Super-efficiency Data Envelopment Analysis Research Articles

Robust, extended goal programming with uncertainty sets: an application to a multi-objective portfolio selection problem leveraging DEA

AbstractThis study presents a two-phase approach of Data Envelopment Analysis (DEA) and Goal Programming (GP) for portfolio selection, representing a pioneering attempt at combining these techniques within the context of portfolio selection. The approach expands on the conventional risk and return framework by incorporating additional financial factors and addressing data uncertainty, which allows for a thorough examination of portfolio outcomes while accommodating investor preferences and conservatism levels. The initial phase employs a super-efficiency DEA model to streamline asset selection by identifying suitable investment candidates based on efficiency scores, setting the stage for subsequent portfolio optimization. The second phase leverages the Extended GP (EGP) framework, which facilitates the comprehensive incorporation of investor preferences to determine the optimal weights of the efficient assets previously identified within the portfolio. Each goal is tailored to reflect specific financial factors spanning both technical and fundamental aspects. To tackle data uncertainty, robust optimization is applied. The research contributes to the robust GP (RGP) literature by analyzing new RGP variants, overcoming limitations of traditional and other uncertain GP models by incorporating uncertainty sets. Robust counterparts of the EGP models are accordingly developed using polyhedral and combined interval and polyhedral uncertainty sets, providing a flexible representation of uncertainty in financial markets. Empirical results, based on real data from the Tehran Stock Exchange comprising 779 assets, demonstrate the superiority of the proposed approach over traditional portfolio selection methods across various uncertainty settings. Additionally, a comprehensive sensitivity analysis investigates the impact of uncertainty levels on the robust EGP models. The proposed framework offers guidance to investors and fund managers through a pragmatic approach, enabling informed and robust portfolio decisions by considering efficiency, uncertainty, and extended financial factors.

Functional-Combination-Based Comprehensive Benefit Evaluation of Energy Storage Projects under Source-Grid-Load Scenarios via Super-Efficiency DEA

As an important support for power systems with high penetration of sustainable energy, the energy storage system (ESS) has changed the traditional model of simultaneous implementation of electricity production and consumption. Its installed capacity under the source-grid-load scenario is rising year by year, contributing to sustainable development, but it faces the problems of insufficient utilization and benefits. This study analyzes the functional combination of ESS under source-grid-load scenarios. A comprehensive benefit evaluation method of energy storage projects (ESPs), based on a fuzzy decision-making trial and evaluation laboratory (DEMATEL) and super-efficiency data envelopment analysis (DEA), is proposed. Firstly, the functional requirements of energy storage in source-grid-load scenarios are explored, and the characteristics of various functions are analyzed to form eight functional combination schemes. Secondly, index modeling is carried out from three aspects—the whole life cycle cost, functional combination benefits, and social and environmental benefits—and a comprehensive benefit evaluation index system of ESP is proposed. Then, the intuitionistic trapezoidal fuzzy number (ITFN) is combined with DEMATEL to form an effective analysis method for the input–output relationship of the indices, and the comprehensive evaluation is realized based on the SE-DEA model. Compared with other methods, this model can ensure the objectivity and stability of the evaluation results in ESP evaluation. Finally, the effectiveness of the proposed evaluation method and the rationality of the functional combination are verified under source-grid-load scenarios. The calculation results show that in the application scenario of source-grid-load, after adopting the functional combination scheme formulated in this article, the comprehensive investment benefits of ESPs have been improved. Moreover, the source side effect is at its best, with an efficiency value of 2.209.

Provincial-scale assessment of vulnerability and resilience to drought in China

Frequent droughts have caused severe disaster losses in China. Such events can be minimized by enhancing the country's resilience and reducing its vulnerability, where this can ensure socioeconomic stability and sustainable development. Evaluating the vulnerability and resilience to drought is thus crucial for effectively managing the risk of disasters and promoting sustainable socioeconomic development. In this study, we constructed a comprehensive framework to assess the spatiotemporal characteristics of China's vulnerability and resilience to drought at the provincial scale from an input-output perspective by using the Super-Efficiency Data Envelopment Analysis (DEA) model and the Super-Efficiency Slacks-Based Measure DEA (SBM-DEA) model. This study focused on drought drivers, the disaster-forming environment, drought bearers, disaster intensity, and recovery. The results showed that the vulnerability to drought of 42 % of China's provinces decreased from 2010 to 2022, that of only 29 % of the provinces increased, while the status of a majority of provinces improved in general. The center of gravity of the vulnerability to drought moved toward the southwest over time and a spatial clustering of vulnerability was observed, with High-High clusters moving from the north to the south. Moreover, the resilience to drought declined in 36 % of provinces and increased in only 20 %, reflecting poor resilience overall. The center of gravity of China's overall resilience to drought moved northward, with a relatively stable spatial pattern and prominent clusters of Low-Low resilience indicating a pressing need for improvement. Areas with high vulnerability and low resilience were concentrated in inland western and eastern regions, and this highlights the importance of drought prevention and mitigation in provinces like Xinjiang, Inner Mongolia, Jiangxi, and Fujian. The findings here provide valuable insights for mitigating the risk of drought and promoting sustainable socioeconomic development.

