arXiv subjects

Xiaojun Lin

Publications and source records attributed to Xiaojun Lin.

34 records · Page 2Linked to original sources

arXiv2021

Time-of-use Pricing for Energy Storage Investment

Time-of-use (ToU) pricing is widely used by the electricity utility to shave peak load. Such a pricing scheme provides users with incentives to invest in behind-the-meter energy storage and to shift peak load towards low-price intervals. However, without considering the implication on energy storage investment, an improperly designed ToU pricing scheme may lead to significant welfare loss, especially when users over-invest the storage, which leads to new energy consumption peaks. In this paper, we will study how to design a social-optimum ToU pricing scheme by explicitly considering its impact on storage investment. We model the interactions between the utility and users as a two-stage optimization problem. To resolve the challenge of asymmetric information due to users' private storage cost, we propose a ToU pricing scheme based on different storage types and the aggregate demand per type. Each user does not need to reveal his private cost information. We can further compute the optimal ToU pricing with only a linear complexity. Simulations based on real-world data show that the suboptimality gap of our proposed ToU pricing, compared with the social optimum achieved under complete information, is less than 5%.

eess.SY↗

arXiv2021

Virtual Energy Storage Sharing and Capacity Allocation

Energy storage can play an important role in energy management of end users. To promote an efficient utilization of energy storage, we develop a novel business model to enable virtual storage sharing among a group of users. Specifically, a storage aggregator invests and operates the central physical storage unit, by virtualizing it into separable virtual capacities and selling to users. Each user purchases the virtual capacity, and utilize it to reduce the energy cost. We formulate the interaction between the aggregator and users as a two-stage optimization problem. In Stage 1, over the investment horizon, the aggregator determines the investment and pricing decisions. In Stage 2, in each operational horizon, each user decides the virtual capacity to purchase together with the operation of the virtual storage. We characterize a stepwise form of the optimal solution of Stage-2 Problem and a piecewise linear structure of the optimal profit of Stage-1 Problem, both with respect to the virtual capacity price. Based on the solution structure, we design an algorithm to attain the optimal solution of the two-stage problem. In our simulation results, the proposed storage virtualization model can reduce the physical energy storage investment of the aggregator by 54.3% and reduce the users' total costs by 34.7%, compared to the case where users acquire their own physical storage.

eess.SY↗

arXiv2021

The Case for Task Sampling based Learning for Cluster Job Scheduling

The ability to accurately estimate job runtime properties allows a scheduler to effectively schedule jobs. State-of-the-art online cluster job schedulers use history-based learning, which uses past job execution information to estimate the runtime properties of newly arrived jobs. However, with fast-paced development in cluster technology (in both hardware and software) and changing user inputs, job runtime properties can change over time, which lead to inaccurate predictions. In this paper, we explore the potential and limitation of real-time learning of job runtime properties, by proactively sampling and scheduling a small fraction of the tasks of each job. Such a task-sampling-based approach exploits the similarity among runtime properties of the tasks of the same job and is inherently immune to changing job behavior. Our study focuses on two key questions in comparing task-sampling-based learning (learning in space) and history-based learning (learning in time): (1) Can learning in space be more accurate than learning in time? (2) If so, can delaying scheduling the remaining tasks of a job till the completion of sampled tasks be more than compensated by the improved accuracy and result in improved job performance? Our analytical and experimental analysis of 3 production traces with different skew and job distribution shows that learning in space can be substantially more accurate. Our simulation and testbed evaluation on Azure of the two learning approaches anchored in a generic job scheduler using 3 production cluster job traces shows that despite its online overhead, learning in space reduces the average Job Completion Time (JCT) by 1.28x, 1.56x, and 1.32x compared to the prior-art history-based predictor.

cs.DC↗

arXiv2021

Student-Teacher Learning from Clean Inputs to Noisy Inputs

Feature-based student-teacher learning, a training method that encourages the student's hidden features to mimic those of the teacher network, is empirically successful in transferring the knowledge from a pre-trained teacher network to the student network. Furthermore, recent empirical results demonstrate that, the teacher's features can boost the student network's generalization even when the student's input sample is corrupted by noise. However, there is a lack of theoretical insights into why and when this method of transferring knowledge can be successful between such heterogeneous tasks. We analyze this method theoretically using deep linear networks, and experimentally using nonlinear networks. We identify three vital factors to the success of the method: (1) whether the student is trained to zero training loss; (2) how knowledgeable the teacher is on the clean-input problem; (3) how the teacher decomposes its knowledge in its hidden features. Lack of proper control in any of the three factors leads to failure of the student-teacher learning method.

