperiods.In contrast,the activity and body surface temperature,uncoupled from the core body temperature under abnormal photoperiod conditions,strongly depend on light.These results differ from those of other diurnal avian species,suggesting a unique coping mechanism of ETS in response to an abnormal photoperiod.

Effect of urbanization on the abundance and distribution of Tree Sparrows (Passer montanus) in Beijing

With rapid urbanization occurring throughout China,the existence of Tree Sparrows (Passer montanus) in big cities is likely to be affected by a decrease in habitat and food availability.Can the urban Tree Sparrow adapt to these changes? To elucidate this question,we studied the effect of urbanization on the abundance and distribution of Tree Sparrows in Beijing.We found the abundance of the Tree Sparrow negatively correlated with an urbanization score.Sparrow abundance was very low in residential areas with high-rise buildings,commercial centers and main roads,while their numbers were significantly higher in parks,university campuses,low building residential and suburban areas.Environmental factors within the 50 m and 200 m scales were most suitable in predicting the distribution of Tree Sparrows during winter,while factors within 50 m and 400 m scales are suitable during the breeding season.During winter,the number of conifer trees and pedestrians were the major factors at the 50 m scale,while the area of high-rise buildings and vegetation become the predominant factors on a 200 m scale.Alternatively,during the breeding season the area of low buildings and the number of conifers and pedestrians were the main factors on the 50 m scale while the area of high-rise buildings and vegetation remained the most important factors on the 400 m scale.These results indicate that highly urbanized areas are not suitable habitats for the Tree Sparrow,although this species can adapt to human environments.Food and nest sites for urban birds should be considered in urban planning of big cities in developing countries.

Relationship Between Organ Masses and Basal Metabolic Rate (BMR) in Tree Sparrows (Passer montanus)

BMR （basal metabolic rate）, body mass and organ masses of tree sparrows （Passer montanus） were measured to analyze the correlation between organ masses and BMR in tree sparrows, and to evaluate the underlying physiological causes of difference in BMR. Adult tree sparrows were live-trapped by mist net in Qiqihar City, Heilongjiang Province （47°29′N, 124°02′E）. The closed circuit respirometer was used to measure the metabolic rate （MR）, and controlled the ambient temperature by using a water bath （±0.5℃）. Body masses were measured to the nearest 0.01 g before and after BMR measurements with a Sartorius balance （model BT25S）. The mean value was recorded as body mass. Wet and dry masses of several organs were measured, too. BMR was （4.276± 0.385） mL O2/（g·h） and mean body mass was （18.522±0.110） g. Since not all the variables were normal distributed, a log10- transformation of those variables was employed to linearize them, prior to analyses. Simple regression analyses indicated that most organ masses showed a significant high correlation with body mass. Both the small intestine and rectum masses were notable exception to that trend. The body-mass-adjusted residual analysis showed that only the kidney wet mass, brain mass, stomach mass, small mass and rectum wet mass correlated with BMR. In addition, correlations between several organ masses and BMR were observed. Because of the inter-correlations of organ masses, a principal component analysis （PCA） was performed to redefine the morphological variability. The first four components whose eigenvalues were greater than 1 could explain 75.2% variance of BMR. The first component, whose proportion reached 30.19%, was affected mainly by stomach mass, small intestine mass and rectum mass. Therefore, the results supported the hypothesis that BMR was controlled by some ＂expensive metabolic＂ organs

Coping with extremes:lowered myocardial phosphofructokinase activities and glucose content but increased fatty acids content in highland Eurasian Tree Sparrows