Can carbon emission trading improve regional eco-efficiency? Based on the environmental innovation perspective.

This paper uses green innovation and environmental pollution as the mediating variables to construct a mediating effect model to investigate whether China's carbon emission trading policy can improve regional eco-efficiency by reducing regional environmental pollution and stimulating green innovation. This study is based on panel data from 30 provinces and municipalities directly under China's central government and autonomous regions from 2003 to 2019. The eco-efficiency of these provinces is measured using the super-efficiency DEA model and the difference-in-difference method (DID). The results show that (1) China's emission trading policy significantly improves regional ecological efficiency and the per capita GDP. The improvement can effectively improve regional ecological efficiency. (2) The mediating effect of green innovation and environmental pollution is significant. That is, China's carbon emission trading policy further improves regional ecological efficiency by stimulating more green innovation and reducing the synergy brought by environmental pollution. (3) There are differences in the feedback of this impact mechanism between different regions: It shows the characteristics of the western region being more significant than the eastern region. The central region has no significant effect. The research conclusion can provide a policy reference for the subsequent unified promotion of the construction of a carbon emission trading market nationwide and a theoretical basis for helping to achieve the "dual carbon" goal.

Performance Test, Index System Establishment, and Comprehensive Evaluation of Earthquake Rescue Robots

To effectively enhance the adaptability of earthquake rescue robots in dynamic environments and complex tasks, there is an urgent need for a comprehensive evaluation method that encompasses establishing an evaluation index system, testing performance indexes, and conducting performance evaluation. Firstly, four main criterion and twenty-three sub-criterion indexes are established by conducting a comprehensive review of existing assessment measures for rescue robots across diverse domains. These indexes are validated through test modules developed by the National Earthquake Response Support Service to obtain corresponding values for each criterion. Moreover, a method for establishing the index system is proposed based on the fuzzy clustering analysis and grey correlation analysis methods. This method effectively addresses issues related to excessive subjectivity, redundancy, and ambiguous stratification of indexes. Subsequently, the DEMATEL is employed to scrutinize the interrelationships and causal connections among each index within the established index system, leading to the identification of input and output indexes based on the analysis outcomes. Finally, as an empirical example, three earthquake rescue robots are comprehensively evaluated and ranked using the super efficiency DEA model. Alongside analyzing results regarding input redundancy and output deficiency, targeted improvement suggestions are provided for each earthquake rescue robot. Additionally, comparison analysis with the entropy weight method and VIKOR method verifies the effectiveness of our proposed method.

Allocating the fixed cost as a complementary input in two-stage system: A DEA approach

The existing research on fixed cost allocation (FCA) in two-stage system data envelopment analysis (DEA) models typically regards the fixed cost as an additional input for each decision-making unit (DMU). However, these models overlook the prevalent real-world scenario where fixed costs act as complementary inputs in actual production processes. This study proposes a general two-stage network DEA model that incorporates the fixed cost as a complementary input to optimize the allocation scheme. First, we construct a functional relationship between the efficiency scores of DMUs and their allocated fixed costsusing a modified super-efficiency DEA model, which effectively classifies DMUs and solves infeasible solutions within the variable returns to scale (VRS) framework. Then, we propose a fair and unique allocation model based on fairness and efficiency maximization principles. Specifically, we allocate fixed costs based on the operational scale for inelastic DMUs while equitably increasing the efficiency scores for elastic DMUs. Finally, a numerical example and an empirical study on subsidy allocation among 30 provinces demonstrate the rationality and acceptability of our approach.