cs.LG↗

arXiv2021

The Power of $D$-hops in Matching Power-Law Graphs

This paper studies seeded graph matching for power-law graphs. Assume that two edge-correlated graphs are independently edge-sampled from a common parent graph with a power-law degree distribution. A set of correctly matched vertex-pairs is chosen at random and revealed as initial seeds. Our goal is to use the seeds to recover the remaining latent vertex correspondence between the two graphs. Departing from the existing approaches that focus on the use of high-degree seeds in $1$-hop neighborhoods, we develop an efficient algorithm that exploits the low-degree seeds in suitably-defined $D$-hop neighborhoods. Specifically, we first match a set of vertex-pairs with appropriate degrees (which we refer to as the first slice) based on the number of low-degree seeds in their $D$-hop neighborhoods. This significantly reduces the number of initial seeds needed to trigger a cascading process to match the rest of the graphs. Under the Chung-Lu random graph model with $n$ vertices, max degree $Θ(\sqrt{n})$, and the power-law exponent $2<β<3$, we show that as soon as $D> \frac{4-β}{3-β}$, by optimally choosing the first slice, with high probability our algorithm can correctly match a constant fraction of the true pairs without any error, provided with only $Ω((\log n)^{4-β})$ initial seeds. Our result achieves an exponential reduction in the seed size requirement, as the best previously known result requires $n^{1/2+ε}$ seeds (for any small constant $ε>0$). Performance evaluation with synthetic and real data further corroborates the improved performance of our algorithm.

cs.DS↗

arXiv2021

Graph Matching with Partially-Correct Seeds

Graph matching aims to find the latent vertex correspondence between two edge-correlated graphs and has found numerous applications across different fields. In this paper, we study a seeded graph matching problem, which assumes that a set of seeds, i.e., pre-mapped vertex-pairs, is given in advance. While most previous work requires all seeds to be correct, we focus on the setting where the seeds are partially correct. Specifically, consider two correlated graphs whose edges are sampled independently from a parent \ER graph $\mathcal{G}(n,p)$. A mapping between the vertices of the two graphs is provided as seeds, of which an unknown $β$ fraction is correct. We first analyze a simple algorithm that matches vertices based on the number of common seeds in the $1$-hop neighborhoods, and then further propose a new algorithm that uses seeds in the $2$-hop neighborhoods. We establish non-asymptotic performance guarantees of perfect matching for both $1$-hop and $2$-hop algorithms, showing that our new $2$-hop algorithm requires substantially fewer correct seeds than the $1$-hop algorithm when graphs are sparse. Moreover, by combining our new performance guarantees for the $1$-hop and $2$-hop algorithms, we attain the best-known results (in terms of the required fraction of correct seeds) across the entire range of graph sparsity and significantly improve the previous results in \cite{10.14778/2794367.2794371,lubars2018correcting} when $p\ge n^{-5/6}$. For instance, when $p$ is a constant or $p=n^{-3/4}$, we show that only $Ω(\sqrt{n\log n})$ correct seeds suffice for perfect matching, while the previously best-known results demand $Ω(n)$ and $Ω(n^{3/4}\log n)$ correct seeds, respectively. Numerical experiments corroborate our theoretical findings, demonstrating the superiority of our $2$-hop algorithm on a variety of synthetic and real graphs.

cs.DS↗

arXiv2020

Overfitting Can Be Harmless for Basis Pursuit, But Only to a Degree

Recently, there have been significant interests in studying the so-called "double-descent" of the generalization error of linear regression models under the overparameterized and overfitting regime, with the hope that such analysis may provide the first step towards understanding why overparameterized deep neural networks (DNN) still generalize well. However, to date most of these studies focused on the min $\ell_2$-norm solution that overfits the data. In contrast, in this paper we study the overfitting solution that minimizes the $\ell_1$-norm, which is known as Basis Pursuit (BP) in the compressed sensing literature. Under a sparse true linear regression model with $p$ i.i.d. Gaussian features, we show that for a large range of $p$ up to a limit that grows exponentially with the number of samples $n$, with high probability the model error of BP is upper bounded by a value that decreases with $p$. To the best of our knowledge, this is the first analytical result in the literature establishing the double-descent of overfitting BP for finite $n$ and $p$. Further, our results reveal significant differences between the double-descent of BP and min $\ell_2$-norm solutions. Specifically, the double-descent upper-bound of BP is independent of the signal strength, and for high SNR and sparse models the descent-floor of BP can be much lower and wider than that of min $\ell_2$-norm solutions.