Background:Efficient and selective utilization of metabolic substrates is one of the key strategies in high-altitude animals to cope with hypoxia and hypothermia.Previous findings have shown that the energy substrate utilization of highland animals varies with evolutionary history and phylogeny.The heart is a proxy for the cardiopulmonary system,and the metabolic substrate utilization in the myocardium is also under the strong selective pressure of chronically hypoxic and hypothermic environments.However,little information is available on the physiological adjustments in relation to metabolic substrate utilization in the myocardium for coping with high-altitude environments.Methods:We compared the metabolic enzyme activities,including hexokinase(HK),phosphofructokinase(PFK),pyruvate kinase(PK),citrate synthase(CS),carnitine palmitoyl transferase 1(CPT-1),lactic dehydrogenase(LDH),and creatine kinase(CK),and metabolic substrate contents including glucose(Glu),triglyceride(TG),and free fatty acid(FFA)in the myocardium of a typical human commensal species,Eurasian Tree Sparrows(Passer montanus)between the Qinghai-Tibet Plateau(the QTP,3230 m)and low altitude population(Shijiazhuang,80 m),and between sexes.Results:Among the seven metabolic enzymes and three substrates investigated,we identified no significant differences in PK,CPT-1,HK,CS,LDH,and CK activities and TG content of the myocardium between high and low altitude populations.However,the QTP sparrows had significantly lower Glu content and PFK activities but higher FFA content relative to their lowland counterparts.In addition,male sparrows had higher myocardial HK and CS activities relative to females,independent of altitude.Conclusions:Our results showed that the QTP sparrows elevated fatty acid utilization rather than glucose preference in the myocardium relative to lowland counterpart,which contributes to uncovering both the physiological adjustments for adapting to the extreme conditions of the QTP,intraspecifically.

A high incidence of non-cavity nesting in an introduced population of House Sparrows suggests that the species should not be constrained by cavity-nest site availability

Background: The House Sparrow(Passer domesticus) has undergone dramatic population declines in many parts of Europe.It has been widely hypothesised that a lack of cavity nest sites has contributed to this decline.However the idea of the House Sparrow being nest site limited is somewhat incompatible with the long history of nest site plasticity in the species.Methods: The nest-site selection in a population of non-native House Sparrows introduced to Australia from Europe just over 150 years ago was characterised.The prevalence of non-cavity nesting was quantified,and nest-site selection in terms of landscape and nesting structure were described.Results: Flexible nesting behaviors were reported over a range of different landscapes and a surprisingly high rate of nesting in vegetation(43%) was documented.Most nests found in vegetation were not in cavities,but were woven into the foliage and supported by branches and stems.Conclusion: The high rate of vegetation nesting indicates that in this introduced population,the House Sparrow is unlikely to be constrained by cavity-nest site availability.The high degree of nest site plasticity in the Australian population may suggest that European House Sparrows have the potential to shift away from their proclivity for cavity nests.Future work in Europe should examine the incidence of non-cavity nesting in House Sparrows more closely,and perhaps reconsider the idea that House Sparrows are nest-site constrained.

Survey on Parasites in Sparrows of Amol （Mazandaran Province, Iran）

In order to survey on sparrows parasites （Passer domesticus）, 100 samples were collected from the citrus gardens of Amol＇s City. The surface of their body checked for presence of ectoparasites. The blood samples took from their wings for blood parasites. At the laboratory, the body of sparrows opened and the gastrointestinal checked for endoparasites. The intestine opened and scratched carefully to find worms. Worms kept in alcohol-glycerin （10%）. Eggs ＆ oocysts of the parasites checked, by fecal floatation test. The result shows that the infection with Railletina is 1%, Ascaridia galli （2%）, Heterakis gallinarum （4%）, eggs of A. galli （5%）, oocyst of Eimeri （28%）, Dermanyssus gallinae （1%）. 11% of the sparrows infected with Plasmodium in their bloods.

一种基于CatBoost优化的光伏阵列故障诊断模型

大部分光伏电站地处偏僻、地形复杂的区域,受到外界环境的影响,易发生各种故障.而传统的光伏阵列故障诊断方法存在精度不高以及光伏数据利用率低等问题.针对以上问题,本文先是通过引入Levy飞行策略和步长因子动态调整策略改进麻雀搜索算法(Sparrow Search Algorithm,SSA),降低SSA算法陷入局部最优的风险,提升SSA算法的寻优能力.然后采用改进的Levy步长调整麻雀搜索算法(Levy Adjustment Sparrow Search Algorithm,LASSA)对CatBoost模型关键超参数进行寻优,提出了一种基于CatBoost并以LASSA为优化策略的光伏阵列故障诊断模型LASSA-CatBoost,以实现光伏阵列的短路、开路、老化和阴影遮挡故障的精确诊断.实验结果表明,LASSA-CatBoost模型的故障诊断准确率为99.7%,相较于优化前的CatBoost模型,准确率提高了3.6%.与现有的光伏阵列故障诊断模型相比,LASSA-CatBoost模型的准确性和稳定性更高.