Analyzing the Performances and Efficiencies of European Electric Vehicles in the European Union Market Using Decision Analysis Methods

Concerns about the environment have grown worldwide as carbon emissions, one of the primary drivers of global warming, continue to rise. As the transportation industry is one of the most greenhouse-gas-emitting sectors in the European Union (EU), the need for environmentally friendly solutions has been increasing progressively. In this regard, electric vehicles (EVs) play an important part in mitigating some of the adverse effects of road transportation on human health, the environment, and climate. Therefore, the popularity of electric vehicles in the EU has recently increased significantly because of climate change mitigation efforts. In this paper, we aim to analyze and compare the performance of European EVs with multi-criteria decision-making (MCDM) methods, namely preference selection index (PSI) and axial-distance-based aggregated measurement (ADAM) techniques, which do not need the criteria weights for measurement and a novel three-dimensional evaluation technique. The results of both MCDM methods reveal that the EVs of the Tesla Inc. and Geely Group models are found to be the best-performing vehicles. We also investigate the efficiency of the European EV market by the super-efficiency data envelopment analysis (DEA) technique, which enables us to evaluate among efficient units. The efficiency scores indicate that five EVs from three different manufacturer groups obtain efficiency levels. To the best of our knowledge, European EV market evaluation by integrated and comparative analysis has not been encountered for the EU on a group basis. The suggested MCDM and DEA techniques can benefit stakeholders while assessing the European EV market.

Efficiency Characteristics and Evolution Patterns of Urban Carbon Metabolism of Production-Living-Ecological Space in Beijing-Tianjin-Hebei Region

This study explored the carbon metabolism efficiency of a production-living-ecological space system, which is of great significance for regional factor integration and spatial optimization. In this study, the material flow analysis method was introduced to establish a framework for evaluating the carbon metabolism efficiency of the production-living-ecological space system, and the super-efficiency DEA model and Malmquist index were used to empirically analyze the spatio-temporal distribution, dynamic change, and evolution patterns of the carbon metabolism efficiency of production-living-ecological space in the Beijing-Tianjin-Hebei Region, China, from 2000 to 2020 on the basis of the urban metabolic perspective. The results showed that:① the carbon metabolism efficiency of the production-living-ecological space showed a fluctuating growth trend, indicating the significant spatial differentiation of carbon metabolism efficiency in each city. There was a low overall carbon metabolism efficiency level, with a distribution pattern of being high in the middle and low in the north and south. ② The Malmquist index showed that the Total Factor Productivity (TFP) of carbon metabolism efficiency was greater than 1, and both the Technical Change (TC) and Pure Efficiency Change (PEC) were less than 1, in which the TFP showed an increasing trend, whereas there was no significant contribution of technological progress or pure technical efficiency to carbon metabolism efficiency. The total factor productivity of more than 50% of the cities showed an improving trend, only 38.46% of which made technological progress in improving carbon metabolism efficiency, and more than half of the urban pure technical efficiency showed a decreasing trend, in which the technical efficiency change and scale efficiency change were greater than 1 in most cities. ③ There were different types of carbon efficiency characteristics in each city, and according to the movement rules of the corresponding points in the quartile map, the evolution patterns of tourism industry efficiency were classified into stable, reciprocating, progressive, and abrupt. Therefore, local governments should adopt differentiated strategies to reasonably allocate spatial resources of production-living-ecological space and improve the technical level and scale efficiency, so as to improve the efficiency of urban carbon metabolism.

Research on the environmental benefits of marine tidal energy and its impact on regional economic structure

Tidal power generation, being one of the earliest and largest developed new energy technologies, has evolved into a mature and increasingly competitive source of energy. This article delves into the evaluation of tidal energy's socioeconomic impact, establishing a connection between its environmental benefits and regional economic development. The focus is on marine economic efficiency, and the super-efficiency DEA model is employed to gauge this efficiency. The study conducts a thorough analysis of the green ocean economic efficiency in three major regions, introducing the Malmquist efficiency index for a comprehensive understanding of changing trends. Utilizing an economic effect model, the research explores the contribution of tidal energy development to regional economic growth, delving into industry-related effects. Through these analyses, we aim to provide a clearer and more comprehensive insight into the positive influence of tidal energy on regional socioeconomics. This understanding is pivotal for guiding sustainable tidal energy development and formulating relevant policies.