cs.LG↗

arXiv2020

Contract-based Time-of-use Pricing for Energy Storage Investment

Time-of-use (ToU) pricing is widely used by the electricity utility. A carefully designed ToU pricing can incentivize end-users' energy storage deployment, which helps shave the system peak load and reduce the system social cost. However, the optimization of ToU pricing is highly non-trivial, and an improperly designed ToU pricing may lead to storage investments that are far from the social optimum. In this paper, we aim at designing the optimal ToU pricing, jointly considering the social cost of the utility and the storage investment decisions of users. Since the storage investment costs are users' private information, we design low-complexity contracts to elicit the necessary information and induce the proper behavior of users' storage investment. The proposed contracts only specify three contract items, which guides users of arbitrarily many different storage-cost types to invest in full, partial, or no storage capacity with respect to their peak demands. Our contracts can achieve the social optimum when the utility knows the aggregate demand of each storage-cost type (but not the individual user's type). When the utility only knows the distribution of each storage-cost type's demand, our contracts can lead to a near-optimal solution. The gap with the social optimum is as small as 1.5% based on the simulations using realistic data. We also show that the proposed contracts can reduce the system social cost by over 30%, compared with no storage investment benchmark.

eess.SY↗

arXiv2020

Learning Large Electrical Loads via Flexible Contracts with Commitment

Large electricity customers (e.g., large data centers) can exhibit huge and variable electricity demands, which poses significant challenges for the electricity suppliers to plan for sufficient capacity. Thus, it is desirable to design incentive and coordination mechanisms between the customers and the supplier to lower the capacity cost. This paper proposes a novel scheme based on flexible contracts. Unlike existing demand-side management schemes in the literature, a flexible contract leads to information revelation. That is, a customer committing to a flexible contract reveals valuable information about its future demand to the supplier. Such information revelation allows the customers and the supplier to share the risk of future demand uncertainty. On the other hand, the customer will still retain its autonomy in operation. We address two key challenges for the design of optimal flexible contracts: i) the contract design is a non-convex optimization problem and is intractable for a large number of customer types, and ii) the design should be robust to unexpected or adverse responses of the customers, i.e., a customer facing more than one contract yielding the same benefit may choose the contract less favorable to the supplier. We address these challenges by proposing sub-optimal contracts of low computational complexity that can achieve a provable fraction of the performance gain under the global optimum.

cs.GT↗

arXiv2019

Storage or No Storage: Duopoly Competition Between Renewable Energy Suppliers in a Local Energy Market

This paper studies the duopoly competition between renewable energy suppliers with or without energy storage in a local energy market. The storage investment brings the benefits of stabilizing renewable energy suppliers' outputs, but it also leads to substantial investment costs as well as some surprising changes in the market outcome. To study the equilibrium decisions of storage investment in the renewable energy suppliers' competition, we model the interactions between suppliers and consumers using a three-stage game-theoretic model. In Stage I, at the beginning of the investment horizon, suppliers decide whether to invest in storage. Once such decisions have been made, in the day-ahead market of each day, suppliers decide on their bidding prices and quantities in Stage II, based on which consumers decide the electricity quantity purchased from each supplier in Stage III. In the real-time market, a supplier is penalized if his actual generation falls short of his commitment. We characterize a price-quantity competition equilibrium of Stage II, and we further characterize a storage-investment equilibrium in Stage I incorporating electricity-selling revenue and storage cost. Counter-intuitively, we show that the uncertainty of renewable energy without storage investment can lead to higher supplier profits compared with the stable generations with storage investment due to the reduced market competition under random energy generation. Simulations further illustrate results due to the market competition. For example, a higher penalty for not meeting the commitment, a higher storage cost, or a lower consumer demand can sometimes increase a supplier's profit. We also show that although storage investment can increase a supplier 's profit, the first-mover supplier who invests in storage may benefit less than the free-rider competitor who chooses not to invest.