What is the sound of fear？ Behavioral responses of white-crowned sparrows Zonotrichia leucophrys to synthesized nonlinear acoustic phenomena

Fear and anxiety may be adaptive responses to life-threatening situations, and animals may communicate fear to others vocally. A fundamental understanding of fear inducing sounds is important for both wildlife conservation and management because it helps us understand how to design repellents and also how （and why） animals may be negatively impacted by anthropogenic sounds. Nonlinear phenomena--sounds produced by the desynchronization of vibrations in a sound production system-are commonly found in stress-induced animal vocalizations, such as in alarm calls, mobbing calls, and fear screams. There are several functional hypotheses for these nonlinear phenomena. One specific hypothesis is the unpredictability hypothesis, which suggests that because nonlinear phenomena are more variable and somewhat unpredictable, animals are less likely to habituate to them. Animals should, therefore, have a prolonged response to sounds with nonlinear phenomena than sounds without them. Most of the studies involving nonlinear phenomena have used mammalian subjects and conspecific stimuli. Our study fo- cused on white-crowned sparrows （Zonotrichia leucophrys ssp. oriantha） and used synthesized acoustic stimuli to investigate behavioral responses to stimuli with and without nonlinear phenomena. We predicted that birds would be less relaxed after hearing a stimulus with a nonlinear component. We calculated the difference from baseline of proportion of time spent in relaxed behaviors and performed pair-wise comparisons between a pure tone control stimulus and each of three experimental stimuli, including a frequency jump up, a frequency jump down, and white noise. These comparisons showed that in the 30q50 s after the playback experiment, birds were significantly less relaxed after hearing noise or an abrupt frequency jump down an octave but not an abrupt frequency jump up an octave or a pure tone. Nonlinear phenomena, therefore, may be generally arousing to animals and may explain why these acoustic properties are commonly found in animal signals associated with fear [Current Zoology 60 （4）： 534-541, 2014].

Dynamic plugging regulating strategy of pipeline robot based on reinforcement learning

Pipeline isolation plugging robot (PIPR) is an important tool in pipeline maintenance operation. During the plugging process, the violent vibration will occur by the flow field, which can cause serious damage to the pipeline and PIPR. In this paper, we propose a dynamic regulating strategy to reduce the plugging-induced vibration by regulating the spoiler angle and plugging velocity. Firstly, the dynamic plugging simulation and experiment are performed to study the flow field changes during dynamic plugging. And the pressure difference is proposed to evaluate the degree of flow field vibration. Secondly, the mathematical models of pressure difference with plugging states and spoiler angles are established based on the extreme learning machine (ELM) optimized by improved sparrow search algorithm (ISSA). Finally, a modified Q-learning algorithm based on simulated annealing is applied to determine the optimal strategy for the spoiler angle and plugging velocity in real time. The results show that the proposed method can reduce the plugging-induced vibration by 19.9% and 32.7% on average, compared with single-regulating methods. This study can effectively ensure the stability of the plugging process.

Research on Evacuation Path Planning Based on Improved Sparrow Search Algorithm

Reducing casualties and property losses through effective evacuation route planning has been a key focus for researchers in recent years.As part of this effort,an enhanced sparrow search algorithm(MSSA)was proposed.Firstly,the Golden Sine algorithm and a nonlinear weight factor optimization strategy were added in the discoverer position update stage of the SSA algorithm.Secondly,the Cauchy-Gaussian perturbation was applied to the optimal position of the SSA algorithm to improve its ability to jump out of local optima.Finally,the local search mechanism based on the mountain climbing method was incorporated into the local search stage of the SSA algorithm,improving its local search ability.To evaluate the effectiveness of the proposed algorithm,the Whale Algorithm,Gray Wolf Algorithm,Improved Gray Wolf Algorithm,Sparrow Search Algorithm,and MSSA Algorithm were employed to solve various test functions.The accuracy and convergence speed of each algorithm were then compared and analyzed.The results indicate that the MSSA algorithm has superior solving ability and stability compared to other algorithms.To further validate the enhanced algorithm’s capabilities for path planning,evacuation experiments were conducted using different maps featuring various obstacle types.Additionally,a multi-exit evacuation scenario was constructed according to the actual building environment of a teaching building.Both the sparrow search algorithm and MSSA algorithm were employed in the simulation experiment for multiexit evacuation path planning.The findings demonstrate that the MSSA algorithm outperforms the comparison algorithm,showcasing its greater advantages and higher application potential.