Quantitative analysis of spatiotemporal disparity of urban water use efficiency and its driving factors in the Yangtze River Economic Belt, China

Study regionYangtze River Economic Belt, China Study focusAs the major national strategic development area of China, there have always been vital problems about imbalance of the water resources distribution and the disparity of economic levels in YREB. Quantitative analysis of water use efficiency (WUE) is essential to the rational use of water resources, as well as the sustainable development. In this study, a WUE evaluation index system for prefecture-level cities in the YREB was constructed, and Super-Efficiency Data envelopment analysis Slacks-Based Measure (DEA-SBM) model, Global Malmquist-Luenberger productivity index, combined with geographically weighted regression model were utilized to measure and identify the spatiotemporal evolution characteristics of WUE and its influencing factors. New hydrological insights for the regionFrom the temporal perspective, the WUE manifests a significant upward trend from 2005 to 2020, and the growth presents lower reach > middle reach > upper reach; in the spatial pattern, the WUE has significant spatial divergence characteristics, high WUE mainly occurred in developed leading cities, while developing cities in the midstream and upstream tended to be inefficient; various effects on WUE were also analyzed, highlighting that technical advancement was the key driver of WUE evolution. Then the negative effects of industrial structure and urban environment was becoming more and more significant. Finally, effective measures for upstream, middle and downstream cities in the YREB were discussed.

Assessment of truck driver safety efficiency based on data envelopment analysis

This paper introduces a safety efficiency evaluation framework that integrates Data Envelopment Analysis (DEA) and Super-Efficiency Data Envelopment Analysis (SE-DEA) for quantitatively assessing the safety of truck drivers. The framework utilizes data from onboard equipment to capture drivers’ dangerous behaviors and poor driving states. Subsequently, it evaluates safety efficiency using the DEA combination model, providing safety rankings. Improvement suggestions are offered to underperforming drivers based on slack variable values. The proposed method is compared with EWM-Topsis and Critic-Topsis models using fixed weights, demonstrating better stability. The study’s outcomes enable freight companies to identify high-risk drivers and offer personalized, targeted safety training.

A [formula omitted]-Number Slacks-Based Measure DEA model-based framework for sustainable supplier selection with imprecise information

The focus of this study is to develop a decision-making framework for selecting sustainable suppliers with imprecise information. Sustainable supplier selection poses a significant challenge for managers and decision-makers seeking a long-term competitive edge. Due to the presence of unreliable, or partially reliable imprecise information in practice, incorporation of the reliability degree of imprecise information in the decision models becomes necessary. Since Z-numbers can incorporate the reliability degree of imprecise information, the Z-number-based “Data Envelopment Analysis (DEA)” approach can be used for decision-making. The current study introduces a super-efficiency DEA approach, namely “Z-number Slacks-Based Measure (ZN-SBM)”, which is further used to construct a framework for selecting sustainable suppliers. Unlike the existing Z-number-based DEA approaches, the proposed ZN-SBM model can assume “constant returns-to-scale”, “variable returns-to-scale”, “non-increasing returns-to-scale”, and “non-decreasing returns-to-scale” conditions. Moreover, the developed framework is free from strategic weight manipulation. To demonstrate the efficacy of this framework in sustainable supplier selection, we present a case study of the automotive industry. Further, the robustness of the proposed framework is investigated through a sensitivity analysis. The results of this study reveal that the proposed framework can be effectively applied as a high-performing decision-support tool for decision-making under imprecision in the domain of sustainable supplier selection.

Evaluation of Ecological Efficiency and Analysis of Its Influencing Factors in Provincial Coastal Regions Using Integrated Super-Efficiency DEA and Tobit Models

Abstract With the rapid development of the Chinese economy, the demand for resources has increased significantly, putting the environment under increasing pressure. Effectively using various resources has become crucial. This study employs the Super-Efficiency Data Envelopment Analysis to assess ecological efficiency during the same period and conducts a residual analysis on cities with high efficiency but not efficiently analyzed by Data Envelopment Analysis. The primary objective of this approach is to investigate the potential ecological development of these regions. The dynamic assessment of ecological efficiency is done using the Malmquist index, which takes into account changes in the total factor output growth rate. To investigate factors that affect ecological efficiency and their magnitudes, a Tobit model is being established using panel data. From 2017 to 2022, there were changes in ecological benefits among cities in Zhejiang Province due to intense competition between high-efficiency cities and frequent position changes, as evidenced by the results. The gap between cities with middle to low efficiency is narrowing, which suggests that ecological benefits are being balanced in the province despite a decreasing trend. Both the degree of openness and the proportion of asset investment have a significant and positive impact on ecological efficiency. Enhancing interregional communication, optimizing resource allocation, increasing openness, and adjusting industrial layout is essential to sustain technological innovation and progress.

