Adam Taylor

Maximizing renewable energy use with decentralized residential demand response

Due to steady urbanization, the electrical grid is facing significant changes in the supply of resources as well as changes in the type, scale, and patterns of residential user demand. To ensure sustainability and reliability of electricity provision in the growing cities, a significant increase in energy generated from renewable sources (e.g., wind, solar) is required. However, renewable energy supply is much more variable and intermittent than traditional supply, as it depends on changing weather conditions. In order to optimize residential energy usage, demand response (DR) techniques are being investigated to shift device usage to the periods of low demand. Currently most DR approaches focus on traditional DR goals, e.g., reducing usage at peak times and increasing it at off-peak times. More flexible and adaptive techniques are needed that can not only meet traditional DR requirements, but enable just-in-time use of renewable energy, rather than requiring its curtailment or using expensive and inefficient storage options. This paper proposes the use of decentralized learning-based multi-agent residential DR to enable more efficient integration of renewable energy sources in the smart grid, in the presence of increased demand caused by high electric vehicle penetration. We evaluate the approach using real household usage data obtained from Irish smart meter trials and data on wind-generated energy from the Irish grid operator. We discuss advantages of the proposed decentralized approach and show that it is able to respond to multiple variable wind-generation patterns by shifting up to 35% of the overall energy usage to the periods of high wind availability.

Accelerating Learning in multi-objective systems through Transfer Learning

Large-scale, multi-agent systems are too complex for optimal control strategies to be known at design time and as a result good strategies must be learned at runtime. Learning in such systems, particularly those with multiple objectives, takes a considerable amount of time because of the size of the environment and dependencies between goals. Transfer Learning (TL) has been shown to reduce learning time in single-agent, single-objective applications. It is the process of sharing knowledge between two learning tasks called the source and target. The source is required to have been completed prior to the target task. This work proposes extending TL to multi-agent, multi-objective applications. To achieve this, an on-line version of TL called Parallel Transfer Learning (PTL) is presented. The issues involved in extending this algorithm to a multi-objective form are discussed. The effectiveness of this approach is evaluated in a smart grid scenario. When using PTL in this scenario learning is significantly accelerated. PTL achieves comparable performance to the base line in one third of the time.

Design of an automatic demand-side management system based on evolutionary algorithms

Demand-Side Management (DSM) refers to programs that aim to control the energy consumption at the customer side of the meter. Different techniques have been proposed to achieve this. Perhaps the most popular techniques are those based on smart pricing (e.g., critical-peak pricing, real-time pricing). The idea, in a nutshell, is to encourage end users to shift their load consumption based on the price at a particular time (e.g., the higher the price, the less number of electric appliances are expected to be turned on). Motivated by these techniques (e.g., a strong positive correlation between the number of appliances being used and the electricity cost), we propose the use of an stochastic evolutionary-based optimisation technique, Evolutionary Algorithms, to automatically generate optimal, or nearly optimal, solutions that represent schedules to charge a number of electric vehicles (EVs) with two goals: (a) that each EV is as fully charged as possible at time of departure, and (b) to avoid charging them at the same time, whenever possible (e.g., load reduction at the transformer level). Instead of using a price signal to shift load consumption, we achieve this by considering what all the EVs might do at a particular time, rather than considering an interaction between an utility company and its user, as normally adopted in DSM programs. We argue that exploiting the interaction of these EVs is crucial at achieving excellent results because it carries the notion of smart pricing (e.g., balance energy usage), which is highly popular in DSM systems. Thus, the main contribution of this work is the notion of load shifting, borrowed from smart pricing methods, implemented in an evolutionary-based algorithm to automatically generate optimal solutions. To test our proposed approach, we used a dynamic scenario, where the state of charge of each EV is different for every day of our 28 days testing period. The results obtained by our proposed approach are highly encouraging in both: EVs being almost fully charged at time of the departure and the transformer load being reduced as a result of avoiding turning on the EVs at the same time.

Multi-agent Collaboration for Conflict Management in Residential Demand Response

Abstract Balancing electricity supply and consumption improves stability and performance of an electricity Grid. Demand-Response (DR) mechanisms are used to optimize energy consumption patterns by shifting non-critical electrical energy demand to times of low electricity demand (off-peak). Market penetration of electrical loads from Electrical Vehicles (EVs) has significantly increased residential demand, with a direct impact on the grid’s performance and effectiveness. By using multi-agent planning and scheduling algorithms such as Parallel Monte-Carlo Tree Search (P-MCTS) in DR, EVs can coordinate their actions and reschedule their consumption pattern. P-MCTS has been used to decentralize consumption planning, scheduling the optimum consumption pattern for each EV. However, a lack of coordination and collaboration limits its reliability in emergent situations, since agents’ sub-optimal solutions are not guaranteed to aggregate to an optimized overall grid solution. This paper describes Collaborative P-MCTS (CP-MCTS), which enables EVs to actively affect the planning process and resolve their conflicts via negotiation and optimizes the final consumption pattern using collective knowledge obtained during the negotiation. The negotiation algorithm supports agents to actively participate in collaboration, arguing about their stance and making new proposals. The results obtained show a significant load-shifting in peak times, a smoother load curve, and improved charging fairness and flexibility.

Reputation-Based Trust Management for Distributed Spectrum Sensing

One of the solutions to the hidden node problem in Cognitive Radio (CR) networks is to construct a global radio environment map (REM) hosted on a central controlling server. With this approach, the responsibility of sensing the radio environment can be distributed among all the nodes in the cognitive radio network. This introduces vulnerability because the server depends on the participating nodes to provide honest and accurate spectrum sense information. This research develops a reputation-based security mechanism that protects the radio environment map against falsified spectrum information that may be provided by malicious members of the network.