Winter Wheat Yield Estimation Based on Sparrow Search Algorithm Combined with Random Forest:A Case Study in Henan Province,China

Precise and timely prediction of crop yields is crucial for food security and the development of agricultural policies.However,crop yield is influenced by multiple factors within complex growth environments.Previous research has paid relatively little attention to the interference of environmental factors and drought on the growth of winter wheat.Therefore,there is an urgent need for more effective methods to explore the inherent relationship between these factors and crop yield,making precise yield prediction increasingly important.This study was based on four type of indicators including meteorological,crop growth status,environmental,and drought index,from October 2003 to June 2019 in Henan Province as the basic data for predicting winter wheat yield.Using the sparrow search al-gorithm combined with random forest(SSA-RF)under different input indicators,accuracy of winter wheat yield estimation was calcu-lated.The estimation accuracy of SSA-RF was compared with partial least squares regression(PLSR),extreme gradient boosting(XG-Boost),and random forest(RF)models.Finally,the determined optimal yield estimation method was used to predict winter wheat yield in three typical years.Following are the findings:1)the SSA-RF demonstrates superior performance in estimating winter wheat yield compared to other algorithms.The best yield estimation method is achieved by four types indicators’composition with SSA-RF)(R^(2)=0.805,RRMSE=9.9%.2)Crops growth status and environmental indicators play significant roles in wheat yield estimation,accounting for 46%and 22%of the yield importance among all indicators,respectively.3)Selecting indicators from October to April of the follow-ing year yielded the highest accuracy in winter wheat yield estimation,with an R^(2)of 0.826 and an RMSE of 9.0%.Yield estimates can be completed two months before the winter wheat harvest in June.4)The predicted performance will be slightly affected by severe drought.Compared with severe drought year(2011)(R^(2)=0.680)and normal year(2017)(R^(2)=0.790),the SSA-RF model has higher prediction accuracy for wet year(2018)(R^(2)=0.820).This study could provide an innovative approach for remote sensing estimation of winter wheat yield.yield.

Fault DiagnosisMethod of Energy Storage Unit of Circuit Breakers Based on EWT-ISSA-BP

Aiming at the problem of energy storage unit failure in the spring operating mechanism of low voltage circuit breakers(LVCBs).A fault diagnosis algorithm based on an improved Sparrow Search Algorithm(ISSA)optimized Backpropagation Neural Network(BPNN)is proposed to improve the operational safety of LVCB.Taking the 1.5kV/4000A/75kA LVCB as an example.According to the current operating characteristics of the energy storage motor,fault characteristics are extracted based on Empirical Wavelet Transform(EWT).Traditional BPNN has problems such as difficulty adjusting network weights and thresholds,being sensitive to initial weights,and quickly falling into local optimal solutions.The Sparrow Search Algorithm(SSA)with self-adjusting weight factors combined with bidirectional mutations is added to optimize the selection of BPNN hyperparameters.The results show that the ISSA-BPNN can accurately and quickly distinguish six conditions of motor voltage reduction:motor voltage increase,motor voltage decrease,energy storage spring stuck,transmission gear stuck,regular state and energy storage spring not locked.It is suitable for fault diagnosis and detection of the energy storage part of LVCB.

Prediction on Failure Pressure of Pipeline Containing Corrosion Defects Based on ISSA-BPNNModel

Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management.Aiming at the shortcomings of the BP Neural Network(BPNN)model,such as low learning efficiency,sensitivity to initial weights,and easy falling into a local optimal state,an Improved Sparrow Search Algorithm(ISSA)is adopted to optimize the initial weights and thresholds of BPNN,and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established.Taking 61 sets of pipelines blasting test data as an example,the prediction model was built and predicted by MATLAB software,and compared with the BPNN model,GA-BPNN model,and SSA-BPNN model.The results show that the MAPE of the ISSA-BPNN model is 3.4177%,and the R2 is 0.9880,both of which are superior to its comparison model.Using the ISSA-BPNN model has high prediction accuracy and stability,and can provide support for pipeline inspection and maintenance.