Rural revitalization helps rural e-commerce level development efficiency-Based on DEA model

Abstract The rural revitalization strategy is underway and can provide the promotion of high-quality growing rural e-commerce as well as supply the facilities and industrial support required for its growth. The complete score of the rural e-commerce development level was assessed using the entropy value technique by analyzing data from 31 Chinese provinces, municipalities, and autonomous regions. The efficiency of rural e-commerce growth was evaluated using the BCC model and the super-efficient DEA model within the DEA model. The study examined the effects of rural revival on the effectiveness of electronic commerce in rural development. Both input and output views were considered when selecting the related factors. After that, the productivity value was examined by merging information on the growth of rural e-commerce between 2016 and 2020. The research indicates that between 2015 and 2022, the comprehensive score of rural e-commerce growth experienced a high-quality increase of 173.50%. Furthermore, 8 out of 31 provinces, municipalities, and autonomous areas had DEA-achieved e-commerce development efficiency, with a mean complete efficiency score of 0.700. However, the mean value of total efficiency decreased by 35.29% when the progress level of rural rejuvenation was eliminated. Apart from providing support for infrastructure construction, rural revitalization can also provide policy assurances and an industrial base for the expansion of rural electronic commerce.

Research on the Water Environment Governance of Hangzhou Bay Based on the DEA–Tobit Model

With rapid urbanization and industrialization, Hangzhou Bay faces significant pressure in water environment governance. This study, based on panel data from 2011 to 2021 in Zhejiang’s Hangzhou, Jiaxing, Shaoxing, and Ningbo, employs the Super-Efficiency DEA model to assess water environment governance performance. The Tobit model analyzes external environmental factors. Findings reveal fluctuating water governance efficiency during the study period, with inefficiencies from 2012 to 2019, followed by significant improvement from 2019 to 2021. Key factors impacting governance include urban water environment performance in Hangzhou, urban residents’ disposable income, population density, and secondary industry GDP development. A higher urban income enhances environmental awareness and governance performance, while population density and industrial GDP intensify resource use, energy consumption, and wastewater discharge, worsening governance pressures and performance. This research offers insights for enhancing water environment governance in Hangzhou Bay, aiding in the formulation of protection plans and management policies. Additionally, it provides valuable experiences for watershed governance globally.

Analysis of the Spatial Correlation Network Structure of Agricultural Water Use Efficiency in Northwest China

There are some problems in Northwest China, such as the fragile ecological environment, poor basic conditions of agricultural production, low efficiency of agricultural water use, and difficulty in clarifying the path of agricultural water use efficiency (AWUE) improvement. Based on the superefficiency data envelopment analysis (DEA) model, this study increases the amount of ‘green water’ resources in the agricultural water consumption index of the input index and increases the wastewater pollutants (total chemical oxygen demand emissions; total ammonia nitrogen emissions) in the undesired output index to measure the AWUE in the northwest region. Based on the calculation results of AWUE, combined with the modified gravity model, the connection strength of AWUE between any two provinces in Northwest China is calculated, and the spatial structure and network characteristics of AWUE in this area are analysed via the social network analysis (SNA) method. The results show that the average AWUE in 2020 is nearly two times higher than that in 2011. From the situation of the northwest provinces, the average AWUE of the five provinces is in the order of Qinghai > Shaanxi > Gansu > Ningxia > Xinjiang. The AWUE value, total population, real GDP and per capita GDP of the capital cities of the five provinces in Northwest China are the key factors for the improvement of the connection intensity of AWUE. From 2011 to 2020, the connection intensity and closeness of AWUE in Northwest China increased, and there was a clear network hierarchy. The improvement in overall AWUE in the region is mainly due to the radiation and driving effect of the central province on other provinces. Based on this, the study proposes policy recommendations for gradually realising the AWUE improvement path of the central province (Shaanxi; Gansu)—cooperation circle (Shaanxi–Ningxia; Gansu–Qinghai)—the whole region. The results provide theoretical support and a quantitative basis for optimising the spatial pattern of agricultural water resources and improving AWUE in Northwest China.