eess.SY↗

arXiv2019

A Probabilistic Approach for Demand-Aware Ride-Sharing Optimization

Ride-sharing is a modern urban-mobility paradigm with tremendous potential in reducing congestion and pollution. Demand-aware design is a promising avenue for addressing a critical challenge in ride-sharing systems, namely joint optimization of request-vehicle assignment and routing for a fleet of vehicles. In this paper, we develop a probabilistic demand-aware framework to tackle the challenge. We focus on maximizing the expected number of passenger pickups, given the probability distributions of future demands. The key idea of our approach is to assign requests to vehicles in a probabilistic manner. It differentiates our work from existing ones and allows us to explore a richer design space to tackle the request-vehicle assignment puzzle with a performance guarantee but still keeping the final solution practically implementable. The optimization problem is non-convex, combinatorial, and NP-hard in nature. As a key contribution, we explore the problem structure and propose an elegant approximation of the objective function to develop a dual-subgradient heuristic. We characterize a condition under which the heuristic generates a $\left(1-1/e\right)$ approximation solution. Our solution is simple and scalable, amendable for practical implementation. Results of numerical experiments based on real-world traces in Manhattan show that, as compared to a conventional demand-oblivious scheme, our demand-aware solution improves the passenger pickups by up to 46%. The results also show that joint optimization at the fleet level leads to 19% more pickups than that by separate optimizations at individual vehicles.

eess.SY↗

arXiv2015

Proactive Demand Response for Data Centers: A Win-Win Solution

In order to reduce the energy cost of data centers, recent studies suggest distributing computation workload among multiple geographically dispersed data centers, by exploiting the electricity price difference. However, the impact of data center load redistribution on the power grid is not well understood yet. This paper takes the first step towards tackling this important issue, by studying how the power grid can take advantage of the data centers' load distribution proactively for the purpose of power load balancing. We model the interactions between power grid and data centers as a two-stage problem, where the utility company chooses proper pricing mechanisms to balance the electric power load in the first stage, and the data centers seek to minimize their total energy cost by responding to the prices in the second stage. We show that the two-stage problem is a bilevel quadratic program, which is NP-hard and cannot be solved using standard convex optimization techniques. We introduce benchmark problems to derive upper and lower bounds for the solution of the two-stage problem. We further propose a branch and bound algorithm to attain the globally optimal solution, and propose a heuristic algorithm with low computational complexity to obtain an alternative close-to-optimal solution. We also study the impact of background load prediction error using the theoretical framework of robust optimization. The simulation results demonstrate that our proposed scheme can not only improve the power grid reliability but also reduce the energy cost of data centers.

eess.SY↗

arXiv2014

Optimal Monitoring and Mitigation of Systemic Risk in Financial Networks

This paper studies the problem of optimally allocating a cash injection into a financial system in distress. Given a one-period borrower-lender network in which all debts are due at the same time and have the same seniority, we address the problem of allocating a fixed amount of cash among the nodes to minimize the weighted sum of unpaid liabilities. Assuming all the loan amounts and asset values are fixed and that there are no bankruptcy costs, we show that this problem is equivalent to a linear program. We develop a duality-based distributed algorithm to solve it which is useful for applications where it is desirable to avoid centralized data gathering and computation. We also consider the problem of minimizing the expectation of the weighted sum of unpaid liabilities under the assumption that the net external asset holdings of all institutions are stochastic. We show that this problem is a two-stage stochastic linear program. To solve it, we develop two algorithms based on: Benders decomposition algorithm and projected stochastic gradient descent. We show that if the defaulting nodes never pay anything, the deterministic optimal cash injection allocation problem is an NP-hard mixed-integer linear program. However, modern optimization software enables the computation of very accurate solutions to this problem on a personal computer in a few seconds for network sizes comparable with the size of the US banking system. In addition, we address the problem of allocating the cash injection amount so as to minimize the number of nodes in default. For this problem, we develop two heuristic algorithms: a reweighted l1 minimization algorithm and a greedy algorithm. We illustrate these two algorithms using three synthetic network structures for which the optimal solution can be calculated exactly. We also compare these two algorithms on three types random networks which are more complex.