How will climate change affect the potential distribution of Eurasian tree sparrows Passer montanus in North America？

Habitat suitability models have been used to predict the present and future potential distribution of a variety of spe- cies. Eurasian tree sparrows Passer montanus, native to Eurasia, have established populations in other parts of the world. In North America, their current distribution is limited to a relatively small region around its original introduction to St. Louis, Missouri. We combined data from the Global Biodiversity Information Facility with current and future climate data to create habitat suitability models using Maxent for this species. Under projected climate change scenarios, our models show that the distribution and range of the Eurasian tree sparrow could increase as far as the Pacific Northwest and Newfoundland. This is potentially important in-formation for prioritizing the management and control of this non-native species [Current Zoology 57 （5）： 648--654, 2011].

Can house sparrows recognize familiar or kin-related individuals by scent?

In the last decades, higher attention has been paid to olfactory perception in birds. As a consequence, a handful of avian species have been discovered to use olfaction in different contexts. Nevertheless, we still have a very limited knowledge about the use of odor cues in avian social life, particularly, in the case of songbirds. Here, we investigate if female house sparrows Passer domesticus show any preference for the odor of kin and nonkin conspecifics and we also test a possible role of familiarity based on male see nt in female choice. We performed the experiment with captive birds twice, duri ng the non breeding and breedi ng seas ons. Our results show that female house sparrows strongly avoided the odor of unrelated familiar (UF) males, both in the breeding and nonbreeding seasons. Our results suggest recognition for olfactory stimuli related to familiarity and kin ship. We suggest that avoidance for UF males is associated with previous experie nee in this species. Also, we provided further evidenee to the use of olfaction in passerine species by using a new experimental setup.

Warmer springs, laying date and clutch size of tree sparrows Passer montanus in Croatia

Global surface air temperatures increased during the past 100 years. Many long-term studies of birds have reported a climatic influence on breeding performance. We analysed long-term changes in first laying date and clutch size for first clutches of sedentary, hole-nesting and socially monogamous tree sparrows Passer montanus during 1980-2009 in northwestern Croatia. Laying date advanced and spring temperature increased significantly during the study. Date of laying was significantly correlated with mean air spring temperature and advanced by 8.6 days during the 30 years period. Laying date was delayed in extremely cold, but not in extremely warm springs compared to years with normal temperatures. These results suggest that current climate change including extreme change does not have negative effects on timing of laying or clutch size. In contrast to laying date, clutch size did not vary systematically during the study period or with mean spring air temperature changes [Current Zoology 57 （3）： 414-418, 2011].

Habitat use of urban Tree Sparrows in the process of urbanization:Beijing as a case study

The Tree Sparrow(Passer montanus)is a dom-inant species in urban bird communities.With the devel-opment of urbanization,the habitats and sources of food for Tree Sparrows are decreasing.Can the urban Tree Sparrow adapt to changes in the urban environment?To answer this question,we studied the habitat use of Tree Sparrows in eight types of urban areas in Beijing.The results show that the number of both breeding and winter-ing Tree Sparrows decreased with increasing urbanization.The habitat use of Tree Sparrows,analyzed using stepwise discriminant analysis,was positively correlated with the number of brick bungalows,coniferous and broad-leaved trees and air conditioners.It was negatively correlated with the area of high buildings and hardened roads,pedestrian and automobile flux.This indicates that the Tree Sparrow had not adapted to rapid urbanization even though it is a generally adaptable species.Urban planning should take birds such as the Tree Sparrow into consideration.