Research on Forest Ecological Product Value Evaluation and Conversion Efficiency: Case Study from Pearl River Delta, China

Exploring an effective scientific method to measure the economic benefits of ecological products is of great significance for green development. Based on the InVEST model, this paper, taking the Pearl River Delta (PRD) as an example, evaluated the FEPs value in the PRD from 2000 to 2015; using a super-efficient DEA model, the conversion efficiency of ecological products was estimated, and its temporal and spatial variation characteristics were analyzed using the Malmquist index. The results showed that the value of FEPs in the PRD shot up during 2000–2015, and that the regulation services value is the main part of FEPs, followed by the value of cultural service. The overall conversion efficiency of FEPs is improving. However, cities differ greatly. Technical efficiency is the key driving factor for improving forest product conversion efficiency. The main reasons for the current efficiency loss are redundant inputs and insufficient outputs. This paper also suggests that conversion efficiency is a convincing method to evaluate the degree of transformation of ecological environment resources into economic benefits and the degree of ecological and economic coordinated development.

Research on the Influencing Factors of The Green Coordinated Development of Productive Service Industry and Manufacturing Industry Under the Background of Dual Carbon

Under the dual-carbon background, along with the process of the two-wheel drive development strategy, the industrial synergistic agglomeration has quietly become the "new normal" of urban industrial spatial layout, and the green total factor productivity has become an essential measure of the quality of economic development of cities in China. This project takes the synergistic agglomeration at the factor level between the productive service industry and manufacturing industry as the perspective and analyzes the realization mechanism of green total factor productivity growth under the synergistic agglomeration of the manufacturing industry and productive service industry from the current situation of China's industrial development, which is also a deepening and expanding of the theory of agglomeration economy. This project first discusses the "greening" issue in the development process of the productive service industry and manufacturing industry, and applies the super-efficient DEA model to account for the green total factor productivity of the productive service industry and manufacturing industry according to the difference of industrial characteristics, and then expounds the inner mechanism of green total factor productivity growth under the synergistic agglomeration of industries. Then, the panel data of 24 provinces in China are used to modify the existing indexes for measuring the level of industrial synergistic agglomeration and analyze the impact factors of the synergistic evolution of the productive service industry and the manufacturing industry on the green total factor productivity. Finally, through scenario simulation analysis, different policy scenarios with different policy incentives are set up to study the impact of policy incentives further and propose corresponding policy recommendations.

Multi-step impacts of environmental regulations on green economic growth: Evidence in the lens of natural resource dependence

Whether and how environmental regulation and resource dependence contribute to green economic growth has been a focus of academic discussion. This paper analyzes the multi-stage transmission mechanism based on environmental regulation to promote green economic growth, especially the important transmission mechanism of resource dependence. The green economic growth and environmental regulation indicators of 286 Chinese cities were measured from 2003 to 2018 using the Metafrontier Global Slack-Based Measure (SBM) super-efficient Data Envelopment Analysis (DEA) approach and Fuzzy Comprehensive Evaluation (FCE) method. In addition, resource dependence indicators are investigated. Spatial panel and multiple mediator models are used to test the one- and two-step transmission mechanisms of resource dependence concerning the effect of environmental regulation on green economic growth. The results show that resource dependence plays a mediating role in the one-step transmission mechanism. Resource dependence further affects green economic growth by influencing the industrial structure, quality of the government system, foreign investments, technological innovation, manufacturing development, and physical capital, thus constituting a two-step transmission mechanism. Finally, we suggest a new method based on the environmental regulation policy in China, which can be used to break the “curse” of urban resources and realize green economic growth.

What Type of Energy Structure Improves Eco-Efficiency? A Study Based on Statistical Data of 285 Prefecture-Level Entities in China

Increasing environmental pollution, resource depletion, and climate change have led to policymakers paying increased attention to the environmental and ecological impacts of economic activities. To establish which type of energy structure is most conducive to improving eco-efficiency, we use the super-efficiency data envelopment analysis (DEA) model to quantify the relationship between the two, based on the panel data of 285 prefecture-level cities in China from 2005 to 2016. The heterogeneity and spatial spillover effect on different types of cities are further discussed. Our findings suggest that energy structure optimization by reducing the proportion of coal energy is beneficial to improving ecological efficiency. However, the effect is nonlinear, showing an inverted U-shaped nonlinear change. The influence of energy structure optimization on ecological efficiency has a stronger effect on its improvement of resource-based and old industrial cities. Moreover, it has an obvious “local–neighborhood” spatial spillover effect. Additionally, the energy structure could be improved according to local conditions in different regions, such as the level of economic development, industrial structure, and resource endowment conditions. Furthermore, regional cooperation and coordination should be strengthened and consolidated, along with the positive spatial effects of high eco-efficiency cities. Especially in city clusters and metropolitan areas, the strengthening of cross-city cooperation in emission trading, environmental governance, and compensation is vital.