q-fin.RM↗

arXiv2014

Achieving Optimal Throughput and Near-Optimal Asymptotic Delay Performance in Multi-Channel Wireless Networks with Low Complexity: A Practical Greedy Scheduling Policy

In this paper, we focus on the scheduling problem in multi-channel wireless networks, e.g., the downlink of a single cell in fourth generation (4G) OFDM-based cellular networks. Our goal is to design practical scheduling policies that can achieve provably good performance in terms of both throughput and delay, at a low complexity. While a class of $O(n^{2.5} \log n)$-complexity hybrid scheduling policies are recently developed to guarantee both rate-function delay optimality (in the many-channel many-user asymptotic regime) and throughput optimality (in the general non-asymptotic setting), their practical complexity is typically high. To address this issue, we develop a simple greedy policy called Delay-based Server-Side-Greedy (D-SSG) with a \lower complexity $2n^2+2n$, and rigorously prove that D-SSG not only achieves throughput optimality, but also guarantees near-optimal asymptotic delay performance. Specifically, we show that the rate-function attained by D-SSG for any delay-violation threshold $b$, is no smaller than the maximum achievable rate-function by any scheduling policy for threshold $b-1$. Thus, we are able to achieve a reduction in complexity (from $O(n^{2.5} \log n)$ of the hybrid policies to $2n^2 + 2n$) with a minimal drop in the delay performance. More importantly, in practice, D-SSG generally has a substantially lower complexity than the hybrid policies that typically have a large constant factor hidden in the $O(\cdot)$ notation. Finally, we conduct numerical simulations to validate our theoretical results in various scenarios. The simulation results show that D-SSG not only guarantees a near-optimal rate-function, but also empirically is virtually indistinguishable from delay-optimal policies.

cs.NI↗

arXiv2013

Low-Complexity Scheduling Policies for Achieving Throughput and Asymptotic Delay Optimality in Multi-Channel Wireless Networks

In this paper, we study the scheduling problem for downlink transmission in a multi-channel (e.g., OFDM-based) wireless network. We focus on a single cell, with the aim of developing a unifying framework for designing low-complexity scheduling policies that can provide optimal performance in terms of both throughput and delay. We develop new easy-to-verify sufficient conditions for rate-function delay optimality (in the many-channel many-user asymptotic regime) and throughput optimality (in general non-asymptotic setting), respectively. The sufficient conditions allow us to prove rate-function delay optimality for a class of Oldest Packets First (OPF) policies and throughput optimality for a large class of Maximum Weight in the Fluid limit (MWF) policies, respectively. By exploiting the special features of our carefully chosen sufficient conditions and intelligently combining policies from the classes of OPF and MWF policies, we design hybrid policies that are both rate-function delay-optimal and throughput-optimal with a complexity of $O(n^{2.5} \log n)$, where $n$ is the number of channels or users. Our sufficient condition is also used to show that a previously proposed policy called Delay Weighted Matching (DWM) is rate-function delay-optimal. However, DWM incurs a high complexity of $O(n^5)$. Thus, our approach yields significantly lower complexity than the only previously designed delay and throughput optimal scheduling policy. We also conduct numerical experiments to validate our theoretical results.

cs.NI↗

arXiv2013

Online Energy Generation Scheduling for Microgrids with Intermittent Energy Sources and Co-Generation

Microgrids represent an emerging paradigm of future electric power systems that can utilize both distributed and centralized generations. Two recent trends in microgrids are the integration of local renewable energy sources (such as wind farms) and the use of co-generation (i.e., to supply both electricity and heat). However, these trends also bring unprecedented challenges to the design of intelligent control strategies for microgrids. Traditional generation scheduling paradigms rely on perfect prediction of future electricity supply and demand. They are no longer applicable to microgrids with unpredictable renewable energy supply and with co-generation (that needs to consider both electricity and heat demand). In this paper, we study online algorithms for the microgrid generation scheduling problem with intermittent renewable energy sources and co-generation, with the goal of maximizing the cost-savings with local generation. Based on the insights from the structure of the offline optimal solution, we propose a class of competitive online algorithms, called CHASE (Competitive Heuristic Algorithm for Scheduling Energy-generation), that track the offline optimal in an online fashion. Under typical settings, we show that CHASE achieves the best competitive ratio among all deterministic online algorithms, and the ratio is no larger than a small constant 3.

cs.OH↗