Optimizing slope safety factor prediction via stacking using sparrow search algorithm for multi-layer machine learning regression models

The safety factor is a crucial quantitative index for evaluating slope stability.However,the traditional calculation methods suffer from unreasonable assumptions,complex soil composition,and inadequate consideration of the influencing factors,leading to large errors in their calculations.Therefore,a stacking ensemble learning model(stacking-SSAOP)based on multi-layer regression algorithm fusion and optimized by the sparrow search algorithm is proposed for predicting the slope safety factor.In this method,the density,cohesion,friction angle,slope angle,slope height,and pore pressure ratio are selected as characteristic parameters from the 210 sets of established slope sample data.Random Forest,Extra Trees,AdaBoost,Bagging,and Support Vector regression are used as the base model(inner loop)to construct the first-level regression algorithm layer,and XGBoost is used as the meta-model(outer loop)to construct the second-level regression algorithm layer and complete the construction of the stacked learning model for improving the model prediction accuracy.The sparrow search algorithm is used to optimize the hyperparameters of the above six regression models and correct the over-and underfitting problems of the single regression model to further improve the prediction accuracy.The mean square error(MSE)of the predicted and true values and the fitting of the data are compared and analyzed.The MSE of the stacking-SSAOP model was found to be smaller than that of the single regression model(MSE=0.03917).Therefore,the former has a higher prediction accuracy and better data fitting.This study innovatively applies the sparrow search algorithm to predict the slope safety factor,showcasing its advantages over traditional methods.Additionally,our proposed stacking-SSAOP model integrates multiple regression algorithms to enhance prediction accuracy.This model not only refines the prediction accuracy of the slope safety factor but also offers a fresh approach to handling the intricate soil composition and other influencing factors,making it a precise and reliable method for slope stability evaluation.This research holds importance for the modernization and digitalization of slope safety assessments.

Cavitation Diagnostics Based on Self-Tuning VMD for Fluid Machinery with Low-SNR Conditions

Variational mode decomposition(VMD)is a suitable tool for processing cavitation-induced vibration signals and is greatly affected by two parameters:the decomposed number K and penalty factorαunder strong noise interference.To solve this issue,this study proposed self-tuning VMD(SVMD)for cavitation diagnostics in fluid machinery,with a special focus on low signal-to-noise ratio conditions.A two-stage progressive refinement of the coarsely located target penalty factor for SVMD was conducted to narrow down the search space for accelerated decomposition.A hybrid optimized sparrow search algorithm(HOSSA)was developed for optimalαfine-tuning in a refined space based on fault-type-guided objective functions.Based on the submodes obtained using exclusive penalty factors in each iteration,the cavitation-related characteristic frequencies(CCFs)were extracted for diagnostics.The power spectrum correlation coefficient between the SVMD reconstruction and original signals was employed as a stop criterion to determine whether to stop further decomposition.The proposed SVMD overcomes the blindness of setting the mode number K in advance and the drawback of sharing penalty factors for all submodes in fixed-parameter and parameter-optimized VMDs.Comparisons with other existing methods in simulation signal decomposition and in-lab experimental data demonstrated the advantages of the proposed method in accurately extracting CCFs with lower computational cost.SVMD especially enhances the denoising capability of the VMD-based method.

Short-Term Power Load Forecasting with Hybrid TPA-BiLSTM Prediction Model Based on CSSA

Since the existing prediction methods have encountered difficulties in processing themultiple influencing factors in short-term power load forecasting,we propose a bidirectional long short-term memory(BiLSTM)neural network model based on the temporal pattern attention(TPA)mechanism.Firstly,based on the grey relational analysis,datasets similar to forecast day are obtained.Secondly,thebidirectional LSTM layermodels the data of thehistorical load,temperature,humidity,and date-type and extracts complex relationships between data from the hidden row vectors obtained by the BiLSTM network,so that the influencing factors(with different characteristics)can select relevant information from different time steps to reduce the prediction error of the model.Simultaneously,the complex and nonlinear dependencies between time steps and sequences are extracted by the TPA mechanism,so the attention weight vector is constructed for the hidden layer output of BiLSTM and the relevant variables at different time steps are weighted to influence the input.Finally,the chaotic sparrow search algorithm(CSSA)is used to optimize the hyperparameter selection of the model.The short-term power load forecasting on different data sets shows that the average absolute errors of short-termpower load forecasting based on our method are 0.876 and 4.238,respectively,which is lower than other forecastingmethods,demonstrating the accuracy and stability of